diff --git a/index.qmd b/index.qmd
index ac19a0e..ae6617e 100644
--- a/index.qmd
+++ b/index.qmd
@@ -13,6 +13,17 @@ development problems. In order to highlight the versatility of that package,
 we have developed a collection of case studies covering a diverse set of 
 clinical questions that were addressed via Bayesian modelling with the `brms` package. 
 
+::: {.content-visible when-profile="public"}
+::: {.callout-tip}
+## Short course at JSM -- Portland, OR -- August 5th 2024
+
+We will offer a short course based on this material at the 2024 Joint Statistical Meetings in Portland on August 5. The materials are available here:
+
+- [Slides](workshops/jsm2024/slides/bamdd_jsm2024.pdf) & [additional material (see readme)](https://github.com/Novartis/bamdd/tree/main/workshops/jsm2024)
+
+:::
+:::
+
 ## Navigating the site
 
 The material is organized as follows:
@@ -26,6 +37,7 @@ studies. You can find a [listing with descriptions on this page](src/02_case_stu
 as exposing and injecting custom stan code to `brms` models,
 and efficient parallel computation to support sampling in `brms`.
 
+
 ## Updates
 
 This web-site is intended as a live document with updates as
@@ -34,6 +46,7 @@ appropiate. Key changes to the web-site are tracked here:
 
 
 ::: {.content-visible when-profile="public"}
+- 31st July 2024: Linked materials from JSM Portland 2024 short course
 - 5th June 2024: Added @sec-pos on assessing probability of success of
   in Phase-III based on a single-arm trial in Phase-II
 - 29th April 2024: Third edition course from Paul Bürkner with the new
diff --git a/src/01b_basic_workflow.qmd b/src/01b_basic_workflow.qmd
index 32b69cc..d58c430 100644
--- a/src/01b_basic_workflow.qmd
+++ b/src/01b_basic_workflow.qmd
@@ -91,7 +91,8 @@ set.seed(5886935)
 #| eval: true 
 #| include: false
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 As `brms` models are translated to Stan model files, which must be
diff --git a/src/01c_priors.qmd b/src/01c_priors.qmd
index f4f9fb0..a174baa 100644
--- a/src/01c_priors.qmd
+++ b/src/01c_priors.qmd
@@ -9,7 +9,10 @@ bibliography: references.bib
 
 # Model setup & priors {#sec-model-priors}
 
-```{r, include=FALSE}
+```{r, eval=TRUE,echo=TRUE,message=FALSE,warning=FALSE}
+#| code-fold: true
+#| code-summary: "Show R setup"
+
 library(ggplot2)
 library(dplyr)
 library(knitr)
@@ -31,7 +34,8 @@ theme_set(theme_bw(12))
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 Within the Bayesian regression modeling in Stan framework `brms`
diff --git a/src/02a_meta_analysis.qmd b/src/02a_meta_analysis.qmd
index 2542b5f..2ab8bc8 100644
--- a/src/02a_meta_analysis.qmd
+++ b/src/02a_meta_analysis.qmd
@@ -46,7 +46,8 @@ set.seed(593467)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 ## Background
diff --git a/src/02ab_meta_analysis_trtdiff.qmd b/src/02ab_meta_analysis_trtdiff.qmd
index d7ad071..dcb4851 100644
--- a/src/02ab_meta_analysis_trtdiff.qmd
+++ b/src/02ab_meta_analysis_trtdiff.qmd
@@ -24,7 +24,8 @@ set.seed(979356)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 ## Background
diff --git a/src/02ac_meta_analysis_strata.qmd b/src/02ac_meta_analysis_strata.qmd
index d937060..66f15c1 100644
--- a/src/02ac_meta_analysis_strata.qmd
+++ b/src/02ac_meta_analysis_strata.qmd
@@ -56,7 +56,8 @@ options(width=120, digits=2)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 ## Background
diff --git a/src/02b_dose_finding.qmd b/src/02b_dose_finding.qmd
index 029708b..3594fc7 100644
--- a/src/02b_dose_finding.qmd
+++ b/src/02b_dose_finding.qmd
@@ -52,7 +52,8 @@ set.seed(8979476)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 ```{r get_annualized_rates}
diff --git a/src/02c_dose_escalation.qmd b/src/02c_dose_escalation.qmd
index 7d9b518..0103dc0 100644
--- a/src/02c_dose_escalation.qmd
+++ b/src/02c_dose_escalation.qmd
@@ -72,7 +72,8 @@ set.seed(8794567)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 Such a model is straightforward to implement in `brms`. Below, we use a nonlinear formula specification, in order to allow the prior for the intercept to be specified on the log scale. 
diff --git a/src/02cb_tte_dose_escalation.qmd b/src/02cb_tte_dose_escalation.qmd
index 9c0680a..478bc41 100644
--- a/src/02cb_tte_dose_escalation.qmd
+++ b/src/02cb_tte_dose_escalation.qmd
@@ -144,7 +144,8 @@ gt_format <- function(x) {
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 ## Example trial
diff --git a/src/02e_multiple_imputation.qmd b/src/02e_multiple_imputation.qmd
index a11ac5e..0f9e98e 100644
--- a/src/02e_multiple_imputation.qmd
+++ b/src/02e_multiple_imputation.qmd
@@ -76,7 +76,8 @@ options(brms.normalize=FALSE)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 Let us consider some simulated data for a trial in chronic obstructive
diff --git a/src/02g_longitudinal.qmd b/src/02g_longitudinal.qmd
index 67c3bf1..cf5ae00 100644
--- a/src/02g_longitudinal.qmd
+++ b/src/02g_longitudinal.qmd
@@ -45,7 +45,8 @@ control_args <- list(adapt_delta = 0.95)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 ```{r get_data, echo = TRUE}
diff --git a/src/02h_mmrm.qmd b/src/02h_mmrm.qmd
index 213ed58..f8d1ffb 100644
--- a/src/02h_mmrm.qmd
+++ b/src/02h_mmrm.qmd
@@ -51,7 +51,8 @@ options(width=120)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 ```{r include=FALSE}
diff --git a/src/02i_time_to_event.qmd b/src/02i_time_to_event.qmd
index 735ac89..bfc0869 100644
--- a/src/02i_time_to_event.qmd
+++ b/src/02i_time_to_event.qmd
@@ -58,7 +58,8 @@ options(width=120)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 
diff --git a/src/02j_network_meta_analysis.qmd b/src/02j_network_meta_analysis.qmd
index de01414..796b37c 100644
--- a/src/02j_network_meta_analysis.qmd
+++ b/src/02j_network_meta_analysis.qmd
@@ -38,7 +38,8 @@ control_args <- list(adapt_delta=0.95)
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 
diff --git a/src/02l_single_arm_pos.qmd b/src/02l_single_arm_pos.qmd
index f0f317b..5044318 100644
--- a/src/02l_single_arm_pos.qmd
+++ b/src/02l_single_arm_pos.qmd
@@ -47,7 +47,8 @@ theme_set(theme_bw(base_size=18))
 
 ```{r, include=FALSE, echo=FALSE, eval=TRUE}
 # invisible to the reader additional setup steps, which are optional
-{{< include setup.R >}}
+# {{< include setup.R >}}
+source("setup.R")
 ```
 
 
diff --git a/workshops/jsm2024/README.md b/workshops/jsm2024/README.md
new file mode 100644
index 0000000..7cfa042
--- /dev/null
+++ b/workshops/jsm2024/README.md
@@ -0,0 +1,28 @@
+# Course materials 
+
+These are the materials accompanying the short course "Applied Modelling in Drug Development using brms" at the Joint Statistical Meetings in Portland, OR on August 5, 2024. 
+
+Instructors:
+- David Ohlssen
+- Andrew Bean
+- Bjoern Holzhauer
+
+Additional contributors:
+- Paul Buerkner
+- Sebastian Weber
+- Lukas Widmer
+- Cong Zhang
+
+## Folder structure
+
+- `schedule.png` has the course schedule
+- `slides/bamdd_jsm2024.pdf` is the main slide deck for the course
+- `slides/R/` is a directory containing the R code from the case studies presented in the course
+- `exercises/` contains two sets of hands-on exercises in the form of Quarto files 
+- `exercises/solutions` has solutions from the organizers
+
+## Exercise instructions
+
+Course participants can find the exercises in the shared Posit Cloud space for the course (link provided during the course). See slides 38-44 in the main slides for instructions.
+
+
diff --git a/workshops/jsm2024/exercises/ex1_historical_control.qmd b/workshops/jsm2024/exercises/ex1_historical_control.qmd
new file mode 100644
index 0000000..2a2f69d
--- /dev/null
+++ b/workshops/jsm2024/exercises/ex1_historical_control.qmd
@@ -0,0 +1,154 @@
+---
+title: 'brms exercises: historical controls'
+author: 'your-name-here'
+date: today
+output: 
+  html_document:
+    toc: true
+    embed-resources: true
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## Background
+
+These exercises accompany the case study [Use of Historical Control
+Data](TODO:link) as part of the training course "Workshop
+on applied modeling in drug development using brms."
+
+## Preliminary code
+
+First load the required packages and set some options as described in the case study.
+
+```{r, warning = FALSE, message = FALSE}
+here::i_am("exercises/ex1_historical_control.qmd")
+library(here)
+
+library(ggplot2)
+library(dplyr)
+library(knitr)
+library(brms)
+library(posterior)
+library(bayesplot)
+library(RBesT)
+theme_set(theme_bw())
+
+options(
+  # how many processor cores would you like to use?
+  mc.cores = 4, 
+  # how would you like to access Stan?
+  brms.backend = "cmdstanr",
+  # cache model binaries
+  cmdstanr_write_stan_file_dir=here::here("_brms-cache"),
+  # no need to normalize likelihoods
+  brms.normalize = FALSE,
+  # when you are storing your model to file, 
+  # how shall it be updated?
+  brms.file_refit = "on_change"  
+  # alternatives: "never", "always"
+  # use "never" for production
+)
+
+set.seed(254335)
+```
+
+Then create the dataset used in the example:
+
+```{r}
+AS_region <- bind_cols(RBesT::AS, region=sample(c("asia", "europe", "north_america"), 8, TRUE))
+kable(AS_region)
+```
+
+And fit the model as shown in the case study:
+
+```{r}
+model <- bf(r | trials(n) ~ 1 + (1 | study), family=binomial)
+
+model_prior <- prior(normal(0, 2), class="Intercept") +
+    prior(normal(0, 1), class="sd", coef="Intercept", group="study")
+
+map_mc_brms  <- brm(model, AS_region, prior = model_prior,
+                    seed = 4767,
+                    silent = 2, refresh = 0)
+
+```
+
+## Exercise 1
+
+Create a posterior predictive check based on the predictive
+distribution for the response rate.  
+Steps:
+* Use `posterior_predict` to create samples from the predictive
+  distribution of outcomes per trial.
+* Use `sweep(predictive, 2, AS_region$n, "/")` to convert these
+  samples from the predictive distribution of the outcome counts to
+  samples from the predictive distribution for responder rates.
+* Use `ppc_intervals` from `bayesplot` to create a plot showing your
+  results.
+    
+```{r}
+# Your solution here -----------------------------------------------------------
+
+
+```
+
+
+## Exercise 2
+
+Redo the analysis with region, but treat region as a fixed
+   effect. Evaluate the informativeness of the obtained MAP priors.
+   The model formula for `brms` should look like `region_model_fixed
+   <- bf(r | trials(n) ~ 1 + region + (1 | study), family=binomial)`.
+Steps:
+* Consider the prior for the region fixed effect first. The reference
+  region is included in the intercept. The reference region is
+  implicitly defined by the first level of the variable region when
+  defined as `factor`.
+  - Define `asia` to be the reference region in the example. Also
+    include a level `other` in the set of levels.
+  - Assume that an odds-ratio of $2$ between regions can be seen as
+    very large such that a prior of $\mbox{N}(0, (\log(2)/1.96)^2)$
+    for the region main effect is adequate.
+* Obtain the MAP prior for each region by using the
+  `AS_region_all` data frame defined below and apply
+  `posterior_linpred` as shown above.
+* Convert the MCMC samples from the MAP prior distribution into
+  mixture distributions with the same code as above.
+* Calculate the ESS for each prior distribution with the `ess`
+  function from `RBesT`.
+	
+```{r}
+
+AS_region_all <- data.frame(region=c("asia", "europe", "north_america", "other")) %>%
+    mutate(study=paste("new_study", region, sep="_"), r=0, n=6)
+
+# Your solution here -----------------------------------------------------------
+
+
+```
+	
+   
+## Exercise 3
+
+Run the analysis for the normal endpoint in the `crohn` data set of
+`RBesT`. Refer to the `RBesT` vignette for a [normal endpoint](https://cran.r-project.org/web/packages/RBesT/vignettes/introduction.html)
+   on more details and context.  
+Steps:
+* Use as `family=gaussian` and use the `se` response modifier in place
+  of `trials` to specify a known standard error.
+* Use the same priors as proposed in the vignette.
+* Compare the obtained MAP prior (in MCMC sample form) from `RBesT`
+  and `brms`.
+    
+```{r}
+crohn <- RBesT::crohn
+
+# Your solution here -----------------------------------------------------------
+
+
+```
+
+
+
diff --git a/workshops/jsm2024/exercises/ex2_dose_finding.qmd b/workshops/jsm2024/exercises/ex2_dose_finding.qmd
new file mode 100644
index 0000000..58aaf51
--- /dev/null
+++ b/workshops/jsm2024/exercises/ex2_dose_finding.qmd
@@ -0,0 +1,342 @@
+---
+title: 'brms exercises: dose finding'
+author: 'your-name-here'
+date: today
+output: 
+  html_document:
+    toc: true
+    embed-resources: true
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## Background
+
+This exercise accompanies the [Dose Finding](https://opensource.nibr.com/bamdd/src/02b_dose_finding.html) case study as part of the training course "Workshop on applied modeling in drug development using brms."
+
+## Preliminary code
+
+First load the required packages and set some options as described in the case study.
+
+```{r, warning = FALSE, message = FALSE}
+here::i_am("exercises/ex2_dose_finding.qmd")
+library(here)
+
+library(tidyverse)
+library(brms)
+library(tidybayes)
+library(ggrepel)
+library(patchwork)
+library(ggplot2)
+library(ggdist)
+
+# Set defaults for ggplot2 ----
+theme_set(theme_bw(base_size=18) +
+          theme(legend.position = "none"))
+
+scale_colour_discrete <- function(...) {
+  # Alternative: ggsci::scale_color_nejm(...)
+  # scale_colour_brewer(..., palette="Set1")
+  ggthemes::scale_colour_colorblind(...)
+}
+scale_fill_discrete <- function(...) {
+  # Alternative: ggsci::scale_fill_nejm(...)
+  #scale_fill_brewer(..., palette="Set1")
+  ggthemes::scale_fill_colorblind(...)
+}
+scale_colour_continuous <- function(...) {
+  scale_colour_viridis_c(..., option="turbo")
+}
+update_geom_defaults("point", list(size=2))
+update_geom_defaults("line", list(size=1.5))
+
+options(
+  # how many processor cores would you like to use?
+  mc.cores = 4, 
+  # how would you like to access Stan?
+  brms.backend = "cmdstanr",
+  # cache model binaries
+  cmdstanr_write_stan_file_dir=here::here("_brms-cache"),
+  # no need to normalize likelihoods
+  brms.normalize = FALSE,
+  # when you are storing your model to file, 
+  # how shall it be updated?
+  brms.file_refit = "on_change"  
+  # alternatives: "never", "always"
+  # use "never" for production
+)
+
+set.seed(254335)
+```
+
+## Excercise: 
+
+### Exercise 1: Peanut allergy
+
+In a hypothetical phase 2b trial children and adolescents with peanut allergy 
+were randomly assigned to placebo or 5 doses (5 to 300 mg) of a new drug.  
+After 26 weeks the patients underwent a double-blind placebo-controlled
+food challenge and the primary endpoint was the proportion of patients that
+could ingest 600 mg or more of peanut protein without experiencing dose-limiting
+symptoms. The plots below show an overview of the data. Note that no placebo
+patients were considered "responders" per the primary endpoint definition.
+
+```{r peanutdata, class.source = 'fold-hide'}
+peanut <- tibble(
+  TRT01P = structure(c(
+    6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
+    6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
+    4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
+    4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
+    3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
+    3L, 3L, 3L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
+    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L
+  ),levels = c("PBO", "5 mg", "15 mg", "50 mg", "150 mg", "300 mg"), class = "factor"),
+  dose = c(
+    300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L,
+    300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L,
+    300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 150L, 150L, 150L, 150L, 150L, 150L, 150L,
+    150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L,
+    150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L,
+    150L, 150L, 150L, 150L, 150L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L,
+    50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L,
+    50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L,
+    15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L,
+    15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
+    0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
+    0L, 0L),
+  AVAL = c(
+    1000L, 100L, 0L, 600L, 600L, 300L, 300L, 10L, 10L, 100L, 1000L, 300L, 10L, 1000L, 1000L, 1000L, 3L, 3L, 600L, 300L,
+    1000L, 1000L, 100L, 1000L, 600L, 600L, 1000L, 1000L, 1000L, 300L, 600L, 1000L, 1000L, 1000L, 1000L, 1000L, 300L,
+    1000L, 600L, 1000L, 300L, 1000L, 600L, 600L, 1000L, 1000L, 600L, 1000L, 1000L, 1000L, 1000L, 600L, 1000L, 1000L,
+    1000L, 0L, 600L, 300L, 1000L, 1000L, 1000L, 100L, 1000L, 1000L, 600L, 1000L, 1000L, 1000L, 600L, 300L, 600L, 600L,
+    100L, 600L, 1000L, 300L, 10L, 3L, 1000L, 300L, 300L, 1000L, 300L, 300L, 10L, 1000L, 1000L, 10L, 10L, 600L, 3L, 10L,
+    600L, 600L, 600L, 1000L, 100L, 1000L, 1000L, 10L, 1000L, 3L, 10L, 1000L, 100L, 1000L, 100L, 10L, 300L, 10L, 100L,
+    1000L, 0L, 1000L, 100L, 3L, 10L, 100L, 100L, 300L, 1000L, 1000L, 1000L, 10L, 1000L, 3L, 3L, 600L, 600L, 10L, 3L,
+    600L, 600L, 300L, 300L, 1000L, 3L, 3L, 1000L, 10L, 1000L, 1000L, 600L, 100L, 300L, 600L, 10L, 100L, 0L, 100L, 3L,
+    0L, 10L, 3L, 600L, 300L, 300L, 300L, 600L, 300L, 100L, 3L, 0L, 10L, 600L, 300L, 10L, 300L, 600L, 1000L, 600L, 600L,
+    0L, 0L, 600L, 600L, 600L, 0L, 0L, 300L, 100L, 0L, 10L, 300L, 1000L, 300L, 600L, 600L, 300L, 10L, 600L, 100L, 100L,
+    300L, 3L, 3L, 300L, 1000L, 10L, 3L, 100L, 3L, 100L, 100L, 300L, 3L, 3L, 600L, 300L, 3L, 3L, 3L, 300L, 3L, 0L, 10L,
+    3L, 300L, 10L, 10L, 600L, 0L, 300L, 600L, 0L, 0L, 100L, 100L, 10L, 100L, 10L, 100L, 600L, 0L, 600L, 0L, 10L, 100L,
+    0L, 0L, 0L, 0L, 3L, 10L, 3L, 300L, 600L, 0L, 0L, 300L, 10L, 10L, 100L, 300L, 0L, 0L, 0L, 3L, 0L, 0L, 10L, 0L, 300L,
+    3L, 0L, 0L, 0L, 0L, 100L, 3L, 0L, 3L, 10L, 10L, 3L, 0L, 3L, 10L, 3L, 0L, 0L, 3L, 100L, 0L, 0L, 300L, 0L, 0L, 0L,
+    0L, 0L, 0L, 0L, 3L, 0L, 3L, 0L, 0L, 0L, 0L),
+  PARAM = structure(
+    c(
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = "Tolerated amount of peanut protein (mg)", class = "factor"),
+  USUBJID = c(
+    129L, 103L, 104L, 185L, 34L, 15L, 140L, 151L, 7L, 144L, 200L, 23L, 138L, 115L, 255L, 147L, 224L, 101L, 156L, 284L,
+    136L, 248L, 179L, 298L, 168L, 295L, 289L, 241L, 36L, 27L, 123L, 266L, 11L, 291L, 236L, 130L, 173L, 195L, 203L, 160L,
+    274L, 167L, 290L, 94L, 9L, 269L, 122L, 135L, 64L, 26L, 95L, 10L, 5L, 234L, 161L, 299L, 88L, 69L, 35L, 233L, 286L,
+    85L, 91L, 189L, 80L, 152L, 223L, 287L, 244L, 57L, 108L, 18L, 62L, 157L, 300L, 283L, 164L, 243L, 89L, 220L, 24L, 271L,
+    166L, 118L, 201L, 127L, 121L, 41L, 267L, 213L, 49L, 73L, 202L, 134L, 112L, 25L, 227L, 29L, 251L, 273L, 119L, 132L,
+    74L, 270L, 83L, 37L, 181L, 258L, 253L, 48L, 120L, 54L, 277L, 176L, 65L, 264L, 107L, 171L, 262L, 162L, 187L, 272L,
+    288L, 294L, 245L, 109L, 172L, 204L, 275L, 22L, 66L, 186L, 247L, 17L, 149L, 141L, 177L, 280L, 216L, 40L, 75L, 263L,
+    246L, 14L, 81L, 260L, 153L, 45L, 237L, 8L, 117L, 86L, 296L, 146L, 154L, 116L, 38L, 100L, 191L, 175L, 92L, 158L, 192L,
+    180L, 256L, 254L, 125L, 222L, 145L, 261L, 155L, 159L, 3L, 206L, 278L, 19L, 31L, 63L, 208L, 55L, 259L, 218L, 111L,
+    226L, 33L, 2L, 44L, 297L, 53L, 87L, 16L, 28L, 90L, 207L, 56L, 137L, 128L, 178L, 142L, 143L, 148L, 193L, 229L, 265L,
+    97L, 252L, 205L, 150L, 165L, 188L, 52L, 99L, 93L, 1L, 221L, 124L, 210L, 6L, 232L, 21L, 211L, 163L, 96L, 60L, 183L,
+    190L, 242L, 42L, 46L, 67L, 126L, 209L, 72L, 194L, 238L, 184L, 39L, 105L, 249L, 61L, 113L, 30L, 77L, 12L, 4L, 51L,
+    139L, 20L, 268L, 215L, 292L, 217L, 199L, 32L, 276L, 47L, 225L, 230L, 79L, 71L, 98L, 50L, 13L, 76L, 231L, 250L, 58L,
+    68L, 239L, 198L, 293L, 212L, 110L, 59L, 182L, 133L, 170L, 43L, 282L, 281L, 131L, 114L, 196L, 214L, 285L, 70L, 102L,
+    279L, 106L, 197L, 257L, 228L, 84L, 235L, 78L, 169L, 240L, 219L, 174L, 82L),
+  CRIT1 = structure(c(
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = "Tolerating >=600 mg of peanut protein without dose-limiting symptoms", class = "factor"),
+  CRIT1FL = structure(c(
+    2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L,
+    2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
+    2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
+    1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L,
+    2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
+    2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = c("N", "Y"), class = "factor"),
+  CRIT2 = structure(c(
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = "Tolerating >=1000 mg of peanut protein without dose-limiting symptoms", class = "factor"),
+  CRIT2FL = structure(c(
+    2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L,
+    2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L,
+    1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
+    1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L,
+    2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = c("N", "Y"), class = "factor" ) )
+
+peanut %>%
+  ggplot(aes(x=factor(AVAL), fill=TRT01P)) +
+  geom_bar( position=position_dodge(preserve = "single")) +
+  scale_fill_manual(values=c("royalblue", "#fb6a4a", "#ef3b2c", "#cb181d", "#a50f15", "#67000d")) +
+  xlab("Peanut protein tolerated without dose-limiting symptoms (mg)") +
+  ylab("Patients") +
+  theme(legend.position="right")
+
+peanut %>%
+  group_by(TRT01P) %>%
+  summarize(proportion = sum(CRIT1FL=="Y") / n()) %>%
+  ggplot(aes(x=TRT01P, y=proportion, fill=TRT01P)) +
+  geom_bar(stat="identity", position=position_dodge()) +
+  geom_text(aes(label=scales::percent(proportion)), size=7, vjust=c(0, rep(1.5, 5))) +
+  scale_fill_manual(values=c("royalblue", "#fb6a4a", "#ef3b2c", "#cb181d", "#a50f15", "#67000d")) +
+  scale_y_continuous(breaks=seq(0, 0.7, 0.1), labels=scales::percent) +
+  xlab("Tolerating >=600 mg of peanut protein without dose-limiting symptoms") +
+  ylab("Percentage of patients")
+```
+
+#### Excercise 1A
+
+Fit a sigmoid Emax logistic regression model 
+(i.e. `family=binomial(link="logit")`). 
+To accelerate likelihood evaluations, first summarize data as "responders" `y`
+out of `n` patients per dose. We tell `brms` to use this information using 
+`y | trials(n) ~ ...`. 
+We expect the true placebo proportion to be around 0.05 (-2.944 on the logit 
+scale) with much more than 0.1 or much less than 0.02 considered unlikely.
+It is a-priori at least possible that there is a huge treatment effect such 
+as 95\% versus 5\% responders (difference on the log-scale close to 6),
+but we are at least mildly skeptical.
+The dose response is a-priori somewhat likely to follow a Emax curve (with Hill
+parameter near 1), but we wish to allow for the possibility of a steeper or 
+shallower curve. The dose with half the effect (ED50) might be near 15 mg, but 
+have considerable uncertainty around that.
+
+```{r peanutmodel1}
+model1 <- bf( #---- INSERT YOUR CODE HERE --- # ~ E0 + Emax * dose^h/(dose^h + ED50^h),
+              family= #---- INSERT YOUR CODE HERE --- # ,
+              nlf(h ~ exp(logh)), nlf(ED50 ~ exp(logED50)),
+              E0 ~ 1, logED50 ~ 1, logh ~ 1, Emax ~ 1, 
+              nl=TRUE)
+
+priors1 <- prior(normal(-2.944, 0.38), nlpar="E0") +
+           prior(normal(0, 1), nlpar="logh") +
+           prior(normal(0, 6), nlpar="Emax") +
+           prior(normal(2.7, 2.5), nlpar="logED50")
+```
+
+Now fit the model
+```{r fitpeanutmodel1}
+brmfit1 <- brm(
+  formula = model1,
+  prior = priors1, 
+  data = peanut %>% group_by(TRT01P, dose) %>% summarize(y=sum(CRIT1FL=="Y"), n=n(), .groups="drop")
+)
+```
+
+Now use 
+`tibble(dose = seq(0, 300, 1), n=1) %>% tidybayes::add_epred_rvars(object=brmfit1, newdata=.)` 
+to obtain predicted proportions for every dose from 0 to 300 mg.
+Then, plot the curve of predicted proportions for each of these doses using 
+`ggplot2` and `ggdist` (using `ydist=.epred` in the aesthetics and the 
+`stat_lineribbon()` geom from the `ggdist` package).
+
+```{r plotmodel1preds}
+tibble(dose = seq(0, 300, 1), n=1) %>% 
+  tidybayes::add_epred_rvars(object=brmfit1, newdata=.) 
+  # ---- INSERT YOUR CODE HERE ---- #
+```
+
+If you prefer, replace the default fill colors e.g. with shades of blue
+using `+ scale_fill_brewer(palette="Blues")
+
+Next obtain the posterior distribution for the difference in proportions for
+each of these dose levels compared with placebo.
+
+```{r model1diffs}
+# ---- INSERT YOUR CODE HERE ---- #
+```
+
+#### Excercise 1B* (optional)
+
+Try to perform a more efficient statistical analysis by either using an ordinal
+outcome or treating the data as interval censored.
+
+Try treating the data about the logarithm of the amount of protein 
+tolerated as interval censored 
+($-\infty$ to <log(3), >= log(3) to <log(10) mg, ...) using
+`logAVAL | cens("interval", logAVALnext) ~` with `family = gaussian()`.
+For the latter approach you might have to set `log(0)` to a very low number
+such as -28 (approximate log(weight) of one single peanut protein 
+molecule) and assume the upper interval end when a patient could tolerate
+1000 mg to, say, `log(30000)` (approximately 100 peanut kernels). This
+achieves approximately the same thing as setting these to `-Inf` and `Inf`,
+but is handled better by `brms`/`Stan`.
+
+How would you change the prior distributions in this case?
+
+```{r lognormal}
+# ---- INSERT YOUR CODE HERE ---- #
+```
+
+
+Now use an ordinal
+outcome via `family = cumulative(link = "logit", threshold = "flexible")`.
+Details of this model are described in 
+[a journal article](https://doi.org/10.1177/2515245918823199), for which there 
+is also [a PsyArXiv preprint](https://doi.org/10.31234/osf.io/x8swp) in case
+you do not have access to the journal. 
+
+Note that the placebo response is described by a series of $K-1$ ordered 
+thresholds $\theta_1, \ldots, \theta_{K-1}$ on the logit scale for $K$ ordered 
+categories. For the placebo group, the probability of being in categories 
+$k=1, \ldots, K-1$ is be given by $\text{logit}^{-1} \theta_k$ and for category 
+$K$ by $1-\text{logit}^{-1} \theta_{K-1}$. In this case, these parameters will
+appear in `summary(brmfit3)` as `Intercept[1]`, ..., `Intercept[6]`.
+
+How would you change the model and the prior distributions in this case?
+
+```{r ordinal}
+# ---- INSERT YOUR CODE HERE ---- #
+```
+
+Note, if we had a baseline amount of protein tolerated, we could treat this
+as a monotonic covariate e.g. using `mo(BASE)` or assume a particular functional
+form.
diff --git a/workshops/jsm2024/exercises/solutions/ex1_historical_control.qmd b/workshops/jsm2024/exercises/solutions/ex1_historical_control.qmd
new file mode 100644
index 0000000..9f8e6ce
--- /dev/null
+++ b/workshops/jsm2024/exercises/solutions/ex1_historical_control.qmd
@@ -0,0 +1,237 @@
+---
+title: 'brms exercises: historical controls'
+author: 'your-name-here'
+date: today
+output: 
+  html_document:
+    toc: true
+    embed-resources: true
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## Background
+
+These exercises accompany the case study [Use of Historical Control
+Data](TODO:link) as part of the training course "Workshop
+on applied modeling in drug development using brms."
+
+## Preliminary code
+
+First load the required packages and set some options as described in the case study.
+
+```{r, warning = FALSE, message = FALSE}
+here::i_am("exercises/solutions/ex1_historical_control.qmd")
+library(here)
+
+library(ggplot2)
+library(dplyr)
+library(knitr)
+library(brms)
+library(posterior)
+library(bayesplot)
+library(RBesT)
+theme_set(theme_bw())
+
+options(
+  # how many processor cores would you like to use?
+  mc.cores = 4, 
+  # how would you like to access Stan?
+  brms.backend = "cmdstanr",
+  # cache model binaries
+  cmdstanr_write_stan_file_dir=here::here("_brms-cache"),
+  # no need to normalize likelihoods
+  brms.normalize = FALSE,
+  # when you are storing your model to file, 
+  # how shall it be updated?
+  brms.file_refit = "on_change"  
+  # alternatives: "never", "always"
+  # use "never" for production
+)
+
+set.seed(254335)
+```
+
+Then create the dataset used in the example:
+
+```{r}
+AS_region <- bind_cols(RBesT::AS, region=sample(c("asia", "europe", "north_america"), 8, TRUE))
+kable(AS_region)
+```
+
+And fit the model as shown in the case study:
+
+```{r}
+model <- bf(r | trials(n) ~ 1 + (1 | study), family=binomial)
+
+model_prior <- prior(normal(0, 2), class="Intercept") +
+    prior(normal(0, 1), class="sd", coef="Intercept", group="study")
+
+map_mc_brms  <- brm(model, AS_region, prior = model_prior,
+                    seed = 4767,
+                    silent = 2, refresh = 0)
+
+```
+
+## Exercise 1
+
+Create a posterior predictive check based on the predictive
+distribution for the response rate.  
+Steps:
+* Use `posterior_predict` to create samples from the predictive
+  distribution of outcomes per trial.
+* Use `sweep(predictive, 2, AS_region$n, "/")` to convert these
+  samples from the predictive distribution of the outcome counts to
+  samples from the predictive distribution for responder rates.
+* Use `ppc_intervals` from `bayesplot` to create a plot showing your
+  results.
+    
+```{r}
+# Your solution here -----------------------------------------------------------
+
+pp_count_AS_region <- posterior_predict(map_mc_brms)
+
+pp_rate_AS_region <- sweep(pp_count_AS_region, 2, AS_region$n, "/")
+
+y_obs_rate <- with(AS_region, r / n)
+
+ppc_intervals(y_obs_rate, pp_rate_AS_region)  +
+    scale_x_continuous("Study", breaks=1:nrow(AS_region), labels=AS_region$study) +
+    ylab("Responder Rate") +
+    coord_flip() +
+    theme(legend.position="right",
+          # suppress vertical grid lines for better readability of intervals
+          panel.grid.major.y = element_blank())
+
+```
+
+
+## Exercise 2
+
+Redo the analysis with region, but treat region as a fixed
+   effect. Evaluate the informativeness of the obtained MAP priors.
+   The model formula for `brms` should look like `region_model_fixed
+   <- bf(r | trials(n) ~ 1 + region + (1 | study), family=binomial)`.
+Steps:
+* Consider the prior for the region fixed effect first. The reference
+  region is included in the intercept. The reference region is
+  implicitly defined by the first level of the variable region when
+  defined as `factor`.
+  - Define `asia` to be the reference region in the example. Also
+    include a level `other` in the set of levels.
+  - Assume that an odds-ratio of $2$ between regions can be seen as
+    very large such that a prior of $\mbox{N}(0, (\log(2)/1.96)^2)$
+    for the region main effect is adequate.
+* Obtain the MAP prior for each region by using the
+  `AS_region_all` data frame defined below and apply
+  `posterior_linpred` as shown above.
+* Convert the MCMC samples from the MAP prior distribution into
+  mixture distributions with the same code as above.
+* Calculate the ESS for each prior distribution with the `ess`
+  function from `RBesT`.
+	
+```{r}
+
+AS_region_all <- data.frame(region=c("asia", "europe", "north_america", "other")) %>%
+    mutate(study=paste("new_study", region, sep="_"), r=0, n=6)
+
+# Your solution here -----------------------------------------------------------
+
+## to get brms to include the other factor level in the model, we have
+## to add a fake row with region "other" and n=0
+AS_region_2 <- mutate(bind_rows(AS_region, mutate(AS_region_all, n=0)[4,]),
+                      region=factor(region, levels=c("asia", "europe", "north_america", "other")))
+
+str(AS_region_2)
+
+model_fixed <- bf(r | trials(n) ~ 1 + region + (1|study), family=binomial)
+
+get_prior(model_fixed, AS_region_2)
+
+model_fixed_prior <- prior(normal(0, 2), class="Intercept") +
+    prior(normal(0, 1), class="sd", coef="Intercept", group="study") +
+    prior(normal(0, log(2)/1.96), class="b")
+
+fixed_mc_brms  <- brm(model_fixed, AS_region_2, prior=model_fixed_prior,
+                      seed=4767,
+                      silent = 2, refresh = 0, control=list(adapt_delta=0.99))
+
+fixed_mc_brms
+
+post_regions <- posterior_linpred(fixed_mc_brms,
+                                  newdata=AS_region_all,
+                                  transform=TRUE,
+                                  allow_new_levels=TRUE,
+                                  sample_new_levels="gaussian")
+
+head(post_regions)
+
+colnames(post_regions) <- AS_region_all$region
+map_region <- list()
+for(r in AS_region_all$region) {
+    map_region[[r]] <- mixfit(post_regions[,r], type="beta", Nc=3, constrain_gt1=TRUE)
+}
+
+kable(bind_rows(lapply(map_region, summary), .id="MAP"), digits=3)
+
+sapply(map_region, ess)
+
+```
+	
+   
+## Exercise 3
+
+Run the analysis for the normal endpoint in the `crohn` data set of
+`RBesT`. Refer to the `RBesT` vignette for a [normal endpoint](https://cran.r-project.org/web/packages/RBesT/vignettes/introduction.html)
+   on more details and context.  
+Steps:
+* Use as `family=gaussian` and use the `se` response modifier in place
+  of `trials` to specify a known standard error.
+* Use the same priors as proposed in the vignette.
+* Compare the obtained MAP prior (in MCMC sample form) from `RBesT`
+  and `brms`.
+    
+```{r}
+crohn <- RBesT::crohn
+
+# Your solution here -----------------------------------------------------------
+
+crohn_sigma <- 88
+crohn$y.se <- crohn_sigma/sqrt(crohn$n)
+
+library(RBesT)
+set.seed(1234)
+rbest_normal_map_mcmc <- gMAP(cbind(y, y.se) ~ 1 | study, 
+                              weights=n, data=crohn,
+                              family=gaussian,
+                              beta.prior=cbind(0, crohn_sigma),
+                              tau.dist="HalfNormal",tau.prior=cbind(0,crohn_sigma/2))
+
+model_normal <- bf(y | se(y.se) ~ 1 + (1 | study), family=gaussian())
+
+prior_normal <- prior(normal(0, 88), class="Intercept") +
+    prior(normal(0, 88/2), class="sd", coef="Intercept", group="study")
+
+brms_normal_map_mcmc <- brm(model_normal, crohn, prior=prior_normal,
+                            seed=4767,
+                            silent = 2, refresh = 0, control=list(adapt_delta=0.99))
+
+## comparing the outputs we see that the random effect posterior
+## matches...
+rbest_normal_map_mcmc
+brms_normal_map_mcmc
+
+brms_normal_map <- posterior_epred(brms_normal_map_mcmc,
+                                   newdata=data.frame(study="new", n=1, y=0, y.se=88),
+                                   allow_new_levels=TRUE,
+                                   sample_new_levels="gaussian")
+
+## ... and the MAP prior is also the same
+summarise_draws(brms_normal_map, mean, sd, ~quantile(., probs = c(0.025, 0.5, 0.975)))
+
+```
+
+
+
diff --git a/workshops/jsm2024/exercises/solutions/ex2_dose_finding.qmd b/workshops/jsm2024/exercises/solutions/ex2_dose_finding.qmd
new file mode 100644
index 0000000..c836043
--- /dev/null
+++ b/workshops/jsm2024/exercises/solutions/ex2_dose_finding.qmd
@@ -0,0 +1,410 @@
+---
+title: 'brms exercises: dose finding'
+author: 'Björn Holzhauer'
+date: today
+output: 
+  html_document:
+    toc: true
+    embed-resources: true
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## Background
+
+This exercises accompany the case study [Dose Finding](https://opensource.nibr.com/bamdd/src/02b_dose_finding.html) as part of the training course "Workshop on applied modeling in drug development using brms."
+
+## Preliminary code
+
+First load the required packages and set some options as described in the case study.
+
+```{r, warning = FALSE, message = FALSE}
+here::i_am("exercises/solutions/ex2_dose_finding.qmd")
+library(here)
+library(tidyverse)
+library(brms)
+library(tidybayes)
+library(ggrepel)
+library(patchwork)
+library(ggplot2)
+library(ggdist)
+
+# Set defaults for ggplot2 ----
+theme_set(theme_bw(base_size=18) +
+          theme(legend.position = "bottom"))
+
+scale_colour_discrete <- function(...) {
+  # Alternative: ggsci::scale_color_nejm(...)
+  # scale_colour_brewer(..., palette="Set1")
+  ggthemes::scale_colour_colorblind(...)
+}
+scale_fill_discrete <- function(...) {
+  # Alternative: ggsci::scale_fill_nejm(...)
+  #scale_fill_brewer(..., palette="Set1")
+  ggthemes::scale_fill_colorblind(...)
+}
+scale_colour_continuous <- function(...) {
+  scale_colour_viridis_c(..., option="turbo")
+}
+update_geom_defaults("point", list(size=2))
+update_geom_defaults("line", list(size=1.5))
+
+options(
+  # how many processor cores would you like to use?
+  mc.cores = 4, 
+  # how would you like to access Stan?
+  brms.backend = "cmdstanr",
+  # cache model binaries
+  cmdstanr_write_stan_file_dir=here::here("_brms-cache"),
+  # no need to normalize likelihoods
+  brms.normalize = FALSE,
+  # when you are storing your model to file, 
+  # how shall it be updated?
+  brms.file_refit = "on_change"  
+  # alternatives: "never", "always"
+  # use "never" for production
+)
+
+set.seed(254335)
+```
+
+## Excercise: 
+
+### Exercise 1: Peanut allergy
+
+In a hypothetical phase 2b trial children and adolescents with peanut allergy 
+were randomly assigned to placebo or 5 doses (5 to 300 mg) of a new drug.  
+After 26 weeks the patients underwent a double-blind placebo-controlled
+food challenge and the primary endpoint was the proportion of patients that
+could ingest 600 mg or more of peanut protein without experiencing dose-limiting
+symptoms. The plots below show an overview of the data. Note that no placebo
+patients were considered "responders" per the primary endpoint definition.
+
+```{r peanutdata, class.source = 'fold-hide'}
+peanut <- tibble(
+  TRT01P = structure(c(
+    6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
+    6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
+    4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
+    4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
+    3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
+    3L, 3L, 3L, 3L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
+    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L
+  ),levels = c("PBO", "5 mg", "15 mg", "50 mg", "150 mg", "300 mg"), class = "factor"),
+  dose = c(
+    300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L,
+    300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L,
+    300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 300L, 150L, 150L, 150L, 150L, 150L, 150L, 150L,
+    150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L,
+    150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L, 150L,
+    150L, 150L, 150L, 150L, 150L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L,
+    50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L,
+    50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 50L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L,
+    15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L,
+    15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
+    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
+    0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
+    0L, 0L),
+  AVAL = c(
+    1000L, 100L, 0L, 600L, 600L, 300L, 300L, 10L, 10L, 100L, 1000L, 300L, 10L, 1000L, 1000L, 1000L, 3L, 3L, 600L, 300L,
+    1000L, 1000L, 100L, 1000L, 600L, 600L, 1000L, 1000L, 1000L, 300L, 600L, 1000L, 1000L, 1000L, 1000L, 1000L, 300L,
+    1000L, 600L, 1000L, 300L, 1000L, 600L, 600L, 1000L, 1000L, 600L, 1000L, 1000L, 1000L, 1000L, 600L, 1000L, 1000L,
+    1000L, 0L, 600L, 300L, 1000L, 1000L, 1000L, 100L, 1000L, 1000L, 600L, 1000L, 1000L, 1000L, 600L, 300L, 600L, 600L,
+    100L, 600L, 1000L, 300L, 10L, 3L, 1000L, 300L, 300L, 1000L, 300L, 300L, 10L, 1000L, 1000L, 10L, 10L, 600L, 3L, 10L,
+    600L, 600L, 600L, 1000L, 100L, 1000L, 1000L, 10L, 1000L, 3L, 10L, 1000L, 100L, 1000L, 100L, 10L, 300L, 10L, 100L,
+    1000L, 0L, 1000L, 100L, 3L, 10L, 100L, 100L, 300L, 1000L, 1000L, 1000L, 10L, 1000L, 3L, 3L, 600L, 600L, 10L, 3L,
+    600L, 600L, 300L, 300L, 1000L, 3L, 3L, 1000L, 10L, 1000L, 1000L, 600L, 100L, 300L, 600L, 10L, 100L, 0L, 100L, 3L,
+    0L, 10L, 3L, 600L, 300L, 300L, 300L, 600L, 300L, 100L, 3L, 0L, 10L, 600L, 300L, 10L, 300L, 600L, 1000L, 600L, 600L,
+    0L, 0L, 600L, 600L, 600L, 0L, 0L, 300L, 100L, 0L, 10L, 300L, 1000L, 300L, 600L, 600L, 300L, 10L, 600L, 100L, 100L,
+    300L, 3L, 3L, 300L, 1000L, 10L, 3L, 100L, 3L, 100L, 100L, 300L, 3L, 3L, 600L, 300L, 3L, 3L, 3L, 300L, 3L, 0L, 10L,
+    3L, 300L, 10L, 10L, 600L, 0L, 300L, 600L, 0L, 0L, 100L, 100L, 10L, 100L, 10L, 100L, 600L, 0L, 600L, 0L, 10L, 100L,
+    0L, 0L, 0L, 0L, 3L, 10L, 3L, 300L, 600L, 0L, 0L, 300L, 10L, 10L, 100L, 300L, 0L, 0L, 0L, 3L, 0L, 0L, 10L, 0L, 300L,
+    3L, 0L, 0L, 0L, 0L, 100L, 3L, 0L, 3L, 10L, 10L, 3L, 0L, 3L, 10L, 3L, 0L, 0L, 3L, 100L, 0L, 0L, 300L, 0L, 0L, 0L,
+    0L, 0L, 0L, 0L, 3L, 0L, 3L, 0L, 0L, 0L, 0L),
+  PARAM = structure(
+    c(
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+      1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = "Tolerated amount of peanut protein (mg)", class = "factor"),
+  USUBJID = c(
+    129L, 103L, 104L, 185L, 34L, 15L, 140L, 151L, 7L, 144L, 200L, 23L, 138L, 115L, 255L, 147L, 224L, 101L, 156L, 284L,
+    136L, 248L, 179L, 298L, 168L, 295L, 289L, 241L, 36L, 27L, 123L, 266L, 11L, 291L, 236L, 130L, 173L, 195L, 203L, 160L,
+    274L, 167L, 290L, 94L, 9L, 269L, 122L, 135L, 64L, 26L, 95L, 10L, 5L, 234L, 161L, 299L, 88L, 69L, 35L, 233L, 286L,
+    85L, 91L, 189L, 80L, 152L, 223L, 287L, 244L, 57L, 108L, 18L, 62L, 157L, 300L, 283L, 164L, 243L, 89L, 220L, 24L, 271L,
+    166L, 118L, 201L, 127L, 121L, 41L, 267L, 213L, 49L, 73L, 202L, 134L, 112L, 25L, 227L, 29L, 251L, 273L, 119L, 132L,
+    74L, 270L, 83L, 37L, 181L, 258L, 253L, 48L, 120L, 54L, 277L, 176L, 65L, 264L, 107L, 171L, 262L, 162L, 187L, 272L,
+    288L, 294L, 245L, 109L, 172L, 204L, 275L, 22L, 66L, 186L, 247L, 17L, 149L, 141L, 177L, 280L, 216L, 40L, 75L, 263L,
+    246L, 14L, 81L, 260L, 153L, 45L, 237L, 8L, 117L, 86L, 296L, 146L, 154L, 116L, 38L, 100L, 191L, 175L, 92L, 158L, 192L,
+    180L, 256L, 254L, 125L, 222L, 145L, 261L, 155L, 159L, 3L, 206L, 278L, 19L, 31L, 63L, 208L, 55L, 259L, 218L, 111L,
+    226L, 33L, 2L, 44L, 297L, 53L, 87L, 16L, 28L, 90L, 207L, 56L, 137L, 128L, 178L, 142L, 143L, 148L, 193L, 229L, 265L,
+    97L, 252L, 205L, 150L, 165L, 188L, 52L, 99L, 93L, 1L, 221L, 124L, 210L, 6L, 232L, 21L, 211L, 163L, 96L, 60L, 183L,
+    190L, 242L, 42L, 46L, 67L, 126L, 209L, 72L, 194L, 238L, 184L, 39L, 105L, 249L, 61L, 113L, 30L, 77L, 12L, 4L, 51L,
+    139L, 20L, 268L, 215L, 292L, 217L, 199L, 32L, 276L, 47L, 225L, 230L, 79L, 71L, 98L, 50L, 13L, 76L, 231L, 250L, 58L,
+    68L, 239L, 198L, 293L, 212L, 110L, 59L, 182L, 133L, 170L, 43L, 282L, 281L, 131L, 114L, 196L, 214L, 285L, 70L, 102L,
+    279L, 106L, 197L, 257L, 228L, 84L, 235L, 78L, 169L, 240L, 219L, 174L, 82L),
+  CRIT1 = structure(c(
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = "Tolerating >=600 mg of peanut protein without dose-limiting symptoms", class = "factor"),
+  CRIT1FL = structure(c(
+    2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L,
+    2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
+    2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
+    1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L,
+    2L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
+    2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = c("N", "Y"), class = "factor"),
+  CRIT2 = structure(c(
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = "Tolerating >=1000 mg of peanut protein without dose-limiting symptoms", class = "factor"),
+  CRIT2FL = structure(c(
+    2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L,
+    2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L,
+    1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
+    1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L,
+    2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
+    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
+    levels = c("N", "Y"), class = "factor" ) )
+
+peanut %>%
+  ggplot(aes(x=factor(AVAL), fill=TRT01P)) +
+  geom_bar( position=position_dodge(preserve = "single")) +
+  scale_fill_manual(values=c("royalblue", "#fb6a4a", "#ef3b2c", "#cb181d", "#a50f15", "#67000d")) +
+  xlab("Peanut protein tolerated without\ndose-limiting symptoms (mg)") +
+  ylab("Patients") +
+  theme(legend.position="right")
+
+peanut %>%
+  group_by(TRT01P) %>%
+  summarize(proportion = sum(CRIT1FL=="Y") / n()) %>%
+  ggplot(aes(x=TRT01P, y=proportion, fill=TRT01P)) +
+  geom_bar(stat="identity", position=position_dodge()) +
+  geom_text(aes(label=scales::percent(proportion)), size=7, vjust=c(0, rep(1.5, 5))) +
+  scale_fill_manual(values=c("royalblue", "#fb6a4a", "#ef3b2c", "#cb181d", "#a50f15", "#67000d")) +
+  scale_y_continuous(breaks=seq(0, 0.7, 0.1), labels=scales::percent) +
+  xlab("Tolerating >=600 mg of peanut protein\nwithout dose-limiting symptoms") +
+  ylab("Percentage of patients")
+```
+
+#### Excercise 1A
+
+Fit a sigmoid Emax logistic regression model 
+(i.e. `family=binomial(link="logit")`). 
+To accelerate likelihood evaluations, first summarize data as "responders" `y`
+out of `n` patients per dose. We tell `brms` to use this information using 
+`y | trials(n) ~ ...`. 
+We expect the true placebo proportion to be around 0.05 (-2.944 on the logit 
+scale) with much more than 0.1 or much less than 0.02 considered unlikely.
+It is a-priori at least possible that there is a huge treatment effect such 
+as 95\% versus 5\% responders (difference on the log-scale close to 6),
+but we are at least mildly skeptical.
+The dose response is a-priori somewhat likely to follow a Emax curve (with Hill
+parameter near 1), but we wish to allow for the possibility of a steeper or 
+shallower curve. The dose with half the effect (ED50) might be near 15 mg, but 
+have considerable uncertainty around that.
+
+```{r peanutmodel1}
+model1 <- bf( y | trials(n) ~ E0 + Emax * dose^h/(dose^h + ED50^h),
+              family=binomial(link="logit"),
+              nlf(h ~ exp(logh)), nlf(ED50 ~ exp(logED50)),
+              E0 ~ 1, logED50 ~ 1, logh ~ 1, Emax ~ 1, 
+              nl=TRUE)
+
+priors1 <- prior(normal(-2.944, 0.38), nlpar="E0") +
+           prior(normal(0, 1), nlpar="logh") +
+           prior(normal(0, 6), nlpar="Emax") +
+           prior(normal(2.7, 2.5), nlpar="logED50")
+```
+
+Now fit the model
+```{r fitpeanutmodel1}
+brmfit1 <- brm(
+  formula = model1,
+  prior = priors1, 
+  data = peanut %>% group_by(TRT01P, dose) %>% summarize(y=sum(CRIT1FL=="Y"), n=n(), .groups="drop")
+)
+
+summary(brmfit1)
+```
+
+Now use 
+`tibble(dose = seq(0, 300, 1), n=1) %>% tidybayes::add_epred_rvars(object=brmfit1, newdata=.)` 
+to obtain predicted proportions for every dose from 0 to 300 mg.
+Then, plot the curve of predicted proportions for each of these doses using 
+`ggplot2` and `ggdist` (using `ydist=.epred` in the aesthetics and the 
+`stat_lineribbon()` geom from the `ggdist` package).
+
+```{r plotmodel1preds}
+tibble(dose = seq(0, 300, 1), n=1) %>% 
+  tidybayes::add_epred_rvars(object=brmfit1, newdata=.) %>%
+  ggplot(aes(x=dose, ydist=.epred)) +
+  stat_lineribbon() +
+  scale_fill_brewer(palette="Blues") +
+  ylab("Model predicted proportion") +
+  xlab("Dose [mg]")
+```
+
+If you prefer, replace the default fill colors e.g. with shades of blue
+using `+ scale_fill_brewer(palette="Blues")
+
+Next obtain the posterior distribution for the difference in proportions for
+each of these dose levels compared with placebo.
+
+```{r model1diffs}
+tibble(dose = seq(0, 300, 1), n=1) %>% 
+  tidybayes::add_epred_rvars(object=brmfit1, newdata=.) %>%
+  (\(x) x %>% 
+     left_join(x %>% 
+                 filter(dose==0) %>% 
+                 dplyr::select(-dose) %>% 
+                 rename(.pbo=.epred), 
+               by="n"))() %>%
+  mutate(diff = .epred - .pbo) %>%
+  ggplot(aes(x=dose, ydist=diff)) +
+  stat_lineribbon() +
+  scale_fill_brewer(palette="Blues") +
+  ylab("Model predicted difference\nin proportion vs. placebo") +
+  xlab("Dose [mg]")
+```
+
+#### Excercise 1B* (optional)
+
+Try to perform a more efficient statistical analysis by either using an ordinal
+outcome or treating the data as interval censored.
+
+Try treating the data about the logarithm of the amount of protein 
+tolerated as interval censored 
+($-\infty$ to <log(3), >= log(3) to <log(10) mg, ...) using
+`logAVAL | cens("interval", logAVALnext) ~` with `family = gaussian()`.
+For the latter approach you might have to set `log(0)` to a very low number
+such as -28 (approximate log(weight) of one single peanut protein 
+molecule) and assume the upper interval end when a patient could tolerate
+1000 mg to, say, `log(30000)` (approximately 100 peanut kernels). This
+achieves approximately the same thing as setting these to `-Inf` and `Inf`,
+but is handled better by `brms`/`Stan`.
+
+How would you change the prior distributions in this case?
+
+```{r lognormal}
+model2 <- bf( logAVAL | cens("interval", logAVALnext) ~ E0 + Emax * dose^h/(dose^h + ED50^h),
+              family = gaussian(),
+              nlf(h ~ exp(logh)), nlf(ED50 ~ exp(logED50)),
+              E0 ~ 1, logED50 ~ 1, logh ~ 1, Emax ~ 1, 
+              nl=TRUE )
+
+priors2 <- prior(normal(0, 5), nlpar="E0") + # centered on 1 mg, but very uncertain
+           prior(normal(0, 1), nlpar="logh") + # No particular reason to change prior (dose response could be just as steep here as for binomial outcome)
+           prior(normal(0, 6.5), nlpar="Emax") + # decent prior probability for >= 1000 mg, still conceivable could reach 300000
+           prior(normal(2.7, 2.5), nlpar="logED50") + # No particular reason to change prior here (ED50 could be same as for binomial outcome)
+           prior(lognormal(5, 10), class=sigma) # Additional parameter: residual SD, clearly a decent amount of variability, want to allow large SD on the log-scale
+
+brmfit2 <- brm(
+  formula = model2,
+  prior = priors2,
+  data = peanut %>% 
+    mutate(logAVAL = ifelse(AVAL==0, -28, log(AVAL)),
+           logAVALnext = case_when(AVAL==0 ~ log(3),
+                                   AVAL==3 ~ log(10),
+                                   AVAL==10 ~ log(100),
+                                   AVAL==100 ~ log(300),
+                                   AVAL==300 ~ log(600),
+                                   AVAL==600 ~ log(1000),
+                                   TRUE ~ log(30000)))
+  )
+
+summary(brmfit2)
+```
+
+
+Now use an ordinal
+outcome via `family = cumulative(link = "logit", threshold = "flexible")`.
+Details of this model are described in 
+[a journal article](https://doi.org/10.1177/2515245918823199), for which there 
+is also [a PsyArXiv preprint](https://doi.org/10.31234/osf.io/x8swp) in case
+you do not have access to the journal. 
+
+Note that the placebo response is described by a series of $K-1$ ordered 
+thresholds $\theta_1, \ldots, \theta_{K-1}$ on the logit scale for $K$ ordered 
+categories. For the placebo group, the probability of being in categories 
+$k=1, \ldots, K-1$ is be given by $\text{logit}^{-1} \theta_k$ and for category 
+$K$ by $1-\text{logit}^{-1} \theta_{K-1}$. In this case, these parameters will
+appear in `summary(brmfit3)` as `Intercept[1]`, ..., `Intercept[6]`.
+
+How would you change the model and the prior distributions in this case?
+
+```{r ordinal}
+# Note that we omit E0 from the model, because the exepcted placebo outcome
+# is already described by the intercept parameters of the distribution
+model3 <- bf( AVAL ~ Emax * dose^h/(dose^h + ED50^h),
+              family = cumulative(link = "logit", threshold = "flexible"),
+              nlf(h ~ exp(logh)), nlf(ED50 ~ exp(logED50)),
+              logED50 ~ 1, logh ~ 1, Emax ~ 1, 
+              nl=TRUE)
+
+priors3 <- prior(normal(0, 1), nlpar="logh") + # No particular reason to change prior here
+           prior(normal(0, 6), nlpar="Emax") + # Prior could be different (odds from one category to the next not necessarily the same as for top two vs. rest)
+           prior(normal(2.7, 2.5), nlpar="logED50") + # No particular reason to change prior here
+           prior(student_t(3, -0.2, 1), class=Intercept, coef=1) +
+           prior(student_t(3, 0, 2.5), class=Intercept, coef=2) +
+           prior(student_t(3, 0, 2.5), class=Intercept, coef=3) +
+           prior(student_t(3, 0, 2.5), class=Intercept, coef=4) +
+           prior(student_t(3, 2.197, 1), class=Intercept, coef=5) +
+           prior(student_t(3, 0, 2.5), class=Intercept, coef=6)
+
+brmfit3 <- brm(
+  formula = model3,
+  prior = priors3,
+  data = peanut %>% mutate(AVAL = ordered(AVAL))
+  )
+
+summary(brmfit3)
+```
+
+For both the ordinal model and the interval-censored model, if we had a baseline 
+amount of protein tolerated, we could treat this as a monotonic covariate e.g. 
+using `mo(BASE)` or assume a particular functional form.
\ No newline at end of file
diff --git a/workshops/jsm2024/schedule.png b/workshops/jsm2024/schedule.png
new file mode 100644
index 0000000..f8bacf1
Binary files /dev/null and b/workshops/jsm2024/schedule.png differ
diff --git a/workshops/jsm2024/slides/R/01_overview.R b/workshops/jsm2024/slides/R/01_overview.R
new file mode 100644
index 0000000..34e853c
--- /dev/null
+++ b/workshops/jsm2024/slides/R/01_overview.R
@@ -0,0 +1,117 @@
+here::i_am("/home/beanan1/work/brms_course/slides/R/01_overview.R")
+library(here)
+
+library(here)
+library(knitr)
+library(tidyverse)
+library(ggrepel)
+library(latex2exp)
+library(patchwork)
+library(glue)
+library(RBesT)
+library(rstan)
+library(brms)
+library(posterior)
+library(tidybayes)
+library(bayesplot)
+library(gt)
+library(ggdist)
+library(distributional)
+library(mvtnorm)
+library(dqrng)
+library(emmeans)
+library(simsurv)
+
+## ----echo=FALSE, out.height="2in", out.width="2in"----------------------------
+knitr::include_graphics("graphics/brms.png")
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+## formula = y ~ 1 + x + (1 | g)
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+## formula = y ~ 1 + x + (1 + x | g)
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+## formula = y ~ 1 + gp(x) + (1 + x | g)
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| echo: true
+#| mysize: true
+#| size: '\small'
+## formula = bf(
+##   y ~ 1 + x + (1 | g) + ...,
+##   par2 ~ 1 + x + (1 | g) + ...,
+##   par3 ~ 1 + x + (1 | g) + ...,
+## )
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| echo: true
+#| mysize: true
+#| size: '\small'
+## formula = bf(
+##   y ~ fun(x, nlpar1, nlpar2),
+##   nlpar1 ~ 1 + x + (1 | g) + ...,
+##   nlpar2 ~ 1 + (1 | g) + ...,
+##   nl = TRUE
+## )
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| echo: true
+#| mysize: true
+#| size: '\small'
+## family = brmsfamily(
+##   family = "<family>", link = "<link>",
+##   more_link_arguments
+## )
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| echo: true
+#| mysize: true
+#| size: '\small'
+## family = brmsfamily(family = "gaussian", link = "identity",
+##                     link_sigma = "log")
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| echo: true
+#| mysize: true
+#| size: '\small'
+## family = brmsfamily(family = "poisson", link = "log")
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\tiny'
+options(
+  # how many processor cores would you like to use?
+  mc.cores = 4, 
+  # how would you like to access Stan?
+  brms.backend = "cmdstanr",
+  # cache model binaries
+  cmdstanr_write_stan_file_dir=here::here("_brms-cache"),
+  # no need to normalize likelihoods
+  brms.normalize = FALSE,
+  # when you are storing your model to file, 
+  # how shall it be updated?
+  brms.file_refit = "on_change"  
+  # alternatives: "never", "always"
+  # use "never" for production
+)
+# create cache directory if not yet available
+dir.create(here::here("_brms-cache"), FALSE)
+
diff --git a/workshops/jsm2024/slides/R/02_hist_control.R b/workshops/jsm2024/slides/R/02_hist_control.R
new file mode 100644
index 0000000..f821fdf
--- /dev/null
+++ b/workshops/jsm2024/slides/R/02_hist_control.R
@@ -0,0 +1,129 @@
+here::i_am("slides/R/02_hist_control.R")
+library(here)
+
+library(here)
+library(knitr)
+library(tidyverse)
+library(ggrepel)
+library(latex2exp)
+library(patchwork)
+library(glue)
+library(RBesT)
+library(rstan)
+library(brms)
+library(posterior)
+library(tidybayes)
+library(bayesplot)
+library(gt)
+library(ggdist)
+library(distributional)
+library(mvtnorm)
+library(dqrng)
+library(emmeans)
+library(simsurv)
+
+## ----echo = FALSE, include = FALSE--------------------------------------------
+AS_region <- withr::with_seed(63523, bind_cols(AS, region=sample(c("asia", "europe", "north_america"), 8, TRUE)))
+
+## ----echo=FALSE---------------------------------------------------------------
+kable(AS_region)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+form_AS <- bf(r | trials(n) ~ 1 + (1|study), 
+              family = binomial("logit"))
+
+
+## -----------------------------------------------------------------------------
+#| eval=FALSE
+## get_prior(form_AS, data = AS)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+bprior_AS <- prior(normal(0, 2), class = "Intercept") +
+  prior(normal(0, 1), class = "sd", coef = "Intercept", 
+        group = "study")
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+#| results: "hide"
+fit_AS <- brm(
+  form_AS, data = AS, prior = bprior_AS, 
+  seed = 2454
+)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\tiny'
+summary(fit_AS)
+
+
+## -----------------------------------------------------------------------------
+AS_new <- data.frame(study = "new_study", n = 1)
+pe <- posterior_epred(
+  fit_AS, newdata = AS_new, allow_new_levels = TRUE, 
+  sample_new_levels = "gaussian"
+)
+posterior_summary(pe)
+
+
+## ----fig.height=4, fig.width=7------------------------------------------------
+pe_mix <- RBesT::automixfit(pe[, 1], type = "beta")
+plot(pe_mix)$mix
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+form_AS_region <- bf(r | trials(n) ~ 1 + (1 | region/study), 
+                     family = binomial("logit"))
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\footnotesize'
+bprior_AS_region <- prior(normal(0, 2), class="Intercept") +
+  prior(normal(0, 0.5), class="sd", coef="Intercept", 
+        group="region") +
+  prior(normal(0, 0.25), class="sd", coef="Intercept", 
+        group="region:study")
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+#| results: 'hide'
+fit_AS_region <- brm(
+  form_AS_region, data = AS_region, 
+  prior = bprior_AS_region, seed = 2341
+)
+
+
+## ----mysize=TRUE, size = "\\tiny"---------------------------------------------
+summary(fit_AS_region)
+
+
+## -----------------------------------------------------------------------------
+AS_region_new <- data.frame(study = "new_study_asia", 
+                            n = 1, region = "asia")
+
+pe_region <- posterior_epred(
+  fit_AS_region, newdata = AS_region_new, 
+  allow_new_levels = TRUE, 
+  sample_new_levels = "gaussian"
+)
+posterior_summary(pe_region)
+
+
+## ----fig.height=4, fig.width=7------------------------------------------------
+pe_mix_region <- 
+  RBesT::automixfit(pe_region[, 1], type = "beta")
+plot(pe_mix_region)$mix
+
diff --git a/workshops/jsm2024/slides/R/05_mmrm.R b/workshops/jsm2024/slides/R/05_mmrm.R
new file mode 100644
index 0000000..3949212
--- /dev/null
+++ b/workshops/jsm2024/slides/R/05_mmrm.R
@@ -0,0 +1,398 @@
+here::i_am("slides/R/05_mmrm.R")
+library(here)
+
+library(here)
+library(knitr)
+library(tidyverse)
+library(ggrepel)
+library(latex2exp)
+library(patchwork)
+library(glue)
+library(RBesT)
+library(rstan)
+library(brms)
+library(posterior)
+library(tidybayes)
+library(bayesplot)
+library(gt)
+library(ggdist)
+library(distributional)
+library(mvtnorm)
+library(dqrng)
+library(emmeans)
+library(simsurv)
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig-height: 4
+tibble(arm = factor(rep(c("Drug 40 mg (N=50)", "Drug 20 mg (N=50)", "Drug 10 mg (N=50)", "Placebo (N=50)"), each=5),
+                   levels=rev(c("Drug 40 mg (N=50)", "Drug 20 mg (N=50)", "Drug 10 mg (N=50)", "Placebo (N=50)"))),
+       x=rep(c(1, 3.65, 3.9, 3.65, 1), 4),
+       y=rep(c(1, 1, 0.6, 0.2, 0.2), 4)+ rep(3:0, each=5),
+       design="Parallel group dose finding") %>%
+  ggplot(aes(x=x, y=y, label=arm, fill=arm)) +
+  geom_polygon() +
+  theme_void() +
+  theme(legend.position="none", panel.border=element_rect(fill = NA),
+        strip.background=element_rect(fill="lightgrey"),
+        strip.text.x = element_text( margin = margin( b = 5, t = 5) ),
+        axis.line.x = element_line(color="black"),
+        axis.text.x = element_text(color="black", angle=0, hjust=0.5, size=18),
+        axis.ticks.x = element_line(color="black"),
+        axis.ticks.length.x = unit(0.2, "cm"),
+        axis.title.x = element_blank()) +
+  geom_text(data=.%>% filter(x==1 & y %in% c(1:10)),
+            aes(x=x+0.1, y=y-0.3),
+            size=10,
+            hjust = 0, vjust=0.75) +
+  geom_rect(aes(xmin=0, xmax=0.95, ymin=0.2, ymax=4), fill="darkgrey") +
+  geom_text(aes(x=0.45, y=1.9+0.2, label="Run-in"), size=10) +
+  scale_fill_manual(values=c("#377eb8", "#fd8d3c", "#f03b20", "#bd0026")) +
+  scale_x_continuous(breaks = c(0, 0.975, 1.6, 2.15, 2.9, 3.65),
+                     labels = c("     Screening", "Baseline /\nRandomization", "Week 2", "Week 4", "Week 8", "Week 12"))
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig.height: 5
+# Correlation matrix between visits (baseline + 4 post-baseline visits)
+corr_matrix <- diag(5)
+rho <- c(0.6, 0.48, 0.4, 0.375)
+corr_matrix[1,2:5] <- rho[1:4]
+corr_matrix[2,3:5] <- rho[1:3]
+corr_matrix[3,4:5] <- rho[1:2]
+corr_matrix[4,5:5] <- rho[1:1]
+corr_matrix[lower.tri(corr_matrix)] <- t(corr_matrix)[lower.tri(corr_matrix)]
+ 
+# Standard deviations by visit (baseline + 4 post-baseline visits)
+sds <- sqrt(c(0.75, 0.8, 0.85, 0.95, 1.1))
+
+cov_matrix <- diag(sds) %*% corr_matrix %*% diag(sds)
+# print(cov_matrix, digits=2)
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+apply_colnames <- function(x,y){
+  colnames(x) <- y
+  return(x)
+}
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+# Simulate from multivariate normal for control group 
+# (before adding treatment effect later)
+# We simulate 1000 patients and then apply inclusion criteria and keep the
+# first 200 that meet them.
+set.seed(4095867)
+N <- 1000
+Nf <- 200 
+simulated_data <- rmvnorm(n=N, mean=rep(0, 5), sigma = cov_matrix) %>%
+    # turn into tibble
+    apply_colnames(c("BASE", paste0("visit", 1:4))) %>%
+    as_tibble() %>%
+    # Apply inclusion criteria and keep first 200 patients
+    filter(BASE>0) %>%
+    filter(row_number()<=Nf) %>%
+    ##filter(row_number()<=200) %>%
+    # Assign subject ID, treatment group and create missing data
+    mutate(USUBJID = row_number(),
+           TRT01P = dqsample(x=c(0L, 10L, 20L, 40L), size=Nf, replace=T),
+           # Simulate dropouts
+           dropp2 = plogis(visit1-2),
+           dropp3 = plogis(visit2-2),
+           dropp4 = plogis(visit3-2),
+           dropv = case_when(runif(n=n())<dropp2 ~ 2L,
+                             runif(n=n())<dropp3 ~ 3L,
+                             runif(n=n())<dropp4 ~ 4L,
+                             TRUE ~ 5L),
+           visit2 = ifelse(dropv<=2L, NA_real_, visit2),
+           visit3 = ifelse(dropv<=3L, NA_real_, visit3),
+           visit4 = ifelse(dropv<=3L, NA_real_, visit4)) %>%
+    dplyr::select(-dropp2, -dropp3, -dropp4, -dropv) %>%
+    # Turn data into long-format
+    pivot_longer(cols=starts_with("visit"), names_to = "AVISIT", values_to="AVAL") %>%
+    mutate(
+        # Assign visit days
+        ADY = case_when(AVISIT=="visit1" ~ 2L*7L,
+                        AVISIT=="visit2" ~ 4L*7L,
+                        AVISIT=="visit3" ~ 8L*7L,
+                        AVISIT=="visit4" ~ 12L*7L),
+        # Turn to factor with defined order of visits
+        AVISIT = factor(AVISIT, paste0("visit", 1:4)),
+        # Assume rising treatment effect over time (half there by week 3) with an 
+        # Emax dose response (ED50 = 5 mg)
+        AVAL = AVAL + 0.9 * (ADY/7)^3/((ADY/7)^3+3^3) * TRT01P/(TRT01P+5),
+        # Change from baseline = value - baseline
+        CHG = AVAL - BASE,
+        TRT01P=factor(TRT01P)) %>%
+    relocate(USUBJID, TRT01P, AVISIT, ADY, AVAL, CHG, BASE) %>%
+    # Discard missing data
+    filter(!is.na(AVAL))
+
+simulated_data <- simulated_data %>% 
+  mutate(USUBJID=factor(USUBJID))
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig-height: 6
+p1 <- simulated_data %>%
+    bind_rows(simulated_data %>%
+              group_by(USUBJID) %>%
+              slice_head(n=1) %>%
+              mutate(AVISIT="Baseline", ADY=0, AVAL=BASE)
+              ) %>% arrange(USUBJID, ADY) %>%
+  ggplot(aes(x=AVISIT, y=AVAL, col=TRT01P)) +
+  theme_bw(base_size=24) +
+  geom_jitter(height=0, width=0.2) +
+  scale_color_manual(values=c("#377eb8", "#fd8d3c", "#f03b20", "#bd0026")) +
+  guides(x =  guide_axis(angle = 45)) +
+  theme(axis.title.x = element_blank(),
+        legend.position="none")
+
+p2 <- simulated_data %>%
+  ggplot(aes(x=AVISIT, y=CHG, fill=TRT01P)) +
+  geom_hline(yintercept=0) +
+  geom_jitter(alpha=0.4, size=0.65, col="black", shape=22, 
+             position=position_jitterdodge(dodge.width=0.75, 
+                                           jitter.width=0.2, jitter.height=0)) +
+  geom_boxplot(outlier.alpha = 0, alpha=0.8) +
+  theme_bw(base_size=24) +
+  scale_fill_manual(values=c("#377eb8", "#fd8d3c", "#f03b20", "#bd0026")) + 
+  guides(x =  guide_axis(angle = 45)) +
+  theme(legend.position="right",
+        axis.title.x = element_blank())
+
+p1 + p2
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+simulated_data %>% 
+  filter(USUBJID %in% c(3, 9, 13)) %>% 
+  gt() %>% 
+  fmt_number(columns=c("AVAL", "CHG", "BASE"), decimals=2) %>%
+  opt_stylize(style = 6, color = "red", add_row_striping = TRUE) %>%
+  tab_style(locations = cells_body(rows = c(4, 8, 10)),
+            style = cell_borders(sides = "bottom", color = "black", weight = px(1.5),style = "solid"))
+
+
+## PROC MIXED DATA=simulated_data;
+##   CLASS TRT01P AVISIT USUBJID;
+##   MODEL CHG ~ TRT01P AVISIT BASE TRT01P*AVISIT AVISIT*BASE
+##     / SOLUTION DDFM=KR ALPHA = 0.05;
+##   REPEATED AVISIT / TYPE=UN SUBJECT = USUBJID R Rcorr GROUP=TRT01P;
+##   LSMEANS TRT01P*AVISIT / DIFFS PDIFF CL OM E;
+## RUN;
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| mysize: true
+#| size: '\small'
+## library(mmrm)
+## mmrm_fit <- mmrm(
+##   formula = CHG ~ TRT01P + AVISIT + BASE + AVISIT:TRT01P +
+##     AVISIT:BASE + us(AVISIT | TRT01P / USUBJID),
+##   method = "Kenward-Roger",
+##   vcov = "Kenward-Roger-Linear", # to match SAS
+##   data = simulated_data %>% mutate(USUBJID=factor(USUBJID))
+## )
+
+
+## -----------------------------------------------------------------------------
+#| eval: true
+#| echo: false
+library(mmrm)
+mmrm_fit <- mmrm(
+  formula = CHG ~ TRT01P + AVISIT + BASE + AVISIT:TRT01P + 
+    AVISIT:BASE + us(AVISIT | TRT01P / USUBJID),
+  method = "Kenward-Roger", 
+  data = simulated_data %>% mutate(USUBJID=factor(USUBJID))
+)
+
+
+## ----mysize=TRUE, size = "\\small"--------------------------------------------
+#| echo: false
+#| include: false
+options(
+  # how many processor cores would you like to use?
+  mc.cores = 4, 
+  # how would you like to access Stan?
+  brms.backend = "cmdstanr",  
+  # ensure the models don't need to be recompiled
+  # by storing the compiled model files in a folder
+  cmdstanr_write_stan_file_dir = here::here("_brms-cache")
+)
+
+
+## -----------------------------------------------------------------------------
+#| echo: FALSE
+#| fig-height: 5
+tibble(treatment = c(rep("PHEN/TPM CR 15/92", 15),
+                     rep("PHEN/TPM CR 3.75/23", 15),
+                     rep("placebo", 15)),
+       week = rep(c(0,4, 8, 12, 16, 20, 24, 28, 32, 36, 40, 44, 48, 52, 56), 3),
+       chg = c(0, -3.73913043478261, -5.88405797101449, -7.50724637681159,-8.95652173913043, -10.0289855072464, -11.1014492753623, -11.8260869565217, -12.3478260869565, -12.8405797101449, -13.2173913043478, -13.304347826087, -13.3333333333333, -13.4492753623188, -13.1884057971014, 0, -2.57971014492753, -3.50724637681159, -4.17391304347826, -4.98550724637681, -5.56521739130435, -6.14492753623188, -6.55072463768116, -6.72463768115942, -6.89855072463768, -7.18840579710145, -7.15942028985507, -6.98550724637681, -6.84057971014492, -6.7536231884058, 0, -1.07246376811594, -1.47826086956522, -1.88405797101449, -2.08695652173913, -2.31884057971014, -2.43478260869565, -2.60869565217391, -2.69565217391304, -2.78260869565217, -2.92753623188406, -2.66666666666666, -2.46376811594203, -2.34782608695652, 
+               -2.20289855072464), 
+       stderr = c(NA, 0.594202898550725, 0.347826086956522, 0.434782608695651, 0.521739130434784, 0.594202898550725, 0.666666666666667, 0.710144927536232, 0.826086956521739, 0.869565217391306, 0.898550724637681, 0.942028985507246, 0.956521739130435, 0.971014492753623, 1.02898550724638, NA, 0.449275362318841, 0.449275362318841, 0.579710144927535, 0.652173913043478, 0.797101449275361, 0.956521739130435, 1.02898550724638, 1.13043478260869, 1.15942028985507, 1.23188405797102, 1.31884057971014, 1.3768115942029, 1.44927536231884, 1.42028985507246, NA, 0.333333333333332, 0.289855072463769, 0.391304347826086, 0.492753623188404, 0.623188405797102, 0.724637681159422, 0.782608695652174, 0.840579710144927, 0.869565217391304, 0.956521739130434, 1.01449275362319, 1.05797101449275, 1.10144927536232, 1.10144927536232), 
+       lcl = c(NA, -4.90374671545133, -6.56578457433277, -8.35940463095944, -9.97911164410786, -11.1936017879151, -12.4080919317224, -13.2179454382966, -13.9669267698374, -14.5448962184406, -14.97851836292, -15.150690710074, -15.2080814924586, -15.3524287965824, -15.205180331918, NA, -3.46027367421365, -4.3878099060977, -5.31012404900872, -6.26374462759858, -7.12750752390873, -8.01967569535715, -8.56749917249773, -8.94024914194382, -9.17097273569861, -9.60285418385369, -9.74430032743688, -9.68400838451167, -9.68110722397109, -9.53734015195544, NA, -1.72578509629596, -2.04636637233045, -2.65100039974755, -3.05273587644002, -3.54026741065539, -3.85504636560874, -4.14258050964004, -4.34315813193221, -4.48692520394787, -4.80228439100932, -4.65503592634498, -4.53735320103513, -4.5066269974644, -4.36169946123252), 
+       ucl = c(NA, -2.57451415411388, -5.20233136769621, -6.65508812266374, -7.93393183415301, -8.86436922657765, -9.79480661900228, -10.4342284747469, -10.7287254040756, -11.1362632018492, -11.4562642457756, -11.4580049420999, -11.4585851742081, -11.5461219280553, -11.1716312622849, NA, -1.69914661564142, -2.62668284752548, -3.0377020379478, -3.70726986515503, -4.00292725869996, -4.27017937710661, -4.53395010286458, -4.50902622037501, -4.62612871357675, -4.7739574103492, -4.57454025227326, -4.28700610824195, -4.00005219631876, -3.96990622485616, NA, -0.419142439935926, -0.910155366799983, -1.11711554228143, -1.12117716703824, -1.09741374876489, -1.01451885178257, -1.07481079470778, -1.04814621589387, -1.07829218735647, -1.05278807275879, -0.678297406988347, -0.390183030848927, -0.189025176448641, -0.0440976402167492)) %>%
+  ggplot(aes(x=week, y=chg, ymin=lcl, ymax=ucl, col=treatment, label=treatment)) +  
+  theme_bw(base_size=18) +
+  theme(legend.position="none") +
+  geom_hline(yintercept=0, alpha=0.5) +
+  geom_errorbar(width=0.75) +
+  geom_line() +
+  geom_point() +
+  geom_text(data=.%>% filter(week==48), size=6,
+            nudge_y=c(-3, -3.25, 3)) +
+  xlab("Time since randomization (weeks)") +
+  ylab("Percent change in body weight (%)") +
+  scale_color_manual(values=c("#e41a1c", "#ff7f00", "#377eb8"))
+
+
+## -----------------------------------------------------------------------------
+contrasts(simulated_data$AVISIT) <- MASS::contr.sdif
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+contrasts(simulated_data$AVISIT) %>% MASS::fractions()
+
+
+## -----------------------------------------------------------------------------
+# add the intercept
+cmat <- cbind("1" = 1, contrasts(simulated_data$AVISIT))
+# compute the inverse matrix
+solve(cmat) %>% MASS::fractions()
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\footnotesize'
+mmrm_model1 <- bf(
+  CHG ~ 1 + AVISIT + BASE + BASE:AVISIT + TRT01P + TRT01P:AVISIT 
+    + unstr(time = AVISIT, gr = USUBJID),
+  sigma ~ 1 + AVISIT + TRT01P + AVISIT:TRT01P
+)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\footnotesize'
+mmrm_prior1 <- prior(normal(0, 2), class=Intercept) +
+    prior(normal(0, 1), class=b) +
+    prior(normal(0, log(10.0)/1.64), class=Intercept, dpar=sigma) +
+    prior(normal(0, log(2.0)/1.64), class=b, dpar=sigma) +  
+    prior(lkj(1), class=cortime)
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| mysize: true
+#| size: '\small'
+## fit_mmrm1 <- brm(
+##   formula = mmrm_model1,
+##   data = simulated_data,
+##   prior = mmrm_prior1,
+##   ...
+## )
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| include: false
+fit_mmrm1 <- brm(
+  formula = mmrm_model1,
+  prior = mmrm_prior1,
+  data = simulated_data,
+  seed = 234235
+)
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| mysize: true
+#| size: '\scriptsize'
+
+## emm2 <- fit_mmrm1 %>%
+##   emmeans(~ TRT01P | AVISIT, weights="proportional")
+
+
+## ----mysize = TRUE, size = "\\tiny\n"-----------------------------------------
+#| echo: false
+
+emm2 <- fit_mmrm1 %>%
+  emmeans(~ TRT01P | AVISIT, weights="proportional", 
+          at = list(AVISIT = c("visit1", "visit4")))
+emm2
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\footnotesize'
+contrast(emm2, adjust="none", method="trt.vs.ctrl", ref="TRT01P0") 
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\footnotesize'
+mmrm_model2 <- bf( 
+  CHG ~ 1 + AVISIT + mo(TRT01P) + BASE + mo(TRT01P):AVISIT 
+    + BASE:AVISIT + unstr(time = AVISIT, gr = USUBJID),
+  sigma ~1 + AVISIT + mo(TRT01P) + mo(TRT01P):AVISIT
+)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+#| eval: false
+## fit_mmrm2 <- brm(
+##   formula = mmrm_model2,
+##   data = simulated_data %>% mutate(TRT01P=ordered(TRT01P)),
+##   prior = mmrm_prior1,
+##   ...)
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| include: false
+fit_mmrm2 <- brm(
+  formula = mmrm_model2,
+  data = simulated_data %>% mutate(TRT01P=ordered(TRT01P)),
+  prior = mmrm_prior1,
+  seed = 234235
+)
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig-height: 6
+map2_dfr(list(mmrm_fit, fit_mmrm1, fit_mmrm2),
+         c("frequentist", "Bayesian", "Bayesian (monotonic)"),
+         \(x, y) emmeans(x, ~ TRT01P | AVISIT, weights="proportional") %>%
+           contrast(adjust="none", method="trt.vs.ctrl", ref="TRT01P0") %>%
+           confint() %>%
+           as_tibble() %>%
+           mutate(Model=y)) %>%
+  mutate(Week = c(2L, 4L, 8L, 12L)[as.integer(str_extract(AVISIT, "[0-9]+"))],
+         Model = factor(Model, 
+                        c("frequentist", "Bayesian", "Bayesian (monotonic)")),
+         Dose = str_remove(str_extract(contrast, "[0-9]+ -"), " -"),
+         lower.CL = ifelse(is.na(lower.CL), lower.HPD, lower.CL),
+         upper.CL = ifelse(is.na(upper.CL), upper.HPD, upper.CL)) %>%
+  ggplot(aes(x=Dose, y=estimate, ymin=lower.CL, ymax=upper.CL, col=Model)) +
+  geom_hline(yintercept=0, col="darkred", lty=2) +
+  theme_bw(base_size=24) +
+  theme(legend.position="bottom",
+        legend.title = element_text(size=22),
+        legend.text = element_text(size=22)) +
+  geom_point(position=position_dodge(width=0.4), size=4) +
+  geom_errorbar(position=position_dodge(width=0.4), lwd=1) +
+  scale_color_manual(values=c("#000000", "#E69F00", "#56B4E9")) +
+  facet_wrap(~Week, label=label_both, nrow=1, ncol=4) +
+  ylab("Difference to placebo") #+ guides(col=guide_legend(nrow=2, byrow=TRUE))
+
diff --git a/workshops/jsm2024/slides/R/06_dose_finding.R b/workshops/jsm2024/slides/R/06_dose_finding.R
new file mode 100644
index 0000000..fc99c42
--- /dev/null
+++ b/workshops/jsm2024/slides/R/06_dose_finding.R
@@ -0,0 +1,417 @@
+here::i_am("slides/R/06_dose_finding.R")
+library(here)
+
+library(here)
+library(knitr)
+library(tidyverse)
+library(ggrepel)
+library(latex2exp)
+library(patchwork)
+library(glue)
+library(RBesT)
+library(rstan)
+library(brms)
+library(posterior)
+library(tidybayes)
+library(bayesplot)
+library(gt)
+library(ggdist)
+library(distributional)
+library(mvtnorm)
+library(dqrng)
+library(emmeans)
+library(simsurv)
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| warning: false
+#| cache: false
+#| fig.height: 6.5
+drfdata <- tibble(Dose=(0:5000)/10,
+                  Emax=Dose/(Dose+70),
+                  `sigmoid Emax`=1/(1+(100/Dose)^3),
+                  `non-monotone`=1/(1+(10/Dose)^0.9)-(Dose>300)*(Dose-300)^2/120000) %>%
+    gather(value = delta, key=Function, -Dose) %>%
+    mutate( pointlabel = ifelse((Dose==300 & Function=="Emax") | (Dose==100 & Function=="non-monotone") | (Dose==120 & Function=="sigmoid Emax"), Function, NA))
+
+p1 <- drfdata %>%
+    filter(Function=="Emax") %>%
+    ggplot(aes(x=Dose, y=delta, col=Function, label=pointlabel)) +
+    scale_color_manual(values=c("#000000", "#E69F00", "#56B4E9")) +
+    theme_bw(base_size = 24) +  
+    ylab("Percentage of full treatment effect") +
+    geom_hline(yintercept=0, size=2) +
+    coord_cartesian(ylim=c(0, 1)) +
+    scale_y_continuous(labels=scales::percent) +
+    geom_line(size=3) +
+    geom_text(data = . %>% filter(!is.na(pointlabel)),
+              size = 10, nudge_y=c(-0.1, -0.15, 0.11), nudge_x=c(10, 80, 2.5)) +
+    guides(color=FALSE)
+
+p2 <- drfdata %>%
+    filter(Function %in% c("Emax", "sigmoid Emax")) %>%
+    ggplot(aes(x=Dose, y=delta, col=Function, label=pointlabel)) +
+    scale_color_manual(values=c("#000000", "#E69F00", "#56B4E9")) +
+    theme_bw(base_size = 24) +  
+    ylab("Percentage of full treatment effect") +
+    coord_cartesian(ylim=c(0, 1)) +
+    scale_y_continuous(labels=scales::percent) +
+    geom_hline(yintercept=0, size=2) +
+    geom_line(size=3) +
+    geom_text(data = . %>% filter(!is.na(pointlabel)),
+              size = 10, nudge_y=c(-0.1, -0.15, 0.11), nudge_x=c(10, 80, 2.5)) +
+    guides(color=FALSE)
+
+p3 <- drfdata %>%
+    ggplot(aes(x=Dose, y=delta, col=Function, label=pointlabel)) +
+    scale_color_manual(values=c("#000000", "#56B4E9", "#E69F00")) +
+    theme_bw(base_size = 24) +  
+    ylab("Percentage of full treatment effect") +
+    coord_cartesian(ylim=c(0, 1)) +
+    scale_y_continuous(labels=scales::percent) +
+    geom_hline(yintercept=0, size=2) +
+    geom_line(size=3) +
+    geom_text(data = . %>% filter(!is.na(pointlabel)),
+              size = 10, nudge_y=c(-0.1, -0.15, 0.11), nudge_x=c(10, 80, 2.5)) +
+    guides(color=FALSE)
+
+p1
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| cache: false
+#| warning: false
+#| fig.height: 6.5
+p2
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| cache: false
+#| warning: false
+#| fig.height: 6.5
+p3
+
+
+## ----include=FALSE------------------------------------------------------------
+# This is the PATHWAY DRF data by group
+pathway = tibble(dose = c(0, 70, 210, 280*2),
+                 group = c("placebo", "tezepelumab 70 mg q4w",
+                           "tezepelumab 210 mg q4w", "tezepelumab 280 mg q2w"),
+                 log_est = log(c(0.67, 0.26, 0.19, 0.22)),
+                 log_stderr = c(0.10304, 0.17689, 0.22217, 0.19108))
+
+
+## ----echo=FALSE---------------------------------------------------------------
+gt(pathway) %>%
+  fmt_number(columns=c("log_est", "log_stderr"), decimals=3) %>%
+  opt_stylize(style = 6, color = 'blue')
+
+
+## ----sigemax_plots------------------------------------------------------------
+#| echo: FALSE
+#| fig-height: 6
+# Plot some example sigEmax curves
+expand_grid(Dose=seq(0, 100, 0.1), Emax=1, E0=0, ED50=c(5,25), h=c(1/3, 1, 3)) %>%
+  mutate(`Dose response` = E0 + Emax * Dose^h/(Dose^h + ED50^h),
+         text = paste0("ED50=", ED50, "/h=",round(h,2))) %>%
+  ggplot(aes(x=Dose, y=`Dose response`, col=text, label=text)) +
+  theme_bw(base_size=24) +
+  geom_line(lwd=3) +
+  scale_y_continuous(labels=scales::percent(seq(0,1,0.25))) +
+  geom_text_repel(data=. %>% filter( Dose==50), max.iter = 100, #max.time = 10,
+                  size=6,
+                  nudge_x=c(35, 30,-16, 30, 10, 5), segment.color = NA,
+                  nudge_y=c(0,-0.02,-0.05, -0.02, -0.03,-0.1)) +
+  scale_color_brewer(palette="Dark2") +
+  theme(legend.position = "none")
+
+
+## ----fit_sigemax--------------------------------------------------------------
+#| results: 'hide'
+form_sig <- bf( 
+  log_est | se(log_stderr) ~ E0 + Emax * dose^h / 
+                             (dose^h + ED50^h),
+  nlf(h ~ exp(logh)), nlf(ED50 ~ exp(logED50)),
+  E0 ~ 1, Emax ~ 1, logh ~ 1, logED50 ~ 1,
+  nl = TRUE,
+  family = gaussian()
+)
+
+prior_sig <- prior(normal(0,1), nlpar="E0") +
+  prior(normal(0,1), nlpar="logh") +
+  prior(normal(0,1), nlpar="Emax") +
+  prior(normal(4,2), nlpar="logED50")
+
+
+## -----------------------------------------------------------------------------
+#| eval: FALSE
+## fit_sig = brm(
+##   formula = form_sig,
+##   data = pathway,
+##   prior = prior_sig,
+##   control = list(adapt_delta = 0.999)
+## )
+
+
+## -----------------------------------------------------------------------------
+#| echo: FALSE
+#| results: 'hide'
+fit_sig = brm(
+  formula = form_sig, 
+  data = pathway, 
+  prior = prior_sig,
+  control = list(adapt_delta = 0.999), 
+  seed = 3624,
+  save_pars = save_pars(all = TRUE)
+) 
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\tiny'
+summary(fit_sig)
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+#| mysize: true
+#| size: '\tiny'
+## tibble(dose = seq(0, 560, 1), log_stderr=1) %>%
+##   add_epred_rvars(object=fit_sig) %>%
+##   (\(x) x %>%
+##      left_join(x %>% filter(dose==0) %>% rename(pbo = .epred) %>% dplyr::select(-dose),
+##                by="log_stderr"))() %>%
+##   mutate(.delta = .epred - pbo) %>%
+##   ggplot(aes(x=dose, ydist=.delta)) +
+##   stat_lineribbon()
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig.height: 4
+tibble(dose = seq(0, 560, 1), log_stderr=1) %>%
+  add_epred_rvars(object=fit_sig) %>%
+  (\(x) x %>% left_join(x %>% filter(dose==0) %>% rename(pbo = .epred) %>% dplyr::select(-dose), by="log_stderr"))() %>%
+  mutate(.delta = .epred - pbo) %>%
+  ggplot(aes(x=dose, ydist=.delta)) +
+  theme_bw(base_size=24) +
+  theme(legend.position = "right") +
+  geom_hline(yintercept=0, color="darkred", lty=2) +
+  stat_lineribbon() +
+  scale_fill_brewer(palette="Blues") +
+  geom_point(aes(x = dose, y = log_rr), inherit.aes = FALSE, 
+             col="#E69F00",
+             data = tibble(dose=c(70, 210, 280*2),
+                           log_rr= log(c(1-0.62, 1-0.71, 1-0.66)),
+                           log_rr_ucl = log(1-c(0.42, 0.54, 0.47)),
+                           log_rr_lcl = log(1-c(0.75, 0.82, 0.79))),
+             size = 3) + 
+  geom_errorbar(aes(x = dose, ymin=log_rr_lcl, ymax=log_rr_ucl), 
+                inherit.aes = FALSE, col="#E69F00", 
+             data = tibble(dose=c(70, 210, 280*2),
+                           log_rr= log(c(1-0.62, 1-0.71, 1-0.66)),
+                           log_rr_ucl = log(1-c(0.42, 0.54, 0.47)),
+                           log_rr_lcl = log(1-c(0.75, 0.82, 0.79))),
+             size = 1, width=30) + 
+  ylab("Rate ratio vs. placebo") +
+  scale_y_continuous(breaks=log(c(1, 0.7, 0.5, 0.35, 0.25, 0.15)), 
+                     labels=c(1, 0.7, 0.5, 0.35, 0.25, 0.15)) +
+  scale_x_continuous(breaks=c(0, 70, 210, 280*2)) +
+  xlab("Total tezepelumab dose [mg/month]")
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+form_mbeta <- bf( 
+  log_est | se(log_stderr) ~ E0 +   
+    Emax * (delta1+delta2)^(delta1+delta2) /
+    (delta1^delta1 * delta2^delta2) * 
+    (dose/850)^delta1 * (1-dose/850)^delta2,
+  nlf(delta1 ~ exp(logdelta1)), nlf(delta2 ~ exp(logdelta2)),
+  E0 ~ 1, Emax ~ 1, logdelta1 ~ 1, logdelta2 ~ 1,
+  nl = TRUE,
+  family = gaussian()
+)
+
+prior_mbeta <- prior(normal(0,1), nlpar="E0") +
+  prior(normal(0,1), nlpar="Emax") +
+  prior(normal(0,1), nlpar="logdelta1") +
+  prior(normal(0,1), nlpar="logdelta2")
+
+
+## -----------------------------------------------------------------------------
+#| eval: FALSE
+## fit_mbeta <- brm(
+##   form_mbeta,
+##   data = pathway,
+##   prior = prior_mbeta,
+##   control = list(adapt_delta = 0.999)
+## )
+
+
+## -----------------------------------------------------------------------------
+#| echo: FALSE
+#| results: 'hide'
+fit_mbeta <- brm(
+  form_mbeta, data = pathway, prior = prior_mbeta,
+  control = list(adapt_delta = 0.999), seed = 7304,
+  save_pars = save_pars(all = TRUE)
+) 
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig.height: 6.5
+tibble(dose = seq(0, 560, 1), log_stderr=1) %>%
+  add_epred_rvars(object=fit_mbeta) %>%
+  (\(x) x %>% left_join(x %>% filter(dose==0) %>% rename(pbo = .epred) %>% dplyr::select(-dose), by="log_stderr"))() %>%
+  mutate(.delta = .epred - pbo) %>%
+  ggplot(aes(x=dose, ydist=.delta)) +
+  theme_bw(base_size=24) +
+  theme(legend.position = "bottom") +
+  geom_hline(yintercept=0, color="darkred", lty=2) +
+  stat_lineribbon() +
+  scale_fill_brewer(palette="Blues") +
+  geom_point(aes(x = dose, y = log_rr), inherit.aes = FALSE, 
+             col="#E69F00",
+             data = tibble(dose=c(70, 210, 280*2),
+                           log_rr= log(c(1-0.62, 1-0.71, 1-0.66)),
+                           log_rr_ucl = log(1-c(0.42, 0.54, 0.47)),
+                           log_rr_lcl = log(1-c(0.75, 0.82, 0.79))),
+             size = 3) + 
+  geom_errorbar(aes(x = dose, ymin=log_rr_lcl, ymax=log_rr_ucl), 
+                inherit.aes = FALSE, col="#E69F00", 
+             data = tibble(dose=c(70, 210, 280*2),
+                           log_rr= log(c(1-0.62, 1-0.71, 1-0.66)),
+                           log_rr_ucl = log(1-c(0.42, 0.54, 0.47)),
+                           log_rr_lcl = log(1-c(0.75, 0.82, 0.79))),
+             size = 1, width=30) + 
+  ylab("Rate ratio compared with placebo") +
+  scale_y_continuous(breaks=log(c(1, 0.7, 0.5, 0.35, 0.25, 0.15)), 
+                     labels=c(1, 0.7, 0.5, 0.35, 0.25, 0.15)) +
+  scale_x_continuous(breaks=c(0, 70, 210, 280*2)) +
+  xlab("Total tezepelumab dose [mg/month]")
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\scriptsize'
+#| cache: true
+(loo_mbeta <- loo(fit_mbeta))
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\scriptsize'
+#| cache: true
+(loo_mm_mbeta <- loo_moment_match(fit_mbeta, loo_mbeta))
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#! message: false
+#! warning: false
+loo_sig <- loo(fit_sig)
+loo_mm_sig <- loo_moment_match(fit_sig, loo_sig)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\footnotesize'
+#| cache: true
+(loo_exact_mbeta <- kfold(fit_mbeta, folds = "loo")) 
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+#| cache: true
+loo_compare(loo_mm_sig, loo_exact_mbeta) 
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+fit_sig$criteria$loo <- loo_mm_sig
+fit_mbeta$criteria$loo <- loo_exact_mbeta
+(w_dose <- model_weights(fit_sig, fit_mbeta, weights = "loo")) 
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+dose_df <- data.frame(
+  dose = seq(min(pathway$dose), max(pathway$dose), length.out = 100),
+  log_stderr = mean(pathway$log_stderr) 
+)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+pe_sig <- posterior_epred(fit_sig, newdata = dose_df)
+pe_mbeta <- posterior_epred(fit_mbeta, newdata = dose_df)
+pe_avg <- pe_sig * w_dose[1] + pe_mbeta * w_dose[2]  
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+pe_avg <- pe_avg %>%
+  posterior_summary() %>%
+  as.data.frame() %>% 
+  bind_cols(dose_df) 
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+pe_avg %>% select(-log_stderr) %>% head(4)
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig.height: 6.5
+tibble(dose = seq(0, 560, 1), log_stderr=1) %>%
+  add_epred_rvars(object=fit_sig) %>%
+  rename(SigEmax = .epred) %>%
+  add_epred_rvars(object=fit_mbeta) %>%
+  rename(ModBeta = .epred) %>%
+  mutate(Averaged = w_dose["fit_sig"] * SigEmax +  w_dose["fit_mbeta"] * ModBeta) %>%
+  (\(x) x %>% left_join(x %>% filter(dose==0) %>% rename(SigEmaxPbo = SigEmax, ModBetaPbo = ModBeta, AveragedPbo=Averaged) %>% dplyr::select(-dose), by="log_stderr"))() %>%
+  mutate(SigEmax = SigEmax - SigEmaxPbo,
+         ModBeta = ModBeta - ModBetaPbo,
+         Averaged = Averaged - AveragedPbo) %>%
+  dplyr::select(-SigEmaxPbo, -ModBetaPbo, -AveragedPbo) %>%
+  pivot_longer(cols=c("Averaged", "SigEmax", "ModBeta"), 
+               names_to="Model", 
+               values_to=".delta") %>%
+  mutate(Model = factor(Model, c("SigEmax", "ModBeta", "Averaged"))) %>%
+  ggplot(aes(x=dose, ydist=.delta)) +
+  theme_bw(base_size=18) +
+  theme(legend.position = "bottom") +
+  geom_hline(yintercept=0, color="darkred", lty=2) +
+  stat_lineribbon() +
+  scale_fill_brewer(palette="Blues") +
+  geom_point(aes(x = dose, y = log_rr), inherit.aes = FALSE, 
+             col="#E69F00",
+             data = tibble(dose=c(70, 210, 280*2),
+                           log_rr= log(c(1-0.62, 1-0.71, 1-0.66)),
+                           log_rr_ucl = log(1-c(0.42, 0.54, 0.47)),
+                           log_rr_lcl = log(1-c(0.75, 0.82, 0.79))),
+             size = 3) + 
+  geom_errorbar(aes(x = dose, ymin=log_rr_lcl, ymax=log_rr_ucl), 
+                inherit.aes = FALSE, col="#E69F00", 
+             data = tibble(dose=c(70, 210, 280*2),
+                           log_rr= log(c(1-0.62, 1-0.71, 1-0.66)),
+                           log_rr_ucl = log(1-c(0.42, 0.54, 0.47)),
+                           log_rr_lcl = log(1-c(0.75, 0.82, 0.79))),
+             size = 1, width=30) + 
+  facet_wrap(~Model, ncol=3, nrow=1, labeller = label_both) +
+  ylab("Rate ratio compared with placebo") +
+  scale_y_continuous(breaks=log(c(1, 0.7, 0.5, 0.35, 0.25, 0.15)), 
+                     labels=c(1, 0.7, 0.5, 0.35, 0.25, 0.15)) +
+  scale_x_continuous(breaks=c(0, 70, 210, 280*2)) +
+  xlab("Total tezepelumab dose [mg/month]")
+
diff --git a/workshops/jsm2024/slides/R/07_time_to_event.R b/workshops/jsm2024/slides/R/07_time_to_event.R
new file mode 100644
index 0000000..0237b2f
--- /dev/null
+++ b/workshops/jsm2024/slides/R/07_time_to_event.R
@@ -0,0 +1,252 @@
+here::i_am("slides/R/07_time_to_event.R")
+library(here)
+
+library(here)
+library(knitr)
+library(tidyverse)
+library(ggrepel)
+library(latex2exp)
+library(patchwork)
+library(glue)
+library(RBesT)
+library(rstan)
+library(brms)
+library(posterior)
+library(tidybayes)
+library(bayesplot)
+library(gt)
+library(ggdist)
+library(distributional)
+library(mvtnorm)
+library(dqrng)
+library(emmeans)
+library(simsurv)
+
+## -----------------------------------------------------------------------------
+#| echo: false
+set.seed(46767)
+## n per group
+n_grp <- 100
+n_hist <- 400
+## use month as time-unit
+rate_1 <- 1 / 6
+rate_cens <- 1 / 10
+beta <- c(trt=-0.2,        ## roughly 20% HR reduction
+          soc_alt=0.05,    ## alternative chemotherapy is 5% worse
+          hist1=0.02) ## simulated historical data has a 2% worse outcome
+
+## covariates of simulated trial data
+covs <- data.frame(id = seq(1, 2*n_grp), trt = c(0, 1),
+                   soc_alt=rbinom(2*n_grp, 1L, 0.3), hist1=0L, hist2=0L)
+
+## covariates of historical data
+hcovs <- data.frame(id = seq(2*n_grp+1, 2*n_grp+1 +n_hist - 1),
+                    trt = c(0), soc_alt=0, hist1=1L, hist2=0L)
+
+simulate_trial <- function(lambda, gamma, lambda_cens, x, betas) {
+  ## simulate censoring times, note that we do not simulate end of
+  ## trial with maxt for now...
+  cens <- simsurv(lambdas = lambda_cens, gammas = 1, x=x)
+  events <- simsurv(lambdas = lambda, gammas = gamma, x=x, betas=betas)
+  names(cens) <- paste0(names(cens), "_cens")
+  bind_cols(events, select(cens, -id_cens), select(x, -id)) %>%
+    rename(censtime=eventtime_cens) %>%
+    mutate(event=1*(eventtime <= censtime),
+           y=if_else(event==1, eventtime, censtime),
+           status=NULL, status_cens=NULL) %>%
+    relocate(id, y, event) %>%
+    mutate(soc=factor(soc_alt, c(0, 1), c("ChA", "ChB")),
+           trt_ind=trt,
+           trt=factor(trt_ind, c(0,1), c("ctl", "act")),
+           arm=factor(paste0(c("ctl", "act")[trt_ind + 1], soc),
+                      levels=c("actChA", "ctlChA",
+                               "actChB", "ctlChB")))
+}
+
+sim <- simulate_trial(rate_1, 1, rate_cens, covs, beta)
+hdata1 <- simulate_trial(rate_1, 1, rate_cens, hcovs, beta) %>%
+  mutate(id=id+max(sim$id))
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+sim %>% 
+  select(y, event, trt, soc, arm) %>%
+  head(8) %>%
+  kable()
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+## cc_inv
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+cc_inv <- matrix(c(1/4,  1/4,  1/4,  1/4,
+                   1/2, -1/2,  1/2, -1/2,
+                   1/2, -1/2, -1/2,  1/2,
+                   0,   -1,    0,    1),
+nrow=4, ncol=4, byrow=TRUE,
+dimnames=list(contrast=c("intercept", "effectAvg",
+                         "deltaEffect", "deltaControl"),
+              arm=c("actChA", "ctlChA",
+                    "actChB", "ctlChB")))
+
+cc_inv %>% MASS::fractions()
+
+
+## -----------------------------------------------------------------------------
+cc <- solve(cc_inv)
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+cc %>% MASS::fractions()
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+contrasts(sim$arm) <- cc[, -1]
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+model_weibull1 <- bf(y | cens(1-event) ~ 1 + arm,
+                     family=weibull())
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+prior_weibull1 <- 
+  prior(normal(meanInter, log(4)/1.64), class="Intercept") +
+  prior(normal(0, sdEffect), coef=armeffectAvg) +
+  prior(normal(0, sdDeltaEffect), coef=armdeltaEffect) +
+  prior(normal(0, sdDeltaControl), coef=armdeltaControl) +
+  prior(gamma(0.1, 0.1), class=shape)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\small'
+stanvars_weibull1 <- 
+  stanvar(-log(log(2)/8), name = "meanInter") + 
+  stanvar(log(2)/1.64, name = "sdEffect") +
+  stanvar(log(1.25)/1.64, name = "sdDeltaEffect") +
+  stanvar(log(1.25)/1.64, name = "sdDeltaControl")
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+## fit_weibull1 <- brm(
+##   formula = model_weibull1,
+##   data = sim,
+##   prior = weibull_prior1,
+##   stanvars = stanvars_weibull1,
+##   ...
+## )
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| include: false
+fit_weibull1 <- brm(
+  formula = model_weibull1, 
+  data = sim, 
+  prior = prior_weibull1,
+  stanvars = stanvars_weibull1
+)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\tiny'
+summary(fit_weibull1)
+
+
+## -----------------------------------------------------------------------------
+#| echo: true
+#| eval: false
+## p_full_fup <- pp_check(
+##   fit_weibull1, type = "km_overlay",
+##   status_y = sim$event, ndraws = 100
+## )
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| fig-height: 4
+p_full_fup <- pp_check(
+  fit_weibull1, status_y=sim$event,
+  type="km_overlay", ndraws=100
+) +
+  scale_y_continuous(breaks=seq(0,1,by=0.1)) +
+  xlab("Time [month]") + coord_cartesian(xlim=c(0, 35))
+
+p_full_fup + coord_cartesian(xlim=c(0, 15))
+# p_full_fup
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+hdata1 %>%
+  select(y, event, arm, hist1) %>%
+  head(8) %>%
+  kable()
+
+
+## -----------------------------------------------------------------------------
+sim_comb <- bind_rows(sim, hdata1)
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+contrasts(sim_comb$arm) <- cc[, -1]
+
+
+## -----------------------------------------------------------------------------
+model_weibull2 <- bf(
+  y | cens(1-event) ~ 1 + arm + hist1, 
+  family=weibull()
+)
+
+
+## -----------------------------------------------------------------------------
+prior_weibull2 <- prior_weibull1 +
+  prior(student_t(6, 0, sdHist), coef = hist1)
+
+
+## -----------------------------------------------------------------------------
+stanvars_weibull2 <- stanvars_weibull1 +
+  stanvar(log(1.8)/1.64, name = "sdHist")
+
+
+## -----------------------------------------------------------------------------
+#| eval: false
+## fit_weibull2 <- brm(
+##   formula = model_weibull2,
+##   data = sim_comb,
+##   prior = weibull_prior2,
+##   stanvars = stanvars_weibull2,
+##   ...
+## )
+
+
+## -----------------------------------------------------------------------------
+#| echo: false
+#| include: false
+fit_weibull2 <- brm(
+  formula = model_weibull2, 
+  data = sim_comb, 
+  prior = prior_weibull2,
+  stanvars = stanvars_weibull2
+)
+
+
+## -----------------------------------------------------------------------------
+#| mysize: true
+#| size: '\tiny'
+summary(fit_weibull2)
+
diff --git a/workshops/jsm2024/slides/bamdd_jsm2024.pdf b/workshops/jsm2024/slides/bamdd_jsm2024.pdf
new file mode 100644
index 0000000..0f6feef
Binary files /dev/null and b/workshops/jsm2024/slides/bamdd_jsm2024.pdf differ