new chapter-strip-plot

_quarto.yml

@@ -25,9 +25,10 @@ book:
     - chapters/rcbd.qmd
     - chapters/split-plot-design.qmd
     - chapters/split-split-plot.qmd
+    - chapters/strip-plot.qmd
     - chapters/factorial-design.qmd
     - chapters/incomplete-block-design.qmd
-    - chapters/strip-plot.qmd
+    #- chapters/Lattice-design.qmd
     - chapters/repeated-measures.qmd
     #- chapters/glmm.qmd
     - chapters/special-conditions.qmd

chapters/Lattice-design.qmd

@@ -0,0 +1,153 @@
+# Lattice Design
+
+```{r, include=FALSE, echo=FALSE}
+source(here::here("settings.r"))
+```
+
+## Background
+
+Yates (1936) proposed this method of arranging agricultural variety trials involving a large number of crop varieties. These types of arrangements were named a quasi-factorial or lattice designs. His paper contained numerical examples based on the results of a uniformity trial on orange trees. A special feature of lattice designs is that the number of treatments, t, is related to the block size, k, in one of three forms: t = k^2^, t = k^3^, or t = k(k +1).
+
+Even though the number of possible treatments is limited, a lattice design may be an ideal design for field experiments with a large number of treatments.
+
+Statistical model for lattice design:
+
+$Y_{ijk} = \mu + \alpha_i + \gamma_j + \tau_t  + \beta_k + \epsilon_ijk$
+
+where, $\mu$ is the experiment mean, 𝛽 is the row effect, 𝛾 is the column effect, and 𝜏 is the treatment effect.
+
+## Example Analysis
+
+The data used in this example is from a balanced lattice experiment in cotton containing 16 treatments in a 4x4 layout in each of 5 replicates. The response variable in this data is the precentage of young flower buds attacked by boll weevils.
+
+Let's start the analysis firstly by loading the required libraries:
+
+::: panel-tabset
+### lme4
+
+```{r, message=FALSE, warning=FALSE}
+library(lme4); library(lmerTest); library(emmeans); library(performance)
+library(dplyr); library(broom.mixed); library(agridat); library(desplot)
+```
+
+### nlme
+```{r, message=FALSE, warning=FALSE}
+library(nlme); library(broom.mixed); library(emmeans); library(performance)
+library(dplyr); library(agridat); library(desplot)
+```
+:::
+
+Import data from agridat package. The data contains . This is a balanced experiment design
+```{r}
+data(cochran.lattice)
+dat2 <- cochran.lattice
+head(dat2)
+str(dat2)
+
+libs(desplot)
+desplot(dat2, y~row*col|rep,
+        text=trt, # aspect unknown, should be 2 or .5
+         main="cochran.lattice")
+
+```
+
+```{r}
+data(burgueno.rowcol)
+dat <- burgueno.rowcol
+head(dat)
+```
+Here, we can use the `desplot()` function from the 'desplot' package to visualize the plot plan from lattice design.
+```{r}
+# Two contiuous reps in 8 rows, 16 columns
+desplot(dat, yield ~ col*row,
+        out1=rep, # aspect unknown
+        text=gen, shorten="none", cex=0.75,
+        main="lattice design")
+
+```
+### Data integrity checks
+```{r, echo=FALSE}
+#| label: lattice_design
+#| fig-cap: "Histogram of the dependent variable."
+#| column: margin
+par(mar=c(5.1, 5, 2.1, 2.1))
+desplot(dat, yield ~ col*row,
+        out1=rep, # aspect unknown
+        text=gen, shorten="none", cex=.75,
+        main="burgueno.rowcol")
+```
+### Data integrity checks
+
+```{r}
+str(dat)
+```
+
+```{r}
+dat2$row <- as.factor(dat2$row)
+dat2$col <- as.factor(dat2$col)
+
+dat$row <- as.factor(dat$row)
+dat$col <- as.factor(dat$col)
+```
+
+```{r, eval=FALSE}
+hist(dat2$y, main = "", xlab = "yield")
+```
+
+```{r, echo=FALSE}
+#| label: fig-rcbd_hist
+#| fig-cap: "Histogram of the dependent variable."
+#| column: margin
+par(mar=c(5.1, 5, 2.1, 2.1))
+hist(dat$yield, main = "", xlab = "yield", cex.lab = 1.8, cex.axis = 1.5)
+```
+
+::: panel-tabset
+### lme4
+
+```{r}
+m1_a <- lmer(yield ~ gen + (1|row) + (1|col:rep) + (1|rep),
+           data = dat,
+           na.action = na.exclude)
+summary(m1_a) 
+```
+
+### nlme
+
+```{r}
+dat$dummy <- factor(1)
+
+m1_b <- lme(yield ~ gen,
+          random = list(dummy = pdBlocked(list(
+                                  pdIdent(~row - 1),
+                                  pdIdent(~rep - 1),
+                                  pdIdent(~col:rep)))),
+          data = dat, 
+          na.action = na.exclude)
+
+VarCorr(m1_b)
+```
+:::
+
+### Check Model Assumptions
+
+Remember those iid assumptions? Let's make sure we actually met them.
+
+```{r, fig.height=9}
+check_model(m1_a)
+```
+
+
+### Inference
+
+Estimates for each treatment level can be obtained with the 'emmeans' package. And we can extract the ANOVA table from model using `anova()` function.
+
+```{r}
+anova(m1_a)
+```
+
+Estimated marginal means
+
+```{r}
+emmeans(m1_a, ~ gen)
+```

chapters/incomplete-block-design.qmd

@@ -48,7 +48,7 @@ library(lme4); library(lmerTest); library(emmeans)
 library(dplyr); library(broom.mixed); library(performance)
 ```
 ### nlme
-```{r, message=FALSE, warning=FALSE, eval=FALSE}
+```{r, message=FALSE, warning=FALSE}
 library(nlme); library(broom.mixed); library(emmeans)
 library(dplyr); library(performance)
 ```
@@ -62,7 +62,7 @@ https://kwstat.github.io/agridat/reference/weiss.incblock.html
   dat <- weiss.incblock
 ```
 
-```{r, fig.height= 9}
+```{r, fig.height= 9, echo=FALSE}
  library(desplot)
   desplot(dat, yield~col*row,
           text=gen, shorten='none', cex=.6, out1=block,

chapters/strip-plot.qmd

@@ -1,153 +1,4 @@
 # Strip Plot Design
 
-```{r, include=FALSE, echo=FALSE}
-source(here::here("settings.r"))
-```
 
-## Background
 
-Yates (1936) proposed this method of arranging agricultural variety trials involving a large number of crop varieties. These types of arrangements were named a quasi-factorial or lattice designs. His paper contained numerical examples based on the results of a uniformity trial on orange trees. A special feature of lattice designs is that the number of treatments, t, is related to the block size, k, in one of three forms: t = k^2^, t = k^3^, or t = k(k +1).
-
-Even though the number of possible treatments is limited, a lattice design may be an ideal design for field experiments with a large number of treatments.
-
-Statistical model for lattice design:
-
-$Y_{ijk} = \mu + \alpha_i + \gamma_j + \tau_t  + \beta_k + \epsilon_ijk$
-
-where, $\mu$ is the experiment mean, 𝛽 is the row effect, 𝛾 is the column effect, and 𝜏 is the treatment effect.
-
-## Example Analysis
-
-The data used in this example is from a balanced lattice experiment in cotton containing 16 treatments in a 4x4 layout in each of 5 replicates. The response variable in this data is the precentage of young flower buds attacked by boll weevils.
-
-Let's start the analysis firstly by loading the required libraries:
-
-::: panel-tabset
-### lme4
-
-```{r, message=FALSE, warning=FALSE}
-library(lme4); library(lmerTest); library(emmeans); library(performance)
-library(dplyr); library(broom.mixed); library(agridat); library(desplot)
-```
-
-### nlme
-```{r, message=FALSE, warning=FALSE}
-library(nlme); library(broom.mixed); library(emmeans); library(performance)
-library(dplyr); library(agridat); library(desplot)
-```
-:::
-
-Import data from agridat package. The data contains . This is a balanced experiment design
-```{r}
-data(cochran.lattice)
-dat2 <- cochran.lattice
-head(dat2)
-str(dat2)
-
-libs(desplot)
-desplot(dat2, y~row*col|rep,
-        text=trt, # aspect unknown, should be 2 or .5
-         main="cochran.lattice")
-
-```
-
-```{r}
-data(burgueno.rowcol)
-dat <- burgueno.rowcol
-head(dat)
-```
-Here, we can use the `desplot()` function from the 'desplot' package to visualize the plot plan from lattice design.
-```{r}
-# Two contiuous reps in 8 rows, 16 columns
-desplot(dat, yield ~ col*row,
-        out1=rep, # aspect unknown
-        text=gen, shorten="none", cex=0.75,
-        main="lattice design")
-
-```
-### Data integrity checks
-```{r, echo=FALSE}
-#| label: lattice_design
-#| fig-cap: "Histogram of the dependent variable."
-#| column: margin
-par(mar=c(5.1, 5, 2.1, 2.1))
-desplot(dat, yield ~ col*row,
-        out1=rep, # aspect unknown
-        text=gen, shorten="none", cex=.75,
-        main="burgueno.rowcol")
-```
-### Data integrity checks
-
-```{r}
-str(dat)
-```
-
-```{r}
-dat2$row <- as.factor(dat2$row)
-dat2$col <- as.factor(dat2$col)
-
-dat$row <- as.factor(dat$row)
-dat$col <- as.factor(dat$col)
-```
-
-```{r, eval=FALSE}
-hist(dat2$y, main = "", xlab = "yield")
-```
-
-```{r, echo=FALSE}
-#| label: fig-rcbd_hist
-#| fig-cap: "Histogram of the dependent variable."
-#| column: margin
-par(mar=c(5.1, 5, 2.1, 2.1))
-hist(dat$yield, main = "", xlab = "yield", cex.lab = 1.8, cex.axis = 1.5)
-```
-
-::: panel-tabset
-### lme4
-
-```{r}
-m1_a <- lmer(yield ~ gen + (1|row) + (1|col:rep) + (1|rep),
-           data = dat,
-           na.action = na.exclude)
-summary(m1_a) 
-```
-
-### nlme
-
-```{r}
-dat$dummy <- factor(1)
-
-m1_b <- lme(yield ~ gen,
-          random = list(dummy = pdBlocked(list(
-                                  pdIdent(~row - 1),
-                                  pdIdent(~rep - 1),
-                                  pdIdent(~col:rep)))),
-          data = dat, 
-          na.action = na.exclude)
-
-VarCorr(m1_b)
-```
-:::
-
-### Check Model Assumptions
-
-Remember those iid assumptions? Let's make sure we actually met them.
-
-```{r, fig.height=9}
-check_model(m1_a)
-```
-
-
-### Inference
-
-Estimates for each treatment level can be obtained with the 'emmeans' package. And we can extract the ANOVA table from model using `anova()` function.
-
-```{r}
-anova(m1_a)
-```
-
-Estimated marginal means
-
-```{r}
-emmeans(m1_a, ~ gen)
-```