diff --git a/.lintr b/.lintr
index c2b2094f..f3e3fb1d 100644
--- a/.lintr
+++ b/.lintr
@@ -1,5 +1,6 @@
 linters: with_defaults(
   line_length_linter = line_length_linter(120),
   cyclocomp_linter = NULL,
-  object_usage_linter = NULL
+  object_usage_linter = NULL,
+  object_name_linter = NULL
   )
diff --git a/DESCRIPTION b/DESCRIPTION
index 9bb0f8cf..88616c81 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -35,7 +35,7 @@ Encoding: UTF-8
 Language: en-US
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.0
+RoxygenNote: 7.2.3
 Collate:
     'Phase1b-package.R'
     'betadiff.R'
diff --git a/R/dbetabinom.R b/R/dbetabinom.R
index cb95108e..a2a9d5c7 100644
--- a/R/dbetabinom.R
+++ b/R/dbetabinom.R
@@ -127,8 +127,8 @@ dbetaMix <- Vectorize(dbetaMix, vectorize.args = "x")
 ##' @param par the beta parameters matrix, with K rows and 2 columns,
 ##' corresponding to the beta parameters of the K components
 ##' @param weights the mixture weights of the beta mixture prior
-##' @param lower.tail logical; if TRUE (default), probabilities are P[X <= x],
-##' and otherwise P[X > x]
+##' @param lower.tail logical; if TRUE (default), probabilities are `P[X <= x]`,
+##' and otherwise `P[X > x]`
 ##' @return the (one minus) cdf value
 ##'
 ##' @export
diff --git a/R/plotBounds.R b/R/plotBounds.R
index 5b4bdb54..e05b2efd 100644
--- a/R/plotBounds.R
+++ b/R/plotBounds.R
@@ -15,8 +15,8 @@
 ##' @param yt  indicate the y axis: response rate is "p", number of responses
 ##' is "x"
 ##' @param add  add the boundary lines or not
-##' @param cols specific the color of [1] efficacy area [2] futility area
-##' [3] efficacy boundary [4] futility boundary
+##' @param cols specific the color of `[1]` efficacy area `[2]` futility area
+##' `[3]` efficacy boundary `[4]` futility boundary
 ##' @param lwds line width (a two dimensional vector)
 ##' @param ltype line type
 ##' @param lpch  a value of plotting characters or symbols
diff --git a/R/postprob.R b/R/postprob.R
index 766f2f72..1f6d65b4 100644
--- a/R/postprob.R
+++ b/R/postprob.R
@@ -29,9 +29,9 @@ postprobOld <- function(x, n, p, a = 1, b = 1) {
 ##' Compute the posterior probability to be above threshold,
 ##' with a beta mixture prior on the response rate.
 ##'
-##' Computes the posterior probability Pr(P_E > p | data). Prior is P_E ~
-##' sum(weights * beta(parE[, 1], parE[, 2])), i.e., a mixture of beta priors.
-##' Default is one component only with uniform or beta(1,1).
+##' Computes the posterior probability `Pr(P_E > p | data)`. Prior is
+##' `P_E ~ sum(weights * beta(parE[, 1], parE[, 2]))`, i.e., a mixture of beta priors.
+##' Default is one component only with uniform or `beta(1,1)`.
 ##'
 ##' We observed x successes in n trials. Note that \code{x} can be a vector.
 ##'
diff --git a/man/betadiff.Rd b/man/betadiff.Rd
index 640f54b3..acc76da1 100644
--- a/man/betadiff.Rd
+++ b/man/betadiff.Rd
@@ -38,40 +38,49 @@ the distribution of the difference of two beta distributions with parameters par
 parX <- c(1, 52)
 parY <- c(5.5, 20.5)
 
-z <- seq(from=-1, to=1, length=100)
-plot(z, dbetadiff(z, parY=parY, parX=parX),
-     type="l")
+z <- seq(from = -1, to = 1, length = 100)
+plot(z, dbetadiff(z, parY = parY, parX = parX),
+  type = "l"
+)
 
 ## calculate probability
 
 ## for Go:
-test <- integrate(f=dbetadiff,
-                  parY=parY,
-                  parX=parX,
-                  lower=0.15,
-                  upper=1)
+test <- integrate(
+  f = dbetadiff,
+  parY = parY,
+  parX = parX,
+  lower = 0.15,
+  upper = 1
+)
 str(test)
 test$value
 
 ## vary close to the Monte Carlo result:
-mean(rbeta(n=1e6, parY[1], parY[2]) -
-     rbeta(n=1e6, parX[1], parX[2]) > 0.15)
+mean(rbeta(n = 1e6, parY[1], parY[2]) -
+  rbeta(n = 1e6, parX[1], parX[2]) > 0.15)
 
 
 ## similar case for Stop:
-integrate(f=dbetadiff,
-          parY=parY,
-          parX=parX,
-          lower=-1,
-          upper=0.5)
+integrate(
+  f = dbetadiff,
+  parY = parY,
+  parX = parX,
+  lower = -1,
+  upper = 0.5
+)
 
-mean(rbeta(n=1e6, parY[1], parY[2]) -
-     rbeta(n=1e6, parX[1], parX[2]) < 0.5)
+mean(rbeta(n = 1e6, parY[1], parY[2]) -
+  rbeta(n = 1e6, parX[1], parX[2]) < 0.5)
 
-test <- qbetadiff(p=0.2,
-                  parY=parY,
-                  parX=parX)
-pbetadiff(q=test,
-          parY=parY,
-          parX=parX)
+test <- qbetadiff(
+  p = 0.2,
+  parY = parY,
+  parX = parX
+)
+pbetadiff(
+  q = test,
+  parY = parY,
+  parX = parX
+)
 }
diff --git a/man/boundsPostprob.Rd b/man/boundsPostprob.Rd
index 68b9a947..1cb2ae60 100644
--- a/man/boundsPostprob.Rd
+++ b/man/boundsPostprob.Rd
@@ -44,8 +44,10 @@ Futility boundary: find maximum x (xL) where Pr(P>p1|x,n,a,b) <= tL
 ## efficacy decision if more than 90\% probability to be above 20\% ORR,
 ## futility decision if less than 10\% probability to be above 20\% ORR,
 ## with uniform prior (i.e. beta(1, 1)) on the ORR:
-boundsPostprob(nvec=c(10,20,30,40), p0=0.20,
-               tL=0.10, tU=0.90, a=1, b=1)
+boundsPostprob(
+  nvec = c(10, 20, 30, 40), p0 = 0.20,
+  tL = 0.10, tU = 0.90, a = 1, b = 1
+)
 ## From this we see e.g. that at the third IA at 30 pts, we would stop for futility
 ## if 5 or less patients responded, and for efficacy if 9 or more pts responded.
 }
diff --git a/man/boundsPredprob.Rd b/man/boundsPredprob.Rd
index 89420347..e0e28cce 100644
--- a/man/boundsPredprob.Rd
+++ b/man/boundsPredprob.Rd
@@ -51,10 +51,11 @@ Pr(Pr(P > p | x, Y) >= tT | x) < phiL
 ## Interim efficacy decision if more than 90\% predictive probability reach this,
 ## interim futility decision if less than 10\% predictive probability.
 ## Uniform prior (i.e. beta(1, 1)) on the ORR:
-boundsPredprob(nvec=c(10,20,30,40), p=0.20, tT=0.80,
-               phiL=0.10, phiU=0.90, a=1, b=1)
+boundsPredprob(
+  nvec = c(10, 20, 30, 40), p = 0.20, tT = 0.80,
+  phiL = 0.10, phiU = 0.90, a = 1, b = 1
+)
 ## From this we see e.g. that at the first IA at 10 pts, we would stop for futility
 ## if no patient responded, and for efficacy if 4 or more pts responded.
-
 }
 \keyword{graphics}
diff --git a/man/dbetabinom.Rd b/man/dbetabinom.Rd
index fcedbabb..d4ede788 100644
--- a/man/dbetabinom.Rd
+++ b/man/dbetabinom.Rd
@@ -28,14 +28,14 @@ The beta-binomial density function has the following form:
 \deqn{p(x) = (m! / (x!*(m-x)!)) * Beta(x+a,m-x+b) / Beta(a,b)}
 }
 \examples{
-## Calculating the beta binomial density 
+## Calculating the beta binomial density
 ## x = 2; m = 29; a = 0.2; b = 0.4
-## p(x) = choose(29,2)*beta(2.2,27.4)/beta(0.2,0.4) = 0.04286893 
+## p(x) = choose(29,2)*beta(2.2,27.4)/beta(0.2,0.4) = 0.04286893
 ##
-dbetabinom(2,29,0.2,0.4)
+dbetabinom(2, 29, 0.2, 0.4)
 
 ## Can also specify x as a vector
 ## x = 1:28
 ##
-dbetabinom(1:28,29,0.2,0.4)
+dbetabinom(1:28, 29, 0.2, 0.4)
 }
diff --git a/man/getBetamixPost.Rd b/man/getBetamixPost.Rd
index e2141bf5..7758bbd5 100644
--- a/man/getBetamixPost.Rd
+++ b/man/getBetamixPost.Rd
@@ -24,12 +24,15 @@ Computes the posterior parameters of a beta mixture
 }
 \examples{
 ## example from Lee and Liu:
-getBetamixPost(x=16, n=23, par=t(c(0.6, 0.4)), weights=1)
-
-getBetamixPost(x=16, n=23,
-               par=
-               rbind(c(0.6, 0.4),
-                     c(1, 1)),
-               weights=c(0.6, 0.4))
+getBetamixPost(x = 16, n = 23, par = t(c(0.6, 0.4)), weights = 1)
 
+getBetamixPost(
+  x = 16, n = 23,
+  par =
+    rbind(
+      c(0.6, 0.4),
+      c(1, 1)
+    ),
+  weights = c(0.6, 0.4)
+)
 }
diff --git a/man/logit.Rd b/man/logit.Rd
index 372502f0..f09556bc 100644
--- a/man/logit.Rd
+++ b/man/logit.Rd
@@ -24,7 +24,7 @@ logit(x)
 
 ## Can also be a vector of probabilities
 ##
-x <- seq(0.1,0.9,0.1)
+x <- seq(0.1, 0.9, 0.1)
 logit(x)
 }
 \keyword{programming}
diff --git a/man/myPlot.Rd b/man/myPlot.Rd
index 45a23e55..b583c635 100644
--- a/man/myPlot.Rd
+++ b/man/myPlot.Rd
@@ -20,7 +20,7 @@ nothing, only produces the plot as side effect
 This function will plot the PDF of a beta distribution
 }
 \examples{
-myPlot(1,2)
-myPlot(1,1)
+myPlot(1, 2)
+myPlot(1, 1)
 }
 \keyword{graphics}
diff --git a/man/myPlotDiff.Rd b/man/myPlotDiff.Rd
index bcc0fb5e..6246d973 100644
--- a/man/myPlotDiff.Rd
+++ b/man/myPlotDiff.Rd
@@ -28,8 +28,8 @@ nothing, only produces the plot as side effect
 This function will plot the PDF of a diffience between two Beta distributions
 }
 \examples{
-myPlotDiff(c(5,10),c(2,5),0.2,0.05,1,0)
-myPlotDiff(c(5,10),c(2,5),0.2,0.05,1)
-myPlotDiff(c(5,10),c(2,5),0.2,0.05,0)
+myPlotDiff(c(5, 10), c(2, 5), 0.2, 0.05, 1, 0)
+myPlotDiff(c(5, 10), c(2, 5), 0.2, 0.05, 1)
+myPlotDiff(c(5, 10), c(2, 5), 0.2, 0.05, 0)
 }
 \keyword{graphics}
diff --git a/man/oc2.Rd b/man/oc2.Rd
index 8e7a3306..555694ef 100644
--- a/man/oc2.Rd
+++ b/man/oc2.Rd
@@ -106,149 +106,167 @@ approximately equal distance between the looks.
 }
 \examples{
 ## this looks OK now:
-oc2(method="Prior.PP",
-    histSize=1e5L,
-    trialSize=100,
-    drift=0,
-    controlRate=0.5,
-    nmeRate=0.70,
-    nSim=20,
-    delta=0.15)
+oc2(
+  method = "Prior.PP",
+  histSize = 1e5L,
+  trialSize = 100,
+  drift = 0,
+  controlRate = 0.5,
+  nmeRate = 0.70,
+  nSim = 20,
+  delta = 0.15
+)
 
 ## this one as well:
-oc2(method="Prior.Bayes",
-    histSize=1e6L,
-    trialSize=100,
-    drift=0,
-    controlRate=0.5,
-    nmeRate=0.65,
-    nSim=20,
-    delta=0.15)
+oc2(
+  method = "Prior.Bayes",
+  histSize = 1e6L,
+  trialSize = 100,
+  drift = 0,
+  controlRate = 0.5,
+  nmeRate = 0.65,
+  nSim = 20,
+  delta = 0.15
+)
 
 ## this example takes longer to run, therefore we don't execute it here:
-if(FALSE)
-{
-## the different methods we are looking at:
-methods <- c("PointMass.Bayes", "Prior.Bayes", "RCT.Bayes", "RCTvanilla.Bayes",
-             "PointMass.PP", "Prior.PP", "RCT.PP", "RCTvanilla.PP")
-
-## the control rate will always be 50\%
-## but the historical data will be generated randomly from that
-## binomial distribution!
-
-## delta will be 0.15
-
-## 200 simulations
-
-## the different prior sample sizes (historical data size)
-## histSizes <- c(10, 20, 50, 150)
-## later: add very large size, but with heterogeneity =>
-## mixture of beta priors
-histSizes <- c(20, 150)
-
-## the trial sample size (total)
-trialSizes <- c(40)
-
-## the drift
-drift <- c(0, 0.1, 0.2)
-
-## the different true rates for the NME:
-## nmeRates <- seq(from=0.05, to=0.95, by=0.05)
-nmeRates <- c(0.4, 0.5, 0.6, 0.7, 0.8)
-
-## so the whole grid is
-wholeGrid <- expand.grid(method=methods,
-                         drift=drift,
-                         histSize=histSizes,
-                         trialSize=trialSizes,
-                         nmeRate=nmeRates, stringsAsFactors = FALSE)
-
-## summarize the methods
-
-## compute the operating characteristics for all combinations
-if(file.exists(savefile <- "allSims4.RData"))
-{
+if (FALSE) {
+  ## the different methods we are looking at:
+  methods <- c(
+    "PointMass.Bayes", "Prior.Bayes", "RCT.Bayes", "RCTvanilla.Bayes",
+    "PointMass.PP", "Prior.PP", "RCT.PP", "RCTvanilla.PP"
+  )
+
+  ## the control rate will always be 50\%
+  ## but the historical data will be generated randomly from that
+  ## binomial distribution!
+
+  ## delta will be 0.15
+
+  ## 200 simulations
+
+  ## the different prior sample sizes (historical data size)
+  ## histSizes <- c(10, 20, 50, 150)
+  ## later: add very large size, but with heterogeneity =>
+  ## mixture of beta priors
+  histSizes <- c(20, 150)
+
+  ## the trial sample size (total)
+  trialSizes <- c(40)
+
+  ## the drift
+  drift <- c(0, 0.1, 0.2)
+
+  ## the different true rates for the NME:
+  ## nmeRates <- seq(from=0.05, to=0.95, by=0.05)
+  nmeRates <- c(0.4, 0.5, 0.6, 0.7, 0.8)
+
+  ## so the whole grid is
+  wholeGrid <- expand.grid(
+    method = methods,
+    drift = drift,
+    histSize = histSizes,
+    trialSize = trialSizes,
+    nmeRate = nmeRates, stringsAsFactors = FALSE
+  )
+
+  ## summarize the methods
+
+  ## compute the operating characteristics for all combinations
+  if (file.exists(savefile <- "allSims4.RData")) {
     load(savefile)
-} else {
+  } else {
 
     ## setup the result list
-    allOcs <- vector(mode="list",
-                     length=nrow(wholeGrid))
+    allOcs <- vector(
+      mode = "list",
+      length = nrow(wholeGrid)
+    )
 
-    for(i in seq_len(nrow(wholeGrid)))
+    for (i in seq_len(nrow(wholeGrid)))
     {
-        set.seed(i)
-        allOcs[[i]] <- with(wholeGrid[i, ],
-                            oc2(method=method,
-                                histSize=histSize,
-                                trialSize=trialSize,
-                                drift=drift,
-                                controlRate=0.5,
-                                nmeRate=nmeRate,
-                                nSim=200,
-                                delta=0.15))
+      set.seed(i)
+      allOcs[[i]] <- with(
+        wholeGrid[i, ],
+        oc2(
+          method = method,
+          histSize = histSize,
+          trialSize = trialSize,
+          drift = drift,
+          controlRate = 0.5,
+          nmeRate = nmeRate,
+          nSim = 200,
+          delta = 0.15
+        )
+      )
     }
 
     save(allOcs,
-         file=savefile)
-}
+      file = savefile
+    )
+  }
 
-length(allOcs)
-allOcs
+  length(allOcs)
+  allOcs
 
-allOcs[[1]]
+  allOcs[[1]]
 
-allPossibleNames <- colnames(allOcs[[1]])
-allPossibleNames
+  allPossibleNames <- colnames(allOcs[[1]])
+  allPossibleNames
 
-allOcsMatrix <-
-t(sapply(allOcs,
-         function(x){
-             res <- rep(NA, length(allPossibleNames))
-             names(res) <- allPossibleNames
-             res[colnames(x)] <- x
-             res
-         }))
+  allOcsMatrix <-
+    t(sapply(
+      allOcs,
+      function(x) {
+        res <- rep(NA, length(allPossibleNames))
+        names(res) <- allPossibleNames
+        res[colnames(x)] <- x
+        res
+      }
+    ))
 
 
-allOcsMatrix
-wholeMatrix <- cbind(wholeGrid, allOcsMatrix)
+  allOcsMatrix
+  wholeMatrix <- cbind(wholeGrid, allOcsMatrix)
 
-library(reshape)
+  library(reshape)
 
 
-## write a table to a Word file in the current directory
-outputTab <- function(tab,
-                      out="output.docx", # name of the output file
-                      digits=2)          # how many digits for numbers?
-{
+  ## write a table to a Word file in the current directory
+  outputTab <- function(tab,
+                        out = "output.docx", # name of the output file
+                        digits = 2) # how many digits for numbers?
+  {
     library(officer)
     doc <- read_docx()
     dat <- as.data.frame(tab)
     whichNum <- which(sapply(dat, is.numeric))
-    whichInt <- which(sapply(dat, function(x) {is.numeric(x) && all(x == round(x))}))
-    for(i in whichNum)
+    whichInt <- which(sapply(dat, function(x) {
+      is.numeric(x) && all(x == round(x))
+    }))
+    for (i in whichNum)
     {
-        if(i \%in\% whichInt)
-        {
-            dat[[i]] <- format(dat[[i]], nsmall=0)
-        } else {
-            dat[[i]] <- format(dat[[i]], digits=digits, nsmall=digits)
-        }
+      if (i \%in\% whichInt) {
+        dat[[i]] <- format(dat[[i]], nsmall = 0)
+      } else {
+        dat[[i]] <- format(dat[[i]], digits = digits, nsmall = digits)
+      }
     }
 
     doc <- body_add_table(doc, dat, style = "Normal Table")
     print(doc, target = paste0(getwd(), "/myreport.docx"))
-}
-
-
-## --------------------------------------------------
-## derive the tables
-## (here change drift and histSize values manually to get the
-## different tables for the slides)
-tab1 <- subset(wholeMatrix,
-               (drift==0.2) &
-               (histSize == 150) &
-               (method \%in\% ppNames))
+  }
+
+
+  ## --------------------------------------------------
+  ## derive the tables
+  ## (here change drift and histSize values manually to get the
+  ## different tables for the slides)
+  tab1 <- subset(
+    wholeMatrix,
+    (drift == 0.2) &
+      (histSize == 150) &
+      (method \%in\% ppNames)
+  )
 }
 }
diff --git a/man/oc3.Rd b/man/oc3.Rd
index 6efcfea6..84c5b5bd 100644
--- a/man/oc3.Rd
+++ b/man/oc3.Rd
@@ -103,141 +103,165 @@ approximately equal distance between the looks.
 }
 \examples{
 ## this looks OK now:
-oc3(method="Prior.PP",
-    histSize=1e5L,
-    trialSize=100,
-    controlRateDist=function(){rbeta(n=1, 10, 10)},
-    nmeRate=0.70,
-    nSim=20,
-    delta=0.15)
+oc3(
+  method = "Prior.PP",
+  histSize = 1e5L,
+  trialSize = 100,
+  controlRateDist = function() {
+    rbeta(n = 1, 10, 10)
+  },
+  nmeRate = 0.70,
+  nSim = 20,
+  delta = 0.15
+)
 
 ## this one as well:
-oc3(method="Prior.Bayes",
-    histSize=1e6L,
-    trialSize=100,
-    controlRateDist=function(){rbeta(n=1, 10, 10)},
-    nmeRate=0.65,
-    nSim=20,
-    delta=0.15)
+oc3(
+  method = "Prior.Bayes",
+  histSize = 1e6L,
+  trialSize = 100,
+  controlRateDist = function() {
+    rbeta(n = 1, 10, 10)
+  },
+  nmeRate = 0.65,
+  nSim = 20,
+  delta = 0.15
+)
 
 ## this example takes longer to run, therefore we don't execute it here:
-if(FALSE)
-{
-## the different methods we are looking at:
-methods <- c("PointMass.Bayes", "Prior.Bayes", "RCT.Bayes", "RCTvanilla.Bayes",
-             "PointMass.PP", "Prior.PP", "RCT.PP", "RCTvanilla.PP")
-
-## the control rate will come from a Beta(10, 10) distribution
-## and the historical data will be generated randomly from the resulting
-## binomial distribution!
-
-## delta will be 0.15
-
-## 200 simulations
-
-## the different prior sample sizes (historical data size)
-## histSizes <- c(10, 20, 50, 150)
-## later: add very large size, but with heterogeneity =>
-## mixture of beta priors
-histSizes <- c(20, 150)
-
-## the trial sample size (total)
-trialSizes <- c(40)
-
-## the different true rates for the NME:
-## nmeRates <- seq(from=0.05, to=0.95, by=0.05)
-nmeRates <- c(0.4, 0.5, 0.6, 0.7, 0.8)
-
-## so the whole grid is
-wholeGrid <- expand.grid(method=methods,
-                         histSize=histSizes,
-                         trialSize=trialSizes,
-                         nmeRate=nmeRates, stringsAsFactors = FALSE)
-
-## summarize the methods
-
-## compute the operating characteristics for all combinations
-if(file.exists(savefile <- "allSims4.RData"))
-{
+if (FALSE) {
+  ## the different methods we are looking at:
+  methods <- c(
+    "PointMass.Bayes", "Prior.Bayes", "RCT.Bayes", "RCTvanilla.Bayes",
+    "PointMass.PP", "Prior.PP", "RCT.PP", "RCTvanilla.PP"
+  )
+
+  ## the control rate will come from a Beta(10, 10) distribution
+  ## and the historical data will be generated randomly from the resulting
+  ## binomial distribution!
+
+  ## delta will be 0.15
+
+  ## 200 simulations
+
+  ## the different prior sample sizes (historical data size)
+  ## histSizes <- c(10, 20, 50, 150)
+  ## later: add very large size, but with heterogeneity =>
+  ## mixture of beta priors
+  histSizes <- c(20, 150)
+
+  ## the trial sample size (total)
+  trialSizes <- c(40)
+
+  ## the different true rates for the NME:
+  ## nmeRates <- seq(from=0.05, to=0.95, by=0.05)
+  nmeRates <- c(0.4, 0.5, 0.6, 0.7, 0.8)
+
+  ## so the whole grid is
+  wholeGrid <- expand.grid(
+    method = methods,
+    histSize = histSizes,
+    trialSize = trialSizes,
+    nmeRate = nmeRates, stringsAsFactors = FALSE
+  )
+
+  ## summarize the methods
+
+  ## compute the operating characteristics for all combinations
+  if (file.exists(savefile <- "allSims4.RData")) {
     load(savefile)
-} else {
+  } else {
 
     ## setup the result list
-    allOcs <- vector(mode="list",
-                     length=nrow(wholeGrid))
+    allOcs <- vector(
+      mode = "list",
+      length = nrow(wholeGrid)
+    )
 
-    for(i in seq_len(nrow(wholeGrid)))
+    for (i in seq_len(nrow(wholeGrid)))
     {
-        set.seed(i)
-        allOcs[[i]] <- with(wholeGrid[i, ],
-                            oc3(method=method,
-                                histSize=histSize,
-                                trialSize=trialSize,
-                                controlRateDist=function(){rbeta(n=1, 10, 10)},
-                                nmeRate=nmeRate,
-                                nSim=200,
-                                delta=0.15))
+      set.seed(i)
+      allOcs[[i]] <- with(
+        wholeGrid[i, ],
+        oc3(
+          method = method,
+          histSize = histSize,
+          trialSize = trialSize,
+          controlRateDist = function() {
+            rbeta(n = 1, 10, 10)
+          },
+          nmeRate = nmeRate,
+          nSim = 200,
+          delta = 0.15
+        )
+      )
     }
 
     save(allOcs,
-         file=savefile)
-}
+      file = savefile
+    )
+  }
 
-length(allOcs)
-allOcs
+  length(allOcs)
+  allOcs
 
-allOcs[[1]]
+  allOcs[[1]]
 
-allPossibleNames <- colnames(allOcs[[1]])
-allPossibleNames
+  allPossibleNames <- colnames(allOcs[[1]])
+  allPossibleNames
 
-allOcsMatrix <-
-t(sapply(allOcs,
-         function(x){
-             res <- rep(NA, length(allPossibleNames))
-             names(res) <- allPossibleNames
-             res[colnames(x)] <- x
-             res
-         }))
+  allOcsMatrix <-
+    t(sapply(
+      allOcs,
+      function(x) {
+        res <- rep(NA, length(allPossibleNames))
+        names(res) <- allPossibleNames
+        res[colnames(x)] <- x
+        res
+      }
+    ))
 
 
-allOcsMatrix
-wholeMatrix <- cbind(wholeGrid, allOcsMatrix)
+  allOcsMatrix
+  wholeMatrix <- cbind(wholeGrid, allOcsMatrix)
 
-library(reshape)
+  library(reshape)
 
 
-## write a table to a Word file in the current directory
-outputTab <- function(tab,
-                      out="output.docx", # name of the output file
-                      digits=2)          # how many digits for numbers?
-{
+  ## write a table to a Word file in the current directory
+  outputTab <- function(tab,
+                        out = "output.docx", # name of the output file
+                        digits = 2) # how many digits for numbers?
+  {
     library(officer)
     doc <- read_docx()
     dat <- as.data.frame(tab)
     whichNum <- which(sapply(dat, is.numeric))
-    whichInt <- which(sapply(dat, function(x) {is.numeric(x) && all(x == round(x))}))
-    for(i in whichNum)
+    whichInt <- which(sapply(dat, function(x) {
+      is.numeric(x) && all(x == round(x))
+    }))
+    for (i in whichNum)
     {
-        if(i \%in\% whichInt)
-        {
-            dat[[i]] <- format(dat[[i]], nsmall=0)
-        } else {
-            dat[[i]] <- format(dat[[i]], digits=digits, nsmall=digits)
-        }
+      if (i \%in\% whichInt) {
+        dat[[i]] <- format(dat[[i]], nsmall = 0)
+      } else {
+        dat[[i]] <- format(dat[[i]], digits = digits, nsmall = digits)
+      }
     }
 
     doc <- body_add_table(doc, dat, style = "Normal Table")
     writeDoc(doc, target = paste0(getwd(), "/myreport.docx"))
-}
-
-
-## --------------------------------------------------
-## derive the tables
-## (here change drift and histSize values manually to get the
-## different tables for the slides)
-tab1 <- subset(wholeMatrix,
-               (histSize == 150) &
-               (method \%in\% ppNames))
+  }
+
+
+  ## --------------------------------------------------
+  ## derive the tables
+  ## (here change drift and histSize values manually to get the
+  ## different tables for the slides)
+  tab1 <- subset(
+    wholeMatrix,
+    (histSize == 150) &
+      (method \%in\% ppNames)
+  )
 }
 }
diff --git a/man/ocPostprob.Rd b/man/ocPostprob.Rd
index bb95c5d0..a60b2d55 100644
--- a/man/ocPostprob.Rd
+++ b/man/ocPostprob.Rd
@@ -78,28 +78,36 @@ PrGrayZone: probability of no decision at the end ("gray zone")
 # multiple looks @ 10, 20, 30 patietns
 # True response rate of the treatment group=40\%
 # stop for futility: P(response rate < 20\% )> 60\%
-#s top for efficacy: P(response rate > 30\% )> 80\%
+# s top for efficacy: P(response rate > 30\% )> 80\%
 # prior of treatment arm parE= Beta(1,1)
-res1<-ocPostprob(nn=c(10,20,30), p=0.4, p0=0.2, p1=0.3, tL=0.6, tU=0.8, 
-                 parE = c(1, 1), ns = 1000)
+res1 <- ocPostprob(
+  nn = c(10, 20, 30), p = 0.4, p0 = 0.2, p1 = 0.3, tL = 0.6, tU = 0.8,
+  parE = c(1, 1), ns = 1000
+)
 res1$oc
 
 # this call will generate d (distance for random looks around the look locations)
 # based on "floor(min(nn - c(0,nn[-length(nn)]))/2)" as d is missing:
-res2<-ocPostprob(nn=c(10,20,30), p=0.4, p0=0.2, p1=0.3, tL=0.6, tU=0.8, 
-                 parE = c(1, 1), ns = 1000, nr=TRUE)
+res2 <- ocPostprob(
+  nn = c(10, 20, 30), p = 0.4, p0 = 0.2, p1 = 0.3, tL = 0.6, tU = 0.8,
+  parE = c(1, 1), ns = 1000, nr = TRUE
+)
 res2$oc
 
 # now d is specified:
-res3<-ocPostprob(nn=c(10,20,30), p=0.4, p0=0.2, p1=0.3, tL=0.6, tU=0.8, 
-                 parE = c(1, 1), ns = 1000, nr=TRUE, d=5)
+res3 <- ocPostprob(
+  nn = c(10, 20, 30), p = 0.4, p0 = 0.2, p1 = 0.3, tL = 0.6, tU = 0.8,
+  parE = c(1, 1), ns = 1000, nr = TRUE, d = 5
+)
 res3$oc
 
-# finally, we can also have separate specification of efficacy and 
+# finally, we can also have separate specification of efficacy and
 # futility analyses. E.g. here have futility decisions only at the final analysis:
-res4<-ocPostprob(nn=c(10,20,30), p=0.4, p0=0.2, p1=0.3, tL=0.6, tU=0.8, 
-                 parE = c(1, 1), ns = 1000, nr=TRUE, d=5,
-                 nnF=c(30))
+res4 <- ocPostprob(
+  nn = c(10, 20, 30), p = 0.4, p0 = 0.2, p1 = 0.3, tL = 0.6, tU = 0.8,
+  parE = c(1, 1), ns = 1000, nr = TRUE, d = 5,
+  nnF = c(30)
+)
 res4$oc
 # compared to res3, we see that there is no early futility stopping anymore,
 # and the overall probability for stopping for futility (which is the type II error here)
diff --git a/man/ocPostprobDist.Rd b/man/ocPostprobDist.Rd
index 9dac7837..045a7bc5 100644
--- a/man/ocPostprobDist.Rd
+++ b/man/ocPostprobDist.Rd
@@ -84,20 +84,22 @@ PrFutility: probability to decide for futility
 PrGrayZone: probability of no decision at the end ("gray zone")
 }
 \examples{
-#operating characteristics for posterior probability method with beta prior on SOC
+# operating characteristics for posterior probability method with beta prior on SOC
 
-#design details
-#multiple looks @ 10, 20, 30 patietns
-#True response rate of the treatment group=0.4
+# design details
+# multiple looks @ 10, 20, 30 patietns
+# True response rate of the treatment group=0.4
 
 # stop for efficacy (deltaE): P(pE > pS + deltaE) >tU
 # stop for futility (deltaF): P(pE < pS - deltaF) >tL
-# where pE is the response rate of treatment group, pS is the response rate of 
+# where pE is the response rate of treatment group, pS is the response rate of
 # control group. Both of them are random variables.
 
 
-res1<-ocPostprobDist(nn=c(10,20,30),p=0.4,deltaE=0.1,deltaF=-0.1,tL=0.6,tU=0.6,
-                      parE=c(1,1),parS=c(5,25),ns=100)
+res1 <- ocPostprobDist(
+  nn = c(10, 20, 30), p = 0.4, deltaE = 0.1, deltaF = -0.1, tL = 0.6, tU = 0.6,
+  parE = c(1, 1), parS = c(5, 25), ns = 100
+)
 
 res1$oc
 
@@ -105,22 +107,28 @@ res1$oc
 # generate random look locations around 10,20,30 patients
 # this call will generate d (distance for random looks around the look locations)
 # based on "floor(min(nn - c(0,nn[-length(nn)]))/2)" as d is missing:
-res2<-ocPostprobDist(nn=c(10,20,30),p=0.4,deltaE=0.1,deltaF=-0.1,tL=0.6,tU=0.6,
-                      parE=c(1,1),parS=c(5,25),ns=100,nr=TRUE)
+res2 <- ocPostprobDist(
+  nn = c(10, 20, 30), p = 0.4, deltaE = 0.1, deltaF = -0.1, tL = 0.6, tU = 0.6,
+  parE = c(1, 1), parS = c(5, 25), ns = 100, nr = TRUE
+)
 
 res2$oc
 
-#specify the distance for random looks around the look locations in nn (d=5 for illustration)
-res3<-ocPostprobDist(nn=c(10,20,30),p=0.4,deltaE=0.1,deltaF=-0.1,tL=0.6,tU=0.6,
-                      parE=c(1,1),parS=c(5,25),ns=100,nr=TRUE,d=5)
+# specify the distance for random looks around the look locations in nn (d=5 for illustration)
+res3 <- ocPostprobDist(
+  nn = c(10, 20, 30), p = 0.4, deltaE = 0.1, deltaF = -0.1, tL = 0.6, tU = 0.6,
+  parE = c(1, 1), parS = c(5, 25), ns = 100, nr = TRUE, d = 5
+)
 
 res3$oc
 
 
-# finally, we can also have separate specification of efficacy and futility analyses. E.g. 
+# finally, we can also have separate specification of efficacy and futility analyses. E.g.
 # here have futility decisions only at the final analysis:
-res4<-ocPostprobDist(nn=c(10,20,30),p=0.4,deltaE=0.1,deltaF=-0.1,tL=0.6,tU=0.6,
-                     parE=c(1,1),parS=c(5,25),ns=100,nr=TRUE,d=5,nnF=c(30))
+res4 <- ocPostprobDist(
+  nn = c(10, 20, 30), p = 0.4, deltaE = 0.1, deltaF = -0.1, tL = 0.6, tU = 0.6,
+  parE = c(1, 1), parS = c(5, 25), ns = 100, nr = TRUE, d = 5, nnF = c(30)
+)
 res4$oc
 # compared to res3, we see that there is no early futility stopping anymore,
 # and the overall probability for stopping for futility (which is the type II error here)
diff --git a/man/ocPredprob.Rd b/man/ocPredprob.Rd
index c2137341..e797f03f 100644
--- a/man/ocPredprob.Rd
+++ b/man/ocPredprob.Rd
@@ -93,31 +93,37 @@ PrGrayZone: probability of no decision at the end ("gray zone")
 }
 \examples{
 ## to examine operating characteristics of a phase Ib design with 2 interim analyses
-##(sample size @ 10, 20 using predictive probability) and one final analysis (sample size @ 30);
+## (sample size @ 10, 20 using predictive probability) and one final analysis (sample size @ 30);
 
-#design details
-#multiple looks @ 10, 20, 30 patietns
-#True response rate of the treatment group=40\%
-#control response rate=25\%
+# design details
+# multiple looks @ 10, 20, 30 patietns
+# True response rate of the treatment group=40\%
+# control response rate=25\%
 
-#denote treatment response rate as RRS
-#trial success is defined as: P(RRS>control)>tT
+# denote treatment response rate as RRS
+# trial success is defined as: P(RRS>control)>tT
 set.seed(20)
-res1<-ocPredprob(c(10,20,30), p=0.4, p0=0.25, tT=0.6, phiL=0.2,
-                 phiU=0.8, parE = c(1, 1), ns = 100)
+res1 <- ocPredprob(c(10, 20, 30),
+  p = 0.4, p0 = 0.25, tT = 0.6, phiL = 0.2,
+  phiU = 0.8, parE = c(1, 1), ns = 100
+)
 res1$oc
 
 
 # this call will generate d (distance for random looks around the look locations)
 # based on "floor(min(nn - c(0,nn[-length(nn)]))/2)" as d is missing:
 
-res2<-ocPredprob(c(10,20,30),0.4,p0=0.25,tT=0.6,phiL=0.2,phiU=0.8,
-                 parE=c(1,1),ns=100,nr=TRUE)
+res2 <- ocPredprob(c(10, 20, 30), 0.4,
+  p0 = 0.25, tT = 0.6, phiL = 0.2, phiU = 0.8,
+  parE = c(1, 1), ns = 100, nr = TRUE
+)
 res2$oc
 
 # now d is specified. note that d has to be a positive value;
-res3<-ocPredprob(c(10,20,30),0.4,p0=0.25,tT=0.6,phiL=0.2,phiU=0.8,
-                 parE=c(1,1),ns=100,nr=TRUE,d=5)
+res3 <- ocPredprob(c(10, 20, 30), 0.4,
+  p0 = 0.25, tT = 0.6, phiL = 0.2, phiU = 0.8,
+  parE = c(1, 1), ns = 100, nr = TRUE, d = 5
+)
 res3$oc
 
 
@@ -125,25 +131,29 @@ res3$oc
 # here have futility decisions only at the final analysis:
 
 
-res4<-ocPredprob(c(10,20,30),0.4,p0=0.25,tT=0.6,phiL=0.2,phiU=0.8,
-                 parE=c(1,1),ns=100,nr=TRUE,d=5,nnF=c(30))
+res4 <- ocPredprob(c(10, 20, 30), 0.4,
+  p0 = 0.25, tT = 0.6, phiL = 0.2, phiU = 0.8,
+  parE = c(1, 1), ns = 100, nr = TRUE, d = 5, nnF = c(30)
+)
 res4$oc
 # compared to res3, we see that there is no early futility stopping anymore,
 # and the overall probability for stopping for futility (which is the type II error here)
 # is much lower.
 
-#2)
-#to examine operating characteristics of a phase Ib design with a seperate
+# 2)
+# to examine operating characteristics of a phase Ib design with a seperate
 # rule for futility at final analysis
-#denote treatment response rate as RRS
-#trial success is defined as: P(RRS>p0)>tT
-#trial failure is defined as: P(RRS<p1)>tFu
-#(gray zone could occur in the final analysis)
+# denote treatment response rate as RRS
+# trial success is defined as: P(RRS>p0)>tT
+# trial failure is defined as: P(RRS<p1)>tFu
+# (gray zone could occur in the final analysis)
 
-#when tFu=1-tT and phiFu=1-phiL, this decisian rule (res5) is the same as the res1
+# when tFu=1-tT and phiFu=1-phiL, this decisian rule (res5) is the same as the res1
 
 set.seed(20)
-res5<-ocPredprob(c(10,20,30), p=0.4, p0=0.25, tT=0.6, tFu=0.4, phiFu=0.8,
-                 phiU=0.8, parE = c(1, 1), ns = 100)
+res5 <- ocPredprob(c(10, 20, 30),
+  p = 0.4, p0 = 0.25, tT = 0.6, tFu = 0.4, phiFu = 0.8,
+  phiU = 0.8, parE = c(1, 1), ns = 100
+)
 res5$oc
 }
diff --git a/man/ocPredprobDist.Rd b/man/ocPredprobDist.Rd
index 04fdab18..5911b8e6 100644
--- a/man/ocPredprobDist.Rd
+++ b/man/ocPredprobDist.Rd
@@ -101,36 +101,42 @@ PrGrayZone: probability of no decision at the end ("gray zone")
 }
 \examples{
 ## to examine operating characteristics of a phase Ib design with 2 interim analyses
-##(sample size @ 10, 20 using predictive probability) and one final analysis
+## (sample size @ 10, 20 using predictive probability) and one final analysis
 ## (sample size @ 30);
 
-#design details
-#multiple looks @ 10, 20, 30 patients
-#True response rate of the treatment group=0.4
-#response rate improvement (delta)=10\%  as an absolute value (default)
-#1)
-#denote treatment response rate as RRS
-#trial success is defined as: P(RRS>control+delta)>tT
-#note: ns is suggested to be a larger value than 10 in a real study in order to
-#achieve correct results
+# design details
+# multiple looks @ 10, 20, 30 patients
+# True response rate of the treatment group=0.4
+# response rate improvement (delta)=10\%  as an absolute value (default)
+# 1)
+# denote treatment response rate as RRS
+# trial success is defined as: P(RRS>control+delta)>tT
+# note: ns is suggested to be a larger value than 10 in a real study in order to
+# achieve correct results
 
 
 set.seed(20)
-res1<-ocPredprobDist(c(10,20,30),0.4,delta=0.1,tT=0.6,phiL=0.2,phiU=0.8,
-                parE=c(1,1),parS=c(5,25),ns=10)
+res1 <- ocPredprobDist(c(10, 20, 30), 0.4,
+  delta = 0.1, tT = 0.6, phiL = 0.2, phiU = 0.8,
+  parE = c(1, 1), parS = c(5, 25), ns = 10
+)
 res1$oc
 
 
 
-#this function will generate d based on "floor(min(nn - c(0,nn[-length(nn)]))/2)"
-#if d is missing
-res2<-ocPredprobDist(c(10,20,30),0.4,delta=0.1,tT=0.6,phiL=0.2,phiU=0.8,
-                     parE=c(1,1),parS=c(5,25),ns=10,nr=TRUE)
+# this function will generate d based on "floor(min(nn - c(0,nn[-length(nn)]))/2)"
+# if d is missing
+res2 <- ocPredprobDist(c(10, 20, 30), 0.4,
+  delta = 0.1, tT = 0.6, phiL = 0.2, phiU = 0.8,
+  parE = c(1, 1), parS = c(5, 25), ns = 10, nr = TRUE
+)
 res2$oc
 
-#note that d has to be a positive value;
-res3<-ocPredprobDist(c(10,20,30),0.4,delta=0.1,tT=0.6,phiL=0.2,phiU=0.8,
-                     parE=c(1,1),parS=c(5,25),ns=10,nr=TRUE,d=5)
+# note that d has to be a positive value;
+res3 <- ocPredprobDist(c(10, 20, 30), 0.4,
+  delta = 0.1, tT = 0.6, phiL = 0.2, phiU = 0.8,
+  parE = c(1, 1), parS = c(5, 25), ns = 10, nr = TRUE, d = 5
+)
 res3$oc
 
 
@@ -138,38 +144,45 @@ res3$oc
 # here have futility decisions only at the final analysis:
 
 
-res4<-ocPredprobDist(c(10,20,30),0.4,delta=0.1,tT=0.6,phiL=0.2,phiU=0.8,
-                     parE=c(1,1),parS=c(5,25),ns=10,nr=TRUE,d=5,nnF=c(30))
+res4 <- ocPredprobDist(c(10, 20, 30), 0.4,
+  delta = 0.1, tT = 0.6, phiL = 0.2, phiU = 0.8,
+  parE = c(1, 1), parS = c(5, 25), ns = 10, nr = TRUE, d = 5, nnF = c(30)
+)
 res4$oc
 # compared to res3, we see that there is no early futility stopping anymore,
 # and the overall probability for stopping for futility (which is the type II error here)
 # is much lower.
 
-#2)
-#to examine operating characteristics of a phase Ib design with a
-#seperate rule for futility at final analysis
-#denote treatment response rate as RRS
-#trial success is defined as: P(RRS>control+delta)>tT
-#trial failure is defined as: P(RRS<control+deltaFu)>tFu
-#(gray zone could occur in the final analysis)
+# 2)
+# to examine operating characteristics of a phase Ib design with a
+# seperate rule for futility at final analysis
+# denote treatment response rate as RRS
+# trial success is defined as: P(RRS>control+delta)>tT
+# trial failure is defined as: P(RRS<control+deltaFu)>tFu
+# (gray zone could occur in the final analysis)
 
 set.seed(20)
-res5<-ocPredprobDist(c(10,20,30),0.4,delta=0.1,deltaFu = 0.05,tT=0.6,tFu=0.6, phiFu=0.8,
-                     phiU=0.8, parE=c(1,1),parS=c(5,25),ns=10)
+res5 <- ocPredprobDist(c(10, 20, 30), 0.4,
+  delta = 0.1, deltaFu = 0.05, tT = 0.6, tFu = 0.6, phiFu = 0.8,
+  phiU = 0.8, parE = c(1, 1), parS = c(5, 25), ns = 10
+)
 res5$oc
 
 
-#when tFu=1-tT and phiFu=1-phiL, this decisian rule (res6) is the same as the res1
+# when tFu=1-tT and phiFu=1-phiL, this decisian rule (res6) is the same as the res1
 set.seed(20)
-res6<-ocPredprobDist(c(10,20,30),0.4,delta=0.1,tT=0.6,tFu=0.4, phiFu=0.8,phiU=0.8,
-                     parE=c(1,1),parS=c(5,25),ns=10)
+res6 <- ocPredprobDist(c(10, 20, 30), 0.4,
+  delta = 0.1, tT = 0.6, tFu = 0.4, phiFu = 0.8, phiU = 0.8,
+  parE = c(1, 1), parS = c(5, 25), ns = 10
+)
 res6$oc
 
-#If both phiL and phiFu arguments are specified, phiL will be overwrite by 1-phiFu.
+# If both phiL and phiFu arguments are specified, phiL will be overwrite by 1-phiFu.
 # See warning message.
 set.seed(20)
-res7<-ocPredprobDist(c(10,20,30),0.4,delta=0.1,tT=0.6,tFu=0.4, phiL=0.1,phiFu=0.8,phiU=0.8,
-                     parE=c(1,1),parS=c(5,25),ns=10)
+res7 <- ocPredprobDist(c(10, 20, 30), 0.4,
+  delta = 0.1, tT = 0.6, tFu = 0.4, phiL = 0.1, phiFu = 0.8, phiU = 0.8,
+  parE = c(1, 1), parS = c(5, 25), ns = 10
+)
 res7$oc
-
 }
diff --git a/man/ocRctPostprobDist.Rd b/man/ocRctPostprobDist.Rd
index 30b704a2..35dd2916 100644
--- a/man/ocRctPostprobDist.Rd
+++ b/man/ocRctPostprobDist.Rd
@@ -107,55 +107,63 @@ PrFutility: probability to decide for futility
 PrGrayZone: probability of no decision at the end ("gray zone")
 }
 \examples{
-#note, deltaF has to be a value between 0 and 1 including the bounds, or NULL.
+# note, deltaF has to be a value between 0 and 1 including the bounds, or NULL.
 
-res<-ocRctPostprobDist(nn=c(10,20,30), pE=0.4, pS=0.3, deltaE=0.15,deltaF=0.05, 
-                       relativeDelta=FALSE,
-                                tL=0.8, tU=0.8,
-                                parE=c(a=1, b=1),
-                                parS=c(a=1, b=1),
-                                randRatio=1,
-                                ns = 100, nr = FALSE, d = NULL)
+res <- ocRctPostprobDist(
+  nn = c(10, 20, 30), pE = 0.4, pS = 0.3, deltaE = 0.15, deltaF = 0.05,
+  relativeDelta = FALSE,
+  tL = 0.8, tU = 0.8,
+  parE = c(a = 1, b = 1),
+  parS = c(a = 1, b = 1),
+  randRatio = 1,
+  ns = 100, nr = FALSE, d = NULL
+)
 
 res$oc
 
 
-# separate specification of efficacy and futility analyses can be performed. E.g. 
+# separate specification of efficacy and futility analyses can be performed. E.g.
 # here have futility decisions only at the final analysis:
 
-res2<-ocRctPostprobDist(nn=c(10,20,30), pE=0.4, pS=0.3, deltaE=0.15,deltaF=0.05, 
-                        relativeDelta=FALSE,
-                        tL=0.8, tU=0.8,
-                        parE=c(a=1, b=1),
-                        parS=c(a=1, b=1),
-                        randRatio=1,
-                        ns = 100, nr = FALSE, d = NULL,nnF=c(30))
+res2 <- ocRctPostprobDist(
+  nn = c(10, 20, 30), pE = 0.4, pS = 0.3, deltaE = 0.15, deltaF = 0.05,
+  relativeDelta = FALSE,
+  tL = 0.8, tU = 0.8,
+  parE = c(a = 1, b = 1),
+  parS = c(a = 1, b = 1),
+  randRatio = 1,
+  ns = 100, nr = FALSE, d = NULL, nnF = c(30)
+)
 res2$oc
 # compared to res3, we see that there is no early futility stopping anymore,
 # and the overall probability for stopping for futility (which is the type II error here)
 # is much lower.
 
-# Also, when deltaF is set to NULL, the futility decision is made when the probability to 
+# Also, when deltaF is set to NULL, the futility decision is made when the probability to
 # be deltaE better than the control is lower than 1 - tL. i.e. Pr(pE-pS>deltaE)<1-tL
-res3<-ocRctPostprobDist(nn=c(10,20,30), pE=0.4, pS=0.3, deltaE=0.15,deltaF=NULL, 
-                        relativeDelta=FALSE,
-                       tL=0.2, tU=0.8,
-                       parE=c(a=1, b=1),
-                       parS=c(a=1, b=1),
-                       randRatio=1,
-                       ns = 100, nr = FALSE, d = NULL)
+res3 <- ocRctPostprobDist(
+  nn = c(10, 20, 30), pE = 0.4, pS = 0.3, deltaE = 0.15, deltaF = NULL,
+  relativeDelta = FALSE,
+  tL = 0.2, tU = 0.8,
+  parE = c(a = 1, b = 1),
+  parS = c(a = 1, b = 1),
+  randRatio = 1,
+  ns = 100, nr = FALSE, d = NULL
+)
 res3$oc
 
 # As when deltaF is set to null, it sometimes makes sense for a futility decision
 # to be made even when the treatment is better than the control, e.g. when that difference
 # is small. This can be accomplished by specifying a negative value for deltaF.
-res4 <- ocRctPostprobDist(nn=c(10,20,30), pE=0.4, pS=0.3,
-                          deltaE=0.15, deltaF=-0.05, 
-                          relativeDelta=FALSE,
-                          tL=0.2, tU=0.8,
-                          parE=c(a=1, b=1),
-                          parS=c(a=1, b=1),
-                          randRatio=1,
-                          ns = 100, nr = FALSE, d = NULL)
+res4 <- ocRctPostprobDist(
+  nn = c(10, 20, 30), pE = 0.4, pS = 0.3,
+  deltaE = 0.15, deltaF = -0.05,
+  relativeDelta = FALSE,
+  tL = 0.2, tU = 0.8,
+  parE = c(a = 1, b = 1),
+  parS = c(a = 1, b = 1),
+  randRatio = 1,
+  ns = 100, nr = FALSE, d = NULL
+)
 res4$oc
 }
diff --git a/man/ocRctPredprobDist.Rd b/man/ocRctPredprobDist.Rd
index fd02a1e2..8d4b46fb 100644
--- a/man/ocRctPredprobDist.Rd
+++ b/man/ocRctPredprobDist.Rd
@@ -118,50 +118,56 @@ PrFutility: probability to decide for futility
 PrGrayZone: probability of no decision at the end ("gray zone")
 }
 \examples{
-#similar input parameters as the oc.predprobDist function
-#default simulation number is 10000. for illustration, the ns is set as 100 to 
-#save program running time. Please note that 10 simulation run (ns=10) may not 
-#be sufficient for a consistent OC evaluation.
-#1)
+# similar input parameters as the oc.predprobDist function
+# default simulation number is 10000. for illustration, the ns is set as 100 to
+# save program running time. Please note that 10 simulation run (ns=10) may not
+# be sufficient for a consistent OC evaluation.
+# 1)
 set.seed(20)
-res<-ocRctPredprobDist(nn=c(10,20,30), pE=0.4, pS=0.3, delta=0.1, 
-                       relativeDelta=FALSE, tT=0.6,
-                                phiL=0.2, phiU=0.8,
-                                parE=c(a=1, b=1), parS=c(a=1, b=1),
-                                randRatio=1,
-                                ns = 10, nr = FALSE, d = NULL)
+res <- ocRctPredprobDist(
+  nn = c(10, 20, 30), pE = 0.4, pS = 0.3, delta = 0.1,
+  relativeDelta = FALSE, tT = 0.6,
+  phiL = 0.2, phiU = 0.8,
+  parE = c(a = 1, b = 1), parS = c(a = 1, b = 1),
+  randRatio = 1,
+  ns = 10, nr = FALSE, d = NULL
+)
 
 res$oc
 
-# separate specification of efficacy and futility analyses can be performed. E.g. 
+# separate specification of efficacy and futility analyses can be performed. E.g.
 # here have futility decisions only at the final analysis:
 set.seed(20)
-res1<-ocRctPredprobDist(nn=c(10,20,30), pE=0.4, pS=0.3, delta=0.1, relativeDelta=FALSE, 
-                        tT=0.6,
-                       phiL=0.2, phiU=0.8,
-                       parE=c(a=1, b=1), parS=c(a=1, b=1),
-                       randRatio=1,
-                       ns = 10, nr = FALSE, d = NULL,nnF=c(30))
+res1 <- ocRctPredprobDist(
+  nn = c(10, 20, 30), pE = 0.4, pS = 0.3, delta = 0.1, relativeDelta = FALSE,
+  tT = 0.6,
+  phiL = 0.2, phiU = 0.8,
+  parE = c(a = 1, b = 1), parS = c(a = 1, b = 1),
+  randRatio = 1,
+  ns = 10, nr = FALSE, d = NULL, nnF = c(30)
+)
 
 res1$oc
 
-#2)
-#to examine operating characters of a phase Ib design with a 
-#seperate rule for futility 
-#at final analysis
-#denote treatment response rate as RRS
-#trial success is defined as: P(RRS>control+delta)>tT
-#trial failure is defined as: P(RRS<control+deltaFu)>tFu
-#(gray zone could occur in the final analysis)
+# 2)
+# to examine operating characters of a phase Ib design with a
+# seperate rule for futility
+# at final analysis
+# denote treatment response rate as RRS
+# trial success is defined as: P(RRS>control+delta)>tT
+# trial failure is defined as: P(RRS<control+deltaFu)>tFu
+# (gray zone could occur in the final analysis)
 
 set.seed(20)
-res2<-ocRctPredprobDist(nn=c(10,20,30), pE=0.4, pS=0.3, delta=0.1, deltaFu=0.05, 
-                        relativeDelta=FALSE, 
-                        tT=0.6,tFu=0.6,
-                        phiFu=0.8, phiU=0.8,
-                        parE=c(a=1, b=1), parS=c(a=1, b=1),
-                        randRatio=1,
-                        ns = 10, nr = FALSE, d = NULL)
+res2 <- ocRctPredprobDist(
+  nn = c(10, 20, 30), pE = 0.4, pS = 0.3, delta = 0.1, deltaFu = 0.05,
+  relativeDelta = FALSE,
+  tT = 0.6, tFu = 0.6,
+  phiFu = 0.8, phiU = 0.8,
+  parE = c(a = 1, b = 1), parS = c(a = 1, b = 1),
+  randRatio = 1,
+  ns = 10, nr = FALSE, d = NULL
+)
 
 res2$oc
 }
diff --git a/man/pbetaMix.Rd b/man/pbetaMix.Rd
index 2990548c..2b875742 100644
--- a/man/pbetaMix.Rd
+++ b/man/pbetaMix.Rd
@@ -14,8 +14,8 @@ corresponding to the beta parameters of the K components}
 
 \item{weights}{the mixture weights of the beta mixture prior}
 
-\item{lower.tail}{logical; if TRUE (default), probabilities are P\link{X <= x},
-and otherwise P\link{X > x}}
+\item{lower.tail}{logical; if TRUE (default), probabilities are \code{P[X <= x]},
+and otherwise \code{P[X > x]}}
 }
 \value{
 the (one minus) cdf value
diff --git a/man/plotBounds.Rd b/man/plotBounds.Rd
index 71fd2d5c..92b38a4c 100644
--- a/man/plotBounds.Rd
+++ b/man/plotBounds.Rd
@@ -31,8 +31,8 @@ is "x"}
 
 \item{add}{add the boundary lines or not}
 
-\item{cols}{specific the color of \link{1} efficacy area \link{2} futility area
-\link{3} efficacy boundary \link{4} futility boundary}
+\item{cols}{specific the color of \verb{[1]} efficacy area \verb{[2]} futility area
+\verb{[3]} efficacy boundary \verb{[4]} futility boundary}
 
 \item{lwds}{line width (a two dimensional vector)}
 
@@ -56,12 +56,19 @@ and \code{\link{boundsPostprob}}
 }
 \examples{
 # examples
-plotBounds(boundsPredprob(nvec=c(10,20,30,40), p=0.20, tT=0.80,
-                          phiL=0.10, phiU=0.90, a=1, b=1), yt="x")
-plotBounds(boundsPredprob(nvec=c(10,20,30,40), p=0.20, tT=0.80,
-                          phiL=0.10, phiU=0.90, a=1, b=1), yt="p")
-plotBounds(boundsPostprob(nvec=c(10,20,30,40), p0=0.20,
-                          tL=0.10, tU=0.90, a=1, b=1), 
-           yt="p", add=TRUE)
+plotBounds(boundsPredprob(
+  nvec = c(10, 20, 30, 40), p = 0.20, tT = 0.80,
+  phiL = 0.10, phiU = 0.90, a = 1, b = 1
+), yt = "x")
+plotBounds(boundsPredprob(
+  nvec = c(10, 20, 30, 40), p = 0.20, tT = 0.80,
+  phiL = 0.10, phiU = 0.90, a = 1, b = 1
+), yt = "p")
+plotBounds(boundsPostprob(
+  nvec = c(10, 20, 30, 40), p0 = 0.20,
+  tL = 0.10, tU = 0.90, a = 1, b = 1
+),
+yt = "p", add = TRUE
+)
 }
 \keyword{graphics}
diff --git a/man/plotDecision.Rd b/man/plotDecision.Rd
index 88325829..7465a052 100644
--- a/man/plotDecision.Rd
+++ b/man/plotDecision.Rd
@@ -22,8 +22,8 @@ and a curve of the prob of a poor improvement over estunated diff
 }
 \examples{
 
-summaries<-do.call(cbind,lapply(c(0:8),sumTable,TotalSample=25,parX=c(1,52),cut_B=0.2,cut_W=0.05))
+summaries <- do.call(cbind, lapply(c(0:8), sumTable, TotalSample = 25, parX = c(1, 52), cut_B = 0.2, cut_W = 0.05))
 
-plotDecision(summaries,Pos_cut=60,Neg_cut=60)
+plotDecision(summaries, Pos_cut = 60, Neg_cut = 60)
 }
 \keyword{graphics}
diff --git a/man/plotOc.Rd b/man/plotOc.Rd
index 50816c37..67bef454 100644
--- a/man/plotOc.Rd
+++ b/man/plotOc.Rd
@@ -17,9 +17,9 @@ Reads results from \code{\link{ocPredprob}}, \code{\link{ocPostprob}}
 etc. and displays a bar plot of the operating characteristics
 }
 \examples{
-#get operating character result from oc.postprob
+# get operating character result from oc.postprob
 
-res1<-ocPostprob(nn=c(10,20,30), p=0.4, p0=0.2, p1=0.3, tL=0.6, tU=0.8, parE = c(1, 1), ns = 10000)
+res1 <- ocPostprob(nn = c(10, 20, 30), p = 0.4, p0 = 0.2, p1 = 0.3, tL = 0.6, tU = 0.8, parE = c(1, 1), ns = 10000)
 res1$oc
 
 plotOc(res1)
diff --git a/man/postprob.Rd b/man/postprob.Rd
index 6b5deb33..a19ea1b9 100644
--- a/man/postprob.Rd
+++ b/man/postprob.Rd
@@ -31,9 +31,9 @@ the other arguments (except \code{p} and \code{log.p} of course)}
 The posterior probability that the response rate P_E is above p.
 }
 \description{
-Computes the posterior probability Pr(P_E > p | data). Prior is P_E ~
-sum(weights * beta(parE\link{, 1}, parE\link{, 2})), i.e., a mixture of beta priors.
-Default is one component only with uniform or beta(1,1).
+Computes the posterior probability \code{Pr(P_E > p | data)}. Prior is
+\code{P_E ~ sum(weights * beta(parE[, 1], parE[, 2]))}, i.e., a mixture of beta priors.
+Default is one component only with uniform or \code{beta(1,1)}.
 }
 \details{
 We observed x successes in n trials. Note that \code{x} can be a vector.
@@ -51,7 +51,7 @@ and beta parameters.
 ## Pr(P_E > p | data) = 0.836
 ##
 
-postprob(x=16, n=23, p=0.60, par=c(0.6, 0.4))
+postprob(x = 16, n = 23, p = 0.60, par = c(0.6, 0.4))
 
 ## We could instead specify a mixture prior
 ## 2 component beta mixture prior, i.e.,
@@ -59,10 +59,13 @@ postprob(x=16, n=23, p=0.60, par=c(0.6, 0.4))
 ## Pr(P_E > p | data) = 0.823
 ##
 
-postprob(x=16, n=23, p=0.60,
-         par=
-         rbind(c(0.6, 0.4),
-               c(1, 1)),
-         weights=c(0.6, 0.4))
-
+postprob(
+  x = 16, n = 23, p = 0.60,
+  par =
+    rbind(
+      c(0.6, 0.4),
+      c(1, 1)
+    ),
+  weights = c(0.6, 0.4)
+)
 }
diff --git a/man/postprobDist.Rd b/man/postprobDist.Rd
index 0af127ba..4658f604 100644
--- a/man/postprobDist.Rd
+++ b/man/postprobDist.Rd
@@ -73,16 +73,18 @@ treatment is e.g. important for the futility decision making (see the
 }
 \examples{
 ## example similar to Lee and Liu:
-postprobDist(x=16, n=23, parE=c(0.6, 0.4), parS=c(0.6, 0.4))
+postprobDist(x = 16, n = 23, parE = c(0.6, 0.4), parS = c(0.6, 0.4))
 
 ## these two should give the same result:
-postprobDist(x = 27, n = 34,
-             xS = 0, nS = 0,
-             delta = 0.15,
-             parE = c(1, 1),
-             parS = c(50007530, 49924090))
+postprobDist(
+  x = 27, n = 34,
+  xS = 0, nS = 0,
+  delta = 0.15,
+  parE = c(1, 1),
+  parS = c(50007530, 49924090)
+)
 
-postprob(x=27, n=34, p=0.65, parE=c(1, 1))
+postprob(x = 27, n = 34, p = 0.65, parE = c(1, 1))
 ## ok, almost
 
 ## try out mixtures:
@@ -91,12 +93,18 @@ postprob(x=27, n=34, p=0.65, parE=c(1, 1))
 ## Note that very extreme beta parameters do no longer increase
 ## the return value, because then that mixture component is too
 ## unlikely a posteriori
-postprobDist(x=16, n=23,
-             parE=
-             rbind(c(0.6, 0.4),
-                   c(10, 20)),
-             parS=
-             rbind(c(0.6, 0.4),
-                   c(10, 10)),
-             weightsS=c(1, 3))
+postprobDist(
+  x = 16, n = 23,
+  parE =
+    rbind(
+      c(0.6, 0.4),
+      c(10, 20)
+    ),
+  parS =
+    rbind(
+      c(0.6, 0.4),
+      c(10, 10)
+    ),
+  weightsS = c(1, 3)
+)
 }
diff --git a/man/postprobOld.Rd b/man/postprobOld.Rd
index 9dd15b37..c2cbab63 100644
--- a/man/postprobOld.Rd
+++ b/man/postprobOld.Rd
@@ -39,5 +39,5 @@ P_E | data  ~ beta(a + x, b + n - x).
 ## Pr(P_E > p | data) = 0.8358808
 ##
 
-postprobOld(x=16, n=23, p=0.60, a=0.6, b=0.4)
+postprobOld(x = 16, n = 23, p = 0.60, a = 0.6, b = 0.4)
 }
diff --git a/man/predprob.Rd b/man/predprob.Rd
index 756a7840..3512b2a1 100644
--- a/man/predprob.Rd
+++ b/man/predprob.Rd
@@ -50,34 +50,42 @@ b: Pr(P_E > p | x, Y=i) using beta (mixture) posterior
 bgttheta: indicator I(b>thetaT)
 }
 \examples{
-## The original Lee and Liu (Table 1) example: 
+## The original Lee and Liu (Table 1) example:
 ## Nmax=40, x=16, n=23, beta(0.6,0.4) prior distribution,
 ## thetaT=0.9. The control response rate is 60\%:
-predprob(x=16, n=23, Nmax=40, p=0.6, thetaT=0.9, 
-         parE=c(0.6, 0.4))
+predprob(
+  x = 16, n = 23, Nmax = 40, p = 0.6, thetaT = 0.9,
+  parE = c(0.6, 0.4)
+)
 ## So the predictive probability is 56.6\%. 12 responses
 ## in the remaining 17 patients are required for success.
 
 ## Lowering/Increasing the probability threshold thetaT of course increases
 ## /decreases the predictive probability of success, respectively:
-predprob(x=16, n=23, Nmax=40, p=0.6, thetaT=0.8, 
-         parE=c(0.6, 0.4))
+predprob(
+  x = 16, n = 23, Nmax = 40, p = 0.6, thetaT = 0.8,
+  parE = c(0.6, 0.4)
+)
 ## 70.8\%
-predprob(x=16, n=23, Nmax=40, p=0.6, thetaT=0.95, 
-         parE=c(0.6, 0.4))
+predprob(
+  x = 16, n = 23, Nmax = 40, p = 0.6, thetaT = 0.95,
+  parE = c(0.6, 0.4)
+)
 ## 40.7\%
 
 ## Instead of a fixed beta prior on the response rate, dynamic borrowing
 ## from a previous data set is possible by using a beta-mixture prior.
 ## For example, assume we have a previous trial where we saw 25 responses
 ## in 40 patients. We would like to use information worth 10 patients in our
-## trial, but be robust against deviations from that response rate (maybe 
+## trial, but be robust against deviations from that response rate (maybe
 ## because it was conducted in slightly different disease or patients).
 ## Then we can use a beta mixture prior, with the informative component getting
 ## weight of 1/4:
-predprob(x=20, n=23, Nmax=40, p=0.6, thetaT=0.9, 
-         parE=rbind(c(1, 1), c(25, 15)),
-         weights=c(3, 1))
+predprob(
+  x = 20, n = 23, Nmax = 40, p = 0.6, thetaT = 0.9,
+  parE = rbind(c(1, 1), c(25, 15)),
+  weights = c(3, 1)
+)
 ## Since the response rate in the historical dataset is lower (62.5\% < 69.6\%)
 ## than in the trial, but similar, we notice that the predictive probability
 ## of success is now lower.
diff --git a/man/predprobDist.Rd b/man/predprobDist.Rd
index 639f96e7..88932f6e 100644
--- a/man/predprobDist.Rd
+++ b/man/predprobDist.Rd
@@ -95,61 +95,70 @@ b: matrix with Pr(P_E > P_S + delta | x, xS, Y=i, Z=j)
 bgttheta: matrix of indicators I(b>thetaT)
 }
 \examples{
-## The original Lee and Liu (Table 1) example: 
+## The original Lee and Liu (Table 1) example:
 ## Nmax=40, x=16, n=23, beta(0.6,0.4) prior distribution,
 ## thetaT=0.9. The control response rate is 60\%:
-predprob(x=16, n=23, Nmax=40, p=0.6, thetaT=0.9, 
-         parE=c(0.6, 0.4))
+predprob(
+  x = 16, n = 23, Nmax = 40, p = 0.6, thetaT = 0.9,
+  parE = c(0.6, 0.4)
+)
 ## So the predictive probability is 56.6\%. 12 responses
 ## in the remaining 17 patients are required for success.
 
-## Now to the modified example, where the control response 
+## Now to the modified example, where the control response
 ## rate p has a beta(7, 11) distribution.
 ## For example if the 60\% threshold stems from a trial
 ## with 10 patients, of which 6 were observed with response.
-predprobDist(x=16, n=23, Nmax=40, delta=0, thetaT=0.9, 
-             parE=c(0.6, 0.4), parS=c(7, 11))
+predprobDist(
+  x = 16, n = 23, Nmax = 40, delta = 0, thetaT = 0.9,
+  parE = c(0.6, 0.4), parS = c(7, 11)
+)
 ## Now only 11 responses are needed in the remaining 17 patients
-## in order to have a successful trial. 
+## in order to have a successful trial.
 ## Also, the predictive probability for a Go decision is now
 ## 70.8\% instead of merely 56.6\%.
 
 ## If the response threshold of 60\% stems from an SOC estimate (e.g. 50\% = 5/10)
 ## and a margin of e.g. 10\%, then the margin can be specified with
 ## the delta argument:
-predprobDist(x=16, n=23, Nmax=40, delta=0.1, thetaT=0.9, 
-             parE=c(1, 1), parS=c(6, 11))
+predprobDist(
+  x = 16, n = 23, Nmax = 40, delta = 0.1, thetaT = 0.9,
+  parE = c(1, 1), parS = c(6, 11)
+)
 ## This again changes the result: Only 10 future responses are required,
 ## the predictive probability of success is now 80\%.
 
 ## Next we will use a beta mixture prior, with a weight of 1/3 for an
 ## informative beta(50, 10) prior, on the experimental response rate:
-predprobDist(x=16, n=23, Nmax=40, delta=0.1, thetaT=0.9,
-             parE=rbind(c(1, 1), c(50, 10)),
-             weights=c(2, 1), parS=c(6, 11))
+predprobDist(
+  x = 16, n = 23, Nmax = 40, delta = 0.1, thetaT = 0.9,
+  parE = rbind(c(1, 1), c(50, 10)),
+  weights = c(2, 1), parS = c(6, 11)
+)
 ## Now still 10 future responses are required for success, but the predictive
 ## success probability is higher (87.2\%).
 
 ## We can also have additional controls in our trial. For example
 ## assume that in the interim analysis we had 10 control patients observed
-## with 5 responses out of 20 in total at the end. 
+## with 5 responses out of 20 in total at the end.
 ## We also had historical control data (say 60 patients of
-## which 20 responded), but in order to be robust against changes in the response 
+## which 20 responded), but in order to be robust against changes in the response
 # rate over time, we will again use a beta mixture, putting only 1/3 of weight
 ## on the historical controls:
-predprobDist(x=16, n=23, xS=5, nS=10,
-             Nmax=40, NmaxControl=20, 
-             delta=0.1, thetaT=0.9,
-             parE=rbind(c(1, 1), c(50, 10)),
-             weights=c(2, 1), 
-             parS=rbind(c(1, 1), c(20, 40)),
-             weightsS=c(2, 1))
+predprobDist(
+  x = 16, n = 23, xS = 5, nS = 10,
+  Nmax = 40, NmaxControl = 20,
+  delta = 0.1, thetaT = 0.9,
+  parE = rbind(c(1, 1), c(50, 10)),
+  weights = c(2, 1),
+  parS = rbind(c(1, 1), c(20, 40)),
+  weightsS = c(2, 1)
+)
 ## Now we only have 59.9\% predictive probability of success. The bgttheta matrix
 ## lists the cases where we would have success, for all possible combinations
-## of future responses in the control and experimental arms. We see that the 
-## success threshold for experimental responses depends on the number of 
+## of future responses in the control and experimental arms. We see that the
+## success threshold for experimental responses depends on the number of
 ## control responses.
-
 }
 \references{
 Lee, J. J., & Liu, D. D. (2008). A predictive probability
diff --git a/man/sumBetadiff.Rd b/man/sumBetadiff.Rd
index ee5c4cac..e99f7936 100644
--- a/man/sumBetadiff.Rd
+++ b/man/sumBetadiff.Rd
@@ -27,5 +27,5 @@ A function to summerize the characters of a betadiff distribution \code{\link{be
 \examples{
 parX <- c(1, 52)
 parY <- c(5.5, 20.5)
-sumBetadiff(parX,parY,0.9,cutB=0.8,cutW=0.2)
+sumBetadiff(parX, parY, 0.9, cutB = 0.8, cutW = 0.2)
 }
diff --git a/man/sumTable.Rd b/man/sumTable.Rd
index f2481b26..e09f7722 100644
--- a/man/sumTable.Rd
+++ b/man/sumTable.Rd
@@ -38,9 +38,9 @@ outcome scenario.
 }
 \examples{
 
-sumTable(2,25,parX=c(1,52),cut_B=0.2,cut_W=0.05,YPri=c(1,1))
+sumTable(2, 25, parX = c(1, 52), cut_B = 0.2, cut_W = 0.05, YPri = c(1, 1))
 
-#for multiple response scenarios (e.g. 0 to 8 responses out of 25)
-summaries<-do.call(cbind,lapply(c(0:8),sumTable,TotalSample=25,parX=c(1,52),cut_B=0.2,cut_W=0.05))
+# for multiple response scenarios (e.g. 0 to 8 responses out of 25)
+summaries <- do.call(cbind, lapply(c(0:8), sumTable, TotalSample = 25, parX = c(1, 52), cut_B = 0.2, cut_W = 0.05))
 summaries
 }