Update branch cran

.Rbuildignore

@@ -6,3 +6,4 @@
 ^README\.Rmd$
 ^LICENSE\.md$
 ^Thumbs.db$
+^\.github$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

.github/workflows/R-CMD-check.yaml

@@ -0,0 +1,49 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+ push:
+ branches: [main, master]
+ pull_request:
+ branches: [main, master]
+
+name: R-CMD-check
+
+jobs:
+ R-CMD-check:
+ runs-on: ${{ matrix.config.os }}
+
+ name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+ strategy:
+ fail-fast: false
+ matrix:
+ config:
+ - {os: macos-latest, r: 'release'}
+ - {os: windows-latest, r: 'release'}
+ - {os: ubuntu-latest, r: 'devel', http-user-agent: 'release'}
+ - {os: ubuntu-latest, r: 'release'}
+ - {os: ubuntu-latest, r: 'oldrel-1'}
+
+ env:
+ GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+ R_KEEP_PKG_SOURCE: yes
+
+ steps:
+ - uses: actions/checkout@v3
+
+ - uses: r-lib/actions/setup-pandoc@v2
+
+ - uses: r-lib/actions/setup-r@v2
+ with:
+ r-version: ${{ matrix.config.r }}
+ http-user-agent: ${{ matrix.config.http-user-agent }}
+ use-public-rspm: true
+
+ - uses: r-lib/actions/setup-r-dependencies@v2
+ with:
+ extra-packages: any::rcmdcheck
+ needs: check
+
+ - uses: r-lib/actions/check-r-package@v2
+ with:
+ upload-snapshots: true

.github/workflows/test-coverage.yaml

@@ -0,0 +1,50 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+ push:
+ branches: [main, master]
+ pull_request:
+ branches: [main, master]
+
+name: test-coverage
+
+jobs:
+ test-coverage:
+ runs-on: ubuntu-latest
+ env:
+ GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+ steps:
+ - uses: actions/checkout@v3
+
+ - uses: r-lib/actions/setup-r@v2
+ with:
+ use-public-rspm: true
+
+ - uses: r-lib/actions/setup-r-dependencies@v2
+ with:
+ extra-packages: any::covr
+ needs: coverage
+
+ - name: Test coverage
+ run: |
+ covr::codecov(
+ quiet = FALSE,
+ clean = FALSE,
+ install_path = file.path(Sys.getenv("RUNNER_TEMP"), "package")
+ )
+ shell: Rscript {0}
+
+ - name: Show testthat output
+ if: always()
+ run: |
+ ## --------------------------------------------------------------------
+ find ${{ runner.temp }}/package -name 'testthat.Rout*' -exec cat '{}' \; || true
+ shell: bash
+
+ - name: Upload test results
+ if: failure()
+ uses: actions/upload-artifact@v3
+ with:
+ name: coverage-test-failures
+ path: ${{ runner.temp }}/package

DESCRIPTION

@@ -1,20 +1,23 @@
 Package: blindrecalc
 Type: Package
 Title: Blinded Sample Size Recalculation
-Version: 0.1.2
+Version: 1.0.1
 Authors@R:
  c(person(given = "Lukas",
  family = "Baumann", 
- role = c("aut"),
- email = "[email protected]"),
+ role = c("aut", "cre"),
+ email = "[email protected]",
+ comment = c(ORCID = "0000-0001-7931-7470")),
  person(given = "Maximilian", 
  family = "Pilz",
- role = c("aut", "cre"),
- email = "[email protected]"),
- person(given = "Institute of Medical Biometry and Informatics - University of Heidelberg",
+ role = c("aut"),
+ email = "[email protected]",
+ comment = c(ORCID = "0000-0002-9685-1613")),
+ person(given = "Institute of Medical Biometry - University of Heidelberg",
  role = c("cph")))
 Description: Computation of key characteristics and plots for blinded sample size recalculation.
  Continuous as well as binary endpoints are supported in superiority and non-inferiority trials.
+ See Baumann, Pilz, Kieser (2022) <doi:10.32614/RJ-2022-001> for a detailed description.
  The implemented methods include the approaches by
  Lu, K. (2019) <doi:10.1002/pst.1737>,
  Kieser, M. and Friede, T. (2000) <doi:10.1002/(SICI)1097-0258(20000415)19:7%3C901::AID-SIM405%3E3.0.CO;2-L>,
@@ -41,6 +44,6 @@ Collate:
  FarringtonManning.R 
  FarringtonManning_helper.R
  RcppExports.R
-RoxygenNote: 7.1.0
+RoxygenNote: 7.2.3
 LinkingTo: 
  Rcpp

LICENSE

@@ -1,2 +1,2 @@
-YEAR: 2019
+YEAR: 2022
 COPYRIGHT HOLDER: Institute of Medical Biometry and Informatics - University of Heidelberg

NEWS.md

@@ -0,0 +1,5 @@
+# blindrecalc 1.0.0
+
+* fix documentation to pass CRAN check
+
+* add reference to R Journal publication

R/ChiSquare.R

@@ -1,14 +1,16 @@
 #' Type I Error Rate
 #'
-#' Computes the type I error rate of designs with blinded sample size recalculation
-#' or of fixed designs for one or several values of the nuisance parameter.
+#' Computes the type I error rate of designs with blinded sample size
+#' recalculation or of fixed designs for one or several values of the
+#' nuisance parameter.
 #'
 #' @template methods_chisquare
 #' @template recalculation
 #' @template allocation_chisquare
 #' @template dotdotdot
 #'
-#' @return One type I error rate value for every nuisance parameter and every value of n1.
+#' @return One type I error rate value for every nuisance parameter and
+#' every value of n1.
 #'
 #' @details The method is only vectorized in either \code{nuisance}
 #' or \code{n1}.
@@ -23,6 +25,7 @@ setMethod("toer", signature("ChiSquare"),
  function(design, n1, nuisance, recalculation,
  allocation = c("exact", "approximate", "kf_approx"), ...) {
  allocation <- match.arg(allocation)
+ # Check if input is valid
  if (allocation == "exact") {
  if (sum(n1 %% (design@r + 1) != 0) > 0) {
  stop("No integer sample sizes.")
@@ -37,11 +40,12 @@ setMethod("toer", signature("ChiSquare"),
  if (sum(design@n_max < n1) > 0) {
  stop("n_max is smaller than n1.")
  }
-
+ # Check whether n1 or nuisance is a vector
  if ((length(n1) > 1) & (length(nuisance) > 1)) {
  stop("only one of n1 and nuisance can have length > 1")
  } else if (length(n1) > 1) {
  if (recalculation) {
+ # Create matrix with total sample sizes
  nmat <- lapply(n1, function(x) get_nmat_chisq(design, x, allocation, ...))
  mapply(chisq_recalc_reject, n1 = n1, nmat = nmat,
  MoreArgs = list(design = design, nuisance = nuisance, type = "size"))
@@ -50,13 +54,15 @@ setMethod("toer", signature("ChiSquare"),
  }
  } else if (length(nuisance) > 1) {
  if (recalculation) {
+ # Create matrix with total sample sizes
  nmat <- get_nmat_chisq(design, n1, allocation, ...)
  sapply(nuisance, function(x) chisq_recalc_reject(design, n1, x, "size", nmat))
  } else {
  sapply(nuisance, function(x) chisq_fix_reject(design, n1, x, "size"))
  }
  } else {
  if (recalculation) {
+ # Create matrix with total sample sizes
  nmat <- get_nmat_chisq(design, n1, allocation, ...)
  chisq_recalc_reject(design, n1, nuisance, "size", nmat)
  } else {
@@ -92,6 +98,7 @@ setMethod("pow", signature("ChiSquare"),
  function(design, n1, nuisance, recalculation,
  allocation = c("exact", "approximate", "kf_approx"), ...) {
  allocation <- match.arg(allocation)
+ # Check if input is valid
  if (allocation == "exact") {
  if (n1 %% (design@r + 1) != 0) {
  stop("No integer sample sizes for first stage.")
@@ -107,10 +114,12 @@ setMethod("pow", signature("ChiSquare"),
  stop("n_max is smaller than n1.")
  }
 
+ # Check whether n1 or nuisance is a vector
  if ((length(n1) > 1) & (length(nuisance) > 1)) {
  stop("Only one of n1 and nuisance can have length > 1")
  } else if (length(n1) > 1) {
  if (recalculation) {
+ # Create matrix with total sample sizes
  nmat <- lapply(n1, function(x) get_nmat_chisq(design, x, allocation, ...))
  mapply(chisq_recalc_reject, n1 = n1, nmat = nmat,
  MoreArgs = list(design = design, nuisance = nuisance, type = "power"))
@@ -119,13 +128,15 @@ setMethod("pow", signature("ChiSquare"),
  }
  } else if (length(nuisance) > 1) {
  if (recalculation) {
+ # Create matrix with total sample sizes
  nmat <- get_nmat_chisq(design, n1, allocation, ...)
  sapply(nuisance, function(x) chisq_recalc_reject(design, n1, x, "power", nmat))
  } else {
  sapply(nuisance, function(x) chisq_fix_reject(design, n1, x, "power"))
  }
  } else {
  if (recalculation) {
+ # Create matrix with total sample sizes
  nmat <- get_nmat_chisq(design, n1, allocation, ...)
  chisq_recalc_reject(design, n1, nuisance, "power", nmat)
  } else {
@@ -143,15 +154,13 @@ setMethod("pow", signature("ChiSquare"),
 #' nuisance parameter or of n1.
 #'
 #' @template methods_chisquare
-#' @param summary Logical. If \code{TRUE} (default) a summary of the sample
-#' size distribution is printed. If \code{FALSE} all sample sizes are
-#' printed.
+#' @template summary
 #' @template plot
 #' @template allocation_chisquare
 #' @template dotdotdot
 #'
-#' @details Only sample sizes that occur with a probability of at least 0.01% are
-#' considered.
+#' @details Only sample sizes that occur with a probability of at least 0.01%
+#' are considered.
 #'
 #' @return Summary and/or plot of the sample size distribution for
 #' every nuisance parameter and every value of n1.
@@ -169,6 +178,7 @@ setMethod("n_dist", signature("ChiSquare"),
  function(design, n1, nuisance, summary = TRUE, plot = FALSE,
  allocation = c("exact", "approximate"), ...) {
  allocation <- match.arg(allocation)
+ # Check if input is valid
  if (allocation == "exact") {
  if (sum(n1 %% (design@r + 1) != 0) > 0) {
  stop("No integer sample sizes for first stage.")
@@ -181,9 +191,11 @@ setMethod("n_dist", signature("ChiSquare"),
  stop("Nuisance has to be within [0, 1].")
  }
 
+ # Check whether n1 or nuisance is a vector
  if ((length(n1) > 1) & (length(nuisance) > 1)) {
  stop("Only one of n1 and nuisance can have length > 1.")
  } else if (length(n1) == 1) {
+ # Calculate possible total sample sizes and probabilities
  out <- lapply(nuisance, function(x) n_distrib_chisq(design, n1, x, allocation, ...))
  out <- Map(cbind, out, nuisance = nuisance)
  out <- do.call("rbind", out)
@@ -247,6 +259,7 @@ setMethod("adjusted_alpha", signature("ChiSquare"),
  function(design, n1, nuisance, nuis_ass, precision = 0.001, gamma = 0,
  recalculation, allocation = c("exact", "approximate"), ...) {
  allocation <- match.arg(allocation)
+ # Check if input is valid
  if (allocation == "exact") {
  if (n1 %% (design@r + 1) != 0) {
  stop("No integer sample sizes for first stage.")
@@ -261,6 +274,7 @@ setMethod("adjusted_alpha", signature("ChiSquare"),
 
  alpha_nom <- design@alpha - gamma
  if (recalculation) {
+ # iteratively reduce the significance level until it is sufficiently small
  repeat {
  nmat <- get_nmat_chisq(design, n1, allocation, ...)
  alpha_max <- max(sapply(nuisance,
@@ -269,6 +283,7 @@ setMethod("adjusted_alpha", signature("ChiSquare"),
  design@alpha <- design@alpha - precision
  }
  } else {
+ # iteratively reduce the significance level until it is sufficiently small
  repeat {
  alpha_max <- max(sapply(nuisance,
  function(x) chisq_fix_reject(design, n1, x, "size")))
@@ -293,10 +308,10 @@ setMethod("adjusted_alpha", signature("ChiSquare"),
 #' @param design Object of class \code{ChiSquare} created by \code{setupChiSquare}.
 #' @param nuisance Value of the nuisance parameter. For the
 #' Chi-Squared test this is the overall response rate.
-#' @param variance A character string indicating whether the "\code{heterogenous}" (default)
-#' or the "\code{homogeneous}" variance formula should be used.
-#' @param rounded Whether the calculated sample size should be rounded up such that
-#' the allocation ratio is preserved.
+#' @param variance A character string indicating whether the "\code{heterogenous}"
+#' (default) or the "\code{homogeneous}" variance formula should be used.
+#' @param rounded Whether the calculated sample size should be rounded up such
+#' that the allocation ratio is preserved.
 #' @template dotdotdot
 #'
 #' @return One value of the fixed sample size for every nuisance parameter
@@ -315,9 +330,11 @@ setMethod("n_fix", signature("ChiSquare"),
  function(design, nuisance, variance = c("heterogeneous", "homogeneous"),
  rounded = TRUE, ...) {
  variance <- match.arg(variance)
+ # Check if input is valid
  if (sum(nuisance < 0) + sum(nuisance > 1) > 0) {
  stop("Nuisance has to be within [0, 1].")
  }
+ # Use recursion if nuisance is a vector
  if (length(nuisance) > 1) {
  sapply(nuisance, function(x) n_fix(design = design, nuisance = x,
  variance = variance, rounded = rounded, ...))

R/ChiSquare_helper.R

@@ -1,3 +1,5 @@
+# Helper function that creates a matrix with the total sample sizes
+# for all possible outcomes of the internal pilot study
 get_nmat_chisq <- function(design, n1, allocation, ...) {
  n_c1 <- ceiling(n1 / (design@r + 1))
  n_e1 <- ceiling(n1 * design@r / (design@r + 1))
@@ -21,6 +23,8 @@ get_nmat_chisq <- function(design, n1, allocation, ...) {
  return(as.matrix(out.mat))
 }
 
+# Helper function that calculates the probability for all possible
+# total sample sizes based on n1 and nuisance
 n_distrib_chisq <- function(design, n1, nuisance, allocation, ...) {
  p_e <- nuisance + design@delta / (1 + design@r)
  p_c <- p_e - design@delta