Prepare new CRAN release

jan-imbi · Jul 9, 2024 · 5ff20d4 · 5ff20d4
1 parent c2addc7
commit 5ff20d4
Show file tree

Hide file tree

Showing 9 changed files with 91 additions and 65 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -15,3 +15,5 @@
 ^.lintr$
 ^vignettes/presentation_onearm$
 ^README\.Rmd$
+^doc$
+^Meta$
diff --git a/.gitignore b/.gitignore
@@ -8,3 +8,5 @@ docs
 .lintr
 paper
 paper_testing_vs_estimation
+/doc/
+/Meta/
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: adestr
 Type: Package
 Title: Estimation in Optimal Adaptive Two-Stage Designs
-Version: 0.5.1
+Version: 0.5.2
 Authors@R:c(person("Jan", "Meis", role = c("aut", "cre"), email = "meis@imbi.uni-heidelberg.de", comment = c(ORCID = "0000-0001-5407-7220")),
   person("Martin", "Maechler", role = c("cph"), email = "maechler@stat.math.ethz.ch", comment = c(ORCID = "0000-0002-8685-9910", "Original author of monoSpl.c (from the 'stats' package).")))
 Description:

diff --git a/R/plot.R b/R/plot.R
@@ -1,3 +1,4 @@
+#nocov start
 #' Plot performance scores for point and interval estimators
 #'
 #' This function extract the values of mu and the score values and a facet plot with
@@ -457,3 +458,4 @@ plot_design <- function(design, data_distribution = Normal(two_armed = FALSE)){
     labs(color = "Type of design")
   ggarrange(pltn, pltc2, pltcp, ncol=3, common.legend = TRUE)
 }
+#nocov end
diff --git a/README.Rmd b/README.Rmd
@@ -16,6 +16,8 @@ knitr::opts_chunk$set(
 # adestr <a href='https://github.com/jan-imbi/adestr'><img src='man/figures/sticker.png' align="right" height="80" /></a>
 
 <!-- badges: start -->
+[![doi](https://img.shields.io/badge/doi-10.1002%2Fsim.10020-blue?link=https%3A%2F%2Fdoi.org%2F10.1002%2Fsim.10020)](https://doi.org/10.1002/sim.10020
+)
 [![R-CMD-check](https://github.com/jan-imbi/adestr/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/jan-imbi/adestr/actions/workflows/R-CMD-check.yaml)
 [![Codecov test coverage](https://codecov.io/gh/jan-imbi/adestr/branch/master/graph/badge.svg?token=ORYWTYOZPT)](https://app.codecov.io/gh/jan-imbi/adestr?branch=master)
 [![License](https://img.shields.io/badge/License-GPL_v2-blue.svg)](https://github.com/jan-imbi/adestr/blob/master/LICENSE.md)

diff --git a/README.md b/README.md
@@ -5,6 +5,7 @@
 
 <!-- badges: start -->
 
+[![doi](https://img.shields.io/badge/doi-10.1002%2Fsim.10020-blue?link=https%3A%2F%2Fdoi.org%2F10.1002%2Fsim.10020)](https://doi.org/10.1002/sim.10020)
 [![R-CMD-check](https://github.com/jan-imbi/adestr/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/jan-imbi/adestr/actions/workflows/R-CMD-check.yaml)
 [![Codecov test
 coverage](https://codecov.io/gh/jan-imbi/adestr/branch/master/graph/badge.svg?token=ORYWTYOZPT)](https://app.codecov.io/gh/jan-imbi/adestr?branch=master)

diff --git a/inst/CITATION b/inst/CITATION
@@ -0,0 +1,17 @@
+citHeader("To cite OptimalGoldstandardDesigns in publications use:")
+
+bibentry(
+bibtype = "Article",
+author = as.person("Jan Meis, Maximilian Pilz, Carolin Herrmann, Björn Bokelmann, Geraldine Rauch, Meinhard Kieser"),
+title = "Point estimation, confidence intervals, and P-values for optimal adaptive two-stage designs with normal endpoints",
+journal = "Statistics in Medicine",
+volume = "43",
+number = "8",
+pages = "1577-1603",
+keywords = "bias, confidence intervals, optimal adaptive designs, P-values, point estimation",
+doi = "10.1002/sim.10020",
+year = {2024},
+  textVersion = paste(
+  "Meis, J, Pilz, M, Herrmann, C, Bokelmann, B, Rauch, G, Kieser, M. Point estimation, confidence intervals, and P-values for optimal adaptive two-stage designs with normal endpoints. Statistics in Medicine. 2024; 43(8): 1577–1603. doi:10.1002/sim.10020"
+  )
+)
diff --git a/tests/testthat/test_LR_boundaries.R b/tests/testthat/test_LR_boundaries.R
@@ -1,21 +1,21 @@
-# test_that("implicit rejection boundary from Neyman-Pearson test matches c2",
-#           {
-#             p2 <- get_stagewise_estimators(NeymanPearsonOrderingPValue(0, 0.4),
-#                                      Normal(FALSE),
-#                                      FALSE,
-#                                      designad,
-#                                      1,
-#                                      FALSE)[[2]]
-#             expect_equal(
-#               implied_c2(
-#                 designad,
-#                 adoptr:::scaled_integration_pivots(designad),
-#                 p2,
-#                 1,
-#                 FALSE,
-#                 0.025
-#               ),
-#               designad@c2_pivots,
-#               tolerance = 1e-3
-#             )
-#           })
+test_that("implicit rejection boundary from Neyman-Pearson test matches c2",
+          {
+            p2 <- get_stagewise_estimators(NeymanPearsonOrderingPValue(0, 0.4),
+                                     Normal(FALSE),
+                                     FALSE,
+                                     designad,
+                                     1,
+                                     FALSE)[[2]]
+            expect_equal(
+              implied_c2(
+                designad,
+                adoptr:::scaled_integration_pivots(designad),
+                p2,
+                1,
+                FALSE,
+                0.025
+              ),
+              designad@c2_pivots,
+              tolerance = 1e-3
+            )
+          })
diff --git a/tests/testthat/test_against_reference.R b/tests/testthat/test_against_reference.R
@@ -55,49 +55,49 @@ test_that("bias reduced estimator agrees with reference implementation.",
                          sw$g2(designad, .3, .3, designad@n1, n2_extrapol(designad, smean_to_z(.3, designad@n1, 1, FALSE)), 1, FALSE),
                          tolerance = 1e-3)
           })
-# test_that("median unbiased (MLE ordering) estimator agrees with reference implementation.",
-#           {
-#             med <- get_stagewise_estimators(MedianUnbiasedMLEOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
-#             expect_equal(.median_unbiased_ml(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
-#                          med$g2(designad, .2, .2, designad@n1, n2(designad, smean_to_z(.2, designad@n1, 1, FALSE), round = FALSE), 1, FALSE),
-#                          tolerance = 1e-3)
-#           })
-# test_that("median unbiased (LR ordering) estimator agrees with reference implementation.",
-#           {
-#             med <- get_stagewise_estimators(MedianUnbiasedLikelihoodRatioOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
-#             expect_equal(.median_unbiased_lr(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
-#                          med$g2(designad, .2, .2, designad@n1, n2(designad, smean_to_z(.2, designad@n1, 1, FALSE), round = FALSE), 1, FALSE),
-#                          tolerance = 1e-3)
-#           })
-# test_that("median unbiased (ST ordering) estimator agrees with reference implementation.",
-#           {
-#             med <- get_stagewise_estimators(MedianUnbiasedScoreTestOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
-#             expect_equal(.median_unbiased_st(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
-#                          med$g2(designad, .2, .2, designad@n1, n2(designad, smean_to_z(.2, designad@n1, 1, FALSE), round = FALSE), 1, FALSE),
-#                          tolerance = 1e-3)
-#           })
-# test_that("median unbiased (SWCF ordering) estimator agrees with reference implementation.",
-#           {
-#             med <- get_stagewise_estimators(MedianUnbiasedStagewiseCombinationFunctionOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
-#             expect_equal(.median_unbiased_swcf(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
-#                          med$g2(designad, .2, .2, designad@n1, n2(designad, smean_to_z(.2, designad@n1, 1, FALSE), round = FALSE), 1, FALSE),
-#                          tolerance = 1e-3)
-#           })
-# test_that("median unbiased (SWCF ordering) estimator agrees with reference implementation.",
-#           {
-#             p <- get_stagewise_estimators(NeymanPearsonOrderingPValue(0, 0.4), Normal(FALSE), FALSE, designad, 1, FALSE)
-#             expect_equal(.p_np(x1 = .2, x2 = .2, mu = 0, mu0 = 0, mu1 = .4, sigma = 1, design = designad),
-#                          p$g2(designad, .2, .2, designad@n1, n2(designad, smean_to_z(.2, designad@n1, 1, FALSE), round = FALSE), 1, FALSE),
-#                          tolerance = 1e-3)
-#           })
-# test_that("P-value (Neyman-Pearson ordering) agrees with reference implementation.",
-#           {
-#             p <- get_stagewise_estimators(NeymanPearsonOrderingPValue(0, 0.4), Normal(FALSE), FALSE, designad, 1, FALSE)
-#             expect_equal(.p_np(x1 = .2, x2 = .2, mu = 0, mu0 = 0, mu1 = .4, sigma = 1, design = designad),
-#                          p$g2(designad, .2, .2, designad@n1, n2(designad, smean_to_z(.2, designad@n1, 1, FALSE), round = FALSE), 1, FALSE),
-#                          tolerance = 1e-3)
-#           })
-#
+test_that("median unbiased (MLE ordering) estimator agrees with reference implementation.",
+          {
+            med <- get_stagewise_estimators(MedianUnbiasedMLEOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
+            expect_equal(.median_unbiased_ml(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
+                         med$g2(designad, .2, .2, designad@n1, n2_extrapol(designad, smean_to_z(.2, designad@n1, 1, FALSE)), 1, FALSE),
+                         tolerance = 1e-3)
+          })
+test_that("median unbiased (LR ordering) estimator agrees with reference implementation.",
+          {
+            med <- get_stagewise_estimators(MedianUnbiasedLikelihoodRatioOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
+            expect_equal(.median_unbiased_lr(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
+                         med$g2(designad, .2, .2, designad@n1, n2_extrapol(designad, smean_to_z(.2, designad@n1, 1, FALSE)), 1, FALSE),
+                         tolerance = 1e-3)
+          })
+test_that("median unbiased (ST ordering) estimator agrees with reference implementation.",
+          {
+            med <- get_stagewise_estimators(MedianUnbiasedScoreTestOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
+            expect_equal(.median_unbiased_st(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
+                         med$g2(designad, .2, .2, designad@n1, n2_extrapol(designad, smean_to_z(.2, designad@n1, 1, FALSE)), 1, FALSE),
+                         tolerance = 1e-3)
+          })
+test_that("median unbiased (SWCF ordering) estimator agrees with reference implementation.",
+          {
+            med <- get_stagewise_estimators(MedianUnbiasedStagewiseCombinationFunctionOrdering(), Normal(FALSE), FALSE, designad, 1, FALSE)
+            expect_equal(.median_unbiased_swcf(x1 = .2, x2 = .2, mu0 = 0, sigma = 1, designad),
+                         med$g2(designad, .2, .2, designad@n1, n2_extrapol(designad, smean_to_z(.2, designad@n1, 1, FALSE)), 1, FALSE),
+                         tolerance = 1e-3)
+          })
+test_that("median unbiased (SWCF ordering) estimator agrees with reference implementation.",
+          {
+            p <- get_stagewise_estimators(NeymanPearsonOrderingPValue(0, 0.4), Normal(FALSE), FALSE, designad, 1, FALSE)
+            expect_equal(.p_np(x1 = .2, x2 = .2, mu = 0, mu0 = 0, mu1 = .4, sigma = 1, design = designad),
+                         p$g2(designad, .2, .2, designad@n1, n2_extrapol(designad, smean_to_z(.2, designad@n1, 1, FALSE)),0, 1, FALSE),
+                         tolerance = 1e-3)
+          })
+test_that("P-value (Neyman-Pearson ordering) agrees with reference implementation.",
+          {
+            p <- get_stagewise_estimators(NeymanPearsonOrderingPValue(0, 0.4), Normal(FALSE), FALSE, designad, 1, FALSE)
+            expect_equal(.p_np(x1 = .2, x2 = .2, mu = 0, mu0 = 0, mu1 = .4, sigma = 1, design = designad),
+                         p$g2(designad, .2, .2, designad@n1, n2_extrapol(designad, smean_to_z(.2, designad@n1, 1, FALSE)),0, 1, FALSE),
+                         tolerance = 1e-3)
+          })
+