Merge branch 'develop' of https://github.com/MeikeSteinhilber/sprtt i…

…nto develop

.Rbuildignore

@@ -16,3 +16,6 @@
 ^CRAN-RELEASE$
 ^test_ANOVA\.R$
 ^compare_anova_script\.csv$
+^revdep$
+^lastMiKTeXException$
+^CRAN-SUBMISSION$

DESCRIPTION

@@ -18,14 +18,12 @@ Authors@R:
              comment = c(ORCID = "0000-0001-7248-0662"))
       )
 Maintainer: Meike Steinhilber <Meike.Steinhilber@aol.com>
-Description: 
-    It is a toolbox for Sequential Probability Ratio Tests (SPRT),  Wald (1945) <doi:10.2134/agronj1947.00021962003900070011x>.
+Description: It is a toolbox for Sequential Probability Ratio Tests (SPRT),  Wald (1945) <doi:10.2134/agronj1947.00021962003900070011x>.
     SPRTs are applied to the data during the sampling process, ideally after each observation.
     At any stage, the test will return a decision to either continue sampling or terminate and accept one of the specified hypotheses.
-    The seq_ttest() function performs sequential t tests developed by Rushton (1950) <doi:10.2307/2332385>, Rushton (1952) <doi:10.2307/2334026> and Hajnal (1961) <doi:10.2307/2333131>, based on the SPRT.
-    Specifically, seq_ttest() performs one-sample, two-sample, and paired t tests for testing one- and two-sided hypotheses.
-    For more information on the SPRT t test, see Schnuerch & Erdfelder (2019) <doi:10.1037/met0000234>.
-    The seq_anova() function allows to perform a sequential one-way fixed effects ANOVA (see Steinhilber et al. (2023) <> ).
+    The seq_ttest() function performs one-sample, two-sample, and paired t-tests for testing one- and two-sided hypotheses (Schnuerch & Erdfelder (2019) <doi:10.1037/met0000234>).
+    The seq_anova() function allows to perform a sequential one-way fixed effects ANOVA (Steinhilber et al. (2023) <doi:10.31234/osf.io/m64ne>).
+    Learn more about the package by using vignettes "browseVignettes(package = "sprtt")" or go to the website <https://meikesteinhilber.github.io/sprtt/>.
 License: AGPL (>= 3)
 URL: https://meikesteinhilber.github.io/sprtt/
 BugReports: https://github.com/MeikeSteinhilber/sprtt/issues

R/calc_plot_sprt.R

@@ -19,11 +19,17 @@ calc_plot_anova <- function(seq_anova_arguments, seq_steps) {
     stop("wrong input for seq_steps argument.")
   }
 
-
   lr_log <- double(length(seq_steps))
   sample_size <- double(length(seq_steps))
   i = 1
 
+  k_groups_start <- table(seq_anova_arguments@data[1:seq_steps[1], 2])
+
+  if (any(k_groups_start < 2)) {
+    stop("The first 2*k_groups data points are not balanced. Every group needs two data points.
+         Solution: Use the argument 'plot' to define a customized vector with the sample size steps in the seq_anova() function")
+  }
+
   for (position in seq_steps) {
     temp_arguments@data <- seq_anova_arguments@data[1:position, ]
     temp_arguments@total_sample_size <- position

R/draw_sample_mixture.R

@@ -17,7 +17,8 @@ rnorm_mix <- function(n, mu1, sig1, mu2, sig2, gamma) {
 #' @param f Cohen's f. The simulated effect size.
 #' @param max_n sample size for the groups (total sample size = max_n*k_groups)
 #' @param counter_n number of times the function tries to find a possible parameter combination for the distribution. Default value is set to 100.
-#' @param verbose `TRUE` or `FALSE.` Print out more information about the internal process of sampling the parameters.
+#' @param verbose `TRUE` or `FALSE.` Print out more information about the internal process of sampling the parameters
+#' (the internal counter that was reached, some additional hints and the drawn parameters for the Gaussian Mixture distributions.)
 #'
 #' @return returns a data.frame with the columns y (observations) and x (factor_A).
 #'

R/plot_sprt.R

@@ -11,9 +11,10 @@
 # #' @param B_boundary_log Log of the B boundary.
 #' @param anova_results result object of the seq_anova() function (argument must be of class `seq_anova_results`).
 #' @param labels show labels in the plot.
-#' @param position_labels_x position of the boundary labels on the x-axis.
-#' @param position_labels_y position of the boundary labels on the y-axis.
-#' @param position_lr_x scales the position of the LR label on the x-axis.
+#' @param position_labels_x position of the boundary labels on the x-axis. 0 positions the center on the 0 of the x-axis.
+#' @param position_labels_y position of the boundary labels on the y-axis. 0 positions the labels on the dotted lines.
+#' @param position_lr_x scales the position of the LR label on the x-axis. 0 positions the label directly under the last calculated LR.
+#' @param position_lr_y scales the position of the LR label on the x-axis. 0 positions the label on the 0 of the y-axis
 #' @param font_size font size of the plot.
 #' @param line_size line size of the plot.
 #' @param highlight_color highlighting color, default is "#CD2626" (red).
@@ -30,6 +31,7 @@ plot_anova <- function(anova_results,
                       position_labels_x = 0.15,
                       position_labels_y = 0.075,
                       position_lr_x = 0.05,
+                      position_lr_y = NULL,
                       font_size = 25,
                       line_size = 1.5,
                       highlight_color = "#CD2626"
@@ -42,6 +44,10 @@ plot_anova <- function(anova_results,
     stop("anova_results argument must be of class seq_anova_results.")
   }
 
+  if (is.null(anova_results@plot)) {
+    stop("The anova_results@plot is NULL. Solution: The function argument `plot` must be set to TRUE in the seq_anova() function.")
+  }
+
   A_boundary_log <- anova_results@plot$A_boundary_log
   B_boundary_log <- anova_results@plot$B_boundary_log
 
@@ -106,11 +112,13 @@ plot_anova <- function(anova_results,
       if (labels == TRUE) {
         LR <- round(exp(results$lr_log[N_steps]), 2)
         nLR <- results$sample_size[N_steps]
-        if (results$lr_log[N_steps]>0) {y_ = -0.5} else{y_ = 0.5}
+        if (is.null(position_lr_y)) {
+          if (results$lr_log[N_steps]>0) {position_lr_y = -0.5} else{position_lr_y = 0.5}
+        }
         plot <- plot +
           annotate(geom = "text",
                    x = results$sample_size[N_steps] + results$sample_size[N_steps]*position_lr_x,
-                   y = y_,
+                   y = position_lr_y,
                    label = glue("LR[{nLR}] ==~ {LR}"),
                    parse = TRUE,
                    size = font_size/.pt, color = highlight_color)

R/seq_anova.R

@@ -11,7 +11,7 @@
 #' `r lifecycle::badge("experimental")`
 #'
 #' Performs a sequential one-way fixed effects ANOVA, see Steinhilber et al. (2023) <doi:10.31234/osf.io/m64ne>
-#' for more information.
+#' for more information. The repeated measurement ANOVA is not implemented yet in this function. For more information check out the vignette `vignette("one_way_anova", package = "sprtt")`
 #'
 #' @param formula A formula specifying the model.
 #' @param data A data frame in which the variables specified in the formula will be found.
@@ -30,6 +30,7 @@
 #' If the data do not fit to this, you have to specify the sequential steps yourself in this argument.
 #' `balanced` specifies that the step size is equal to the number of groups.
 #' Attention: the calculation starts at the number of groups times two.
+#' If the data do not fit to this, you have to specify the sequential steps yourself in this argument.
 #'
 #'@return An object of the S4 class [`seq_anova_results-class`]. Click on the
 #' class link to see the full description of the slots.

README.Rmd

@@ -5,7 +5,7 @@ editor_options:
     mode: gfm
 ---
 
-<!-- <a href='https://meikesteinhilber.github.io/sprtt/'><img src="man/figures/logo.png" align="right" height="139"/></a> <br> <br> -->
+<!-- ATTENTION! see below -->
 
 ```{r setup, include=FALSE}
 knitr::opts_chunk$set(
@@ -25,7 +25,7 @@ options(tibble.print_min = 5, tibble.print_max = 5)
 [![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/sprtt?color=green)](https://cran.r-project.org/package=sprtt)
 [![total](https://cranlogs.r-pkg.org/badges/grand-total/sprtt)](https://cran.r-project.org/package=sprtt)
 [![monthly](https://cranlogs.r-pkg.org/badges/sprtt)](https://cran.r-project.org/package=sprtt)
-[![codecov](https://codecov.io/gh/MeikeSteinhilber/sprtt/branch/main/graph/badge.svg?token=IQHTDTRBAW)](https://codecov.io/gh/MeikeSteinhilber/sprtt) [![pkgdown](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/pkgdown-pak.yaml/badge.svg)](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/pkgdown-pak.yaml) [![R-CMD-check](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/R-CMD-check-windows-macOs.yaml/badge.svg)](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/R-CMD-check-windows-macOs.yaml)
+[![codecov](https://codecov.io/gh/MeikeSteinhilber/sprtt/branch/main/graph/badge.svg?token=IQHTDTRBAW)](https://app.codecov.io/gh/MeikeSteinhilber/sprtt) [![pkgdown](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/pkgdown-pak.yaml/badge.svg)](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/pkgdown-pak.yaml) [![R-CMD-check](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/R-CMD-check-windows-macOs.yaml/badge.svg)](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/R-CMD-check-windows-macOs.yaml)
 
 
 <!-- badges: end -->
@@ -84,6 +84,13 @@ Short examples can be found in the following paragraph.
 >
 > `#> results of function()`: is console output
 
-```{r, code=xfun::read_utf8('inst/examples/seq_ttest.R')}
+<!--
+
+ATTENTION!
+
+in the .md file must be changed by hand. Otherwise the picture is not found on the website and CRAN.
+<img src="man/figures/figure-gfm/unnamed-chunk-3-1.png" width="100%" />
+-->
+```{r, code=xfun::read_utf8('inst/examples/sprtt_examples.R')}
 
 ```

README.md

@@ -1,5 +1,5 @@
 
-<!-- <a href='https://meikesteinhilber.github.io/sprtt/'><img src="man/figures/logo.png" align="right" height="139"/></a> <br> <br> -->
+<!-- ATTENTION! see below -->
 
 # sprtt
 
@@ -8,7 +8,7 @@
 [![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/sprtt?color=green)](https://cran.r-project.org/package=sprtt)
 [![total](https://cranlogs.r-pkg.org/badges/grand-total/sprtt)](https://cran.r-project.org/package=sprtt)
 [![monthly](https://cranlogs.r-pkg.org/badges/sprtt)](https://cran.r-project.org/package=sprtt)
-[![codecov](https://codecov.io/gh/MeikeSteinhilber/sprtt/branch/main/graph/badge.svg?token=IQHTDTRBAW)](https://codecov.io/gh/MeikeSteinhilber/sprtt)
+[![codecov](https://codecov.io/gh/MeikeSteinhilber/sprtt/branch/main/graph/badge.svg?token=IQHTDTRBAW)](https://app.codecov.io/gh/MeikeSteinhilber/sprtt)
 [![pkgdown](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/pkgdown-pak.yaml/badge.svg)](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/pkgdown-pak.yaml)
 [![R-CMD-check](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/R-CMD-check-windows-macOs.yaml/badge.svg)](https://github.com/MeikeSteinhilber/sprtt/actions/workflows/R-CMD-check-windows-macOs.yaml)
 
@@ -79,13 +79,20 @@ Short examples can be found in the following paragraph.
 >
 > `#> results of function()`: is console output
 
+<!--
+&#10;ATTENTION!
+&#10;in the .md file must be changed by hand. Otherwise the picture is not found on the website and CRAN.
+<img src="man/figures/figure-gfm/unnamed-chunk-3-1.png" width="100%" />
+-->
+
 ``` r
 # set seed --------------------------------------------------------------------
 set.seed(333)
 
 # load library ----------------------------------------------------------------
 library(sprtt)
 
+# t-TEST ----------------------------------------------------------------------
 # one sample: numeric input ---------------------------------------------------
 treatment_group <- rnorm(20, mean = 0, sd = 1)
 results <- seq_ttest(treatment_group, mu = 1, d = 0.8)
@@ -99,93 +106,42 @@ results@likelihood_ratio
 results["likelihood_ratio"]
 #> [1] 965.0728
 
-# two sample: numeric input----------------------------------------------------
-treatment_group <- stats::rnorm(20, mean = 0, sd = 1)
-control_group <- stats::rnorm(20, mean = 1, sd = 1)
-seq_ttest(treatment_group, control_group, d = 0.8)
-#> 
-#> *****  Sequential  Two Sample t-test *****
-#> 
-#> formula: treatment_group and  control_group
-#> test statistic:
-#>  log-likelihood ratio = 5.347, decision = accept H1
-#> SPRT thresholds:
-#>  lower log(B) = -2.944, upper log(A) = 2.944
-#> Log-Likelihood of the:
-#>  alternative hypothesis = -4.211
-#>  null hypothesis = -9.558
-#> alternative hypothesis: true difference in means is not equal to 0.
-#> specified effect size: Cohen's d = 0.8
-#> degrees of freedom: df = 38
-#> sample estimates:
-#> mean of x mean of y 
-#>  -0.05204   1.18768 
-#> *Note: to get access to the object of the results use the @ or [] instead of the $ operator.
-
-# two sample: formula input ---------------------------------------------------
-stress_level <- stats::rnorm(20, mean = 0, sd = 1)
-sex <- as.factor(c(rep(1, 10), rep(2, 10)))
-seq_ttest(stress_level ~ sex, d = 0.8)
-#> 
-#> *****  Sequential  Two Sample t-test *****
-#> 
-#> formula: stress_level ~ sex
-#> test statistic:
-#>  log-likelihood ratio = -1.455, decision = continue sampling
-#> SPRT thresholds:
-#>  lower log(B) = -2.944, upper log(A) = 2.944
-#> Log-Likelihood of the:
-#>  alternative hypothesis = -1.233
-#>  null hypothesis = 0.222
-#> alternative hypothesis: true difference in means is not equal to 0.
-#> specified effect size: Cohen's d = 0.8
-#> degrees of freedom: df = 18
-#> sample estimates:
-#> mean of x mean of y 
-#>  -0.23286  -0.08217 
-#> *Note: to get access to the object of the results use the @ or [] instead of the $ operator.
-
-# NA in the data --------------------------------------------------------------
-stress_level <- c(NA, stats::rnorm(20, mean = 0, sd = 2), NA)
-sex <- as.factor(c(rep(1, 11), rep(2, 11)))
-seq_ttest(stress_level ~ sex, d = 0.8, na.rm = TRUE)
+# ANOVA -----------------------------------------------------------------------
+# simulate data ---------------------------------------------------------------
+set.seed(333)
+data <- sprtt::draw_sample_normal(k_groups = 3,
+                                  f = 0.25,
+                                  sd = c(1, 1, 1),
+                                  max_n = 25)
+
+# calculate sequential ANOVA --------------------------------------------------
+results <- sprtt::seq_anova(y ~ x, f = 0.25, data = data, plot = TRUE)
+# test decision
+results@decision
+#> [1] "continue sampling"
+# test results
+results
 #> 
-#> *****  Sequential  Two Sample t-test *****
+#> *****  Sequential ANOVA *****
 #> 
-#> formula: stress_level ~ sex
+#> formula: y ~ x
 #> test statistic:
-#>  log-likelihood ratio = -0.359, decision = continue sampling
+#>  log-likelihood ratio = 2.892, decision = continue sampling
 #> SPRT thresholds:
 #>  lower log(B) = -2.944, upper log(A) = 2.944
 #> Log-Likelihood of the:
-#>  alternative hypothesis = -1.923
-#>  null hypothesis = -1.564
+#>  alternative hypothesis = -2.715
+#>  null hypothesis = -5.607
 #> alternative hypothesis: true difference in means is not equal to 0.
-#> specified effect size: Cohen's d = 0.8
-#> degrees of freedom: df = 18
-#> sample estimates:
-#> mean of x mean of y 
-#>  -0.40818   0.42068 
+#> specified effect size: Cohen's f = 0.25
+#> empirical Cohen's f = 0.4045074, 95% CI[0.129478, 0.6171581]
+#> Cohen's f adjusted = 0.355
+#> degrees of freedom: df1 = 2, df2 = 72
+#> SS effect = 10.74731, SS residual = 65.68208, SS total = 76.42939
 #> *Note: to get access to the object of the results use the @ or [] instead of the $ operator.
 
-# work with dataset (data are in the package included) ------------------------
-seq_ttest(monthly_income ~ sex, data = df_income, d = 0.8)
-#> 
-#> *****  Sequential  Two Sample t-test *****
-#> 
-#> formula: monthly_income ~ sex
-#> test statistic:
-#>  log-likelihood ratio = -9.514, decision = accept H0
-#> SPRT thresholds:
-#>  lower log(B) = -2.944, upper log(A) = 2.944
-#> Log-Likelihood of the:
-#>  alternative hypothesis = -8.093
-#>  null hypothesis = 1.421
-#> alternative hypothesis: true difference in means is not equal to 0.
-#> specified effect size: Cohen's d = 0.8
-#> degrees of freedom: df = 118
-#> sample estimates:
-#> mean of x mean of y 
-#>  3072.086  3080.715 
-#> *Note: to get access to the object of the results use the @ or [] instead of the $ operator.
+# plot results -----------------------------------------------------------------
+sprtt::plot_anova(results)
 ```
+
+<img src="man/figures/figure-gfm/unnamed-chunk-3-1.png" width="100%" />

cran-comments.md

@@ -1,54 +1,26 @@
 ## Test environments
-* local R installation (on windows), R 4.1.0
-* ubuntu-16.04 (on GitHub Actions), R 4.0.0
-* ubuntu-20.04 (on GitHub Actions)
-* macOS-latest (on GitHub Actions)
-* windows-latest (on GitHub Actions)
-* R-hub
-- Windows Server 2008 R2 SP1, R-devel, 32/64 bit
-- Ubuntu Linux 20.04.1 LTS, R-release, GCC
-- Fedora Linux, R-devel, clang, gfortran
-* win builder
-- using R version 4.1.0 (2021-05-18), using platform: x86_64-w64-mingw32 (64-bit)
-- using R Under development (unstable) (2021-07-25 r80663), using platform: x86_64-w64-mingw32 (64-bit)
+* GitHub Action
+macos-latest (release)
+windows-latest (release)
+ubuntu-latest (devel)
+ubuntu-latest (release)
+ubuntu-latest (oldrel-1)
 
+* macOS builder
+Build system: r-release-macosx-arm64|4.3.0|macosx|macOS 13.3.1 (22E261)|Mac mini|Apple M1||en_US.UTF-8|macOS 11.3|clang-1403.0.22.14.1|GNU Fortran (GCC) 12.2.0 
+* win-builder
 
 ## R CMD check results
-New submission
-==> This is my first submission
+── R CMD check results ────────────────── sprtt 0.2.0 ────
+Duration: 2m 28.5s
 
-Possibly mis-spelled words in DESCRIPTION:
-  Erdfelder (31:34)
-  Hajnal (25:5)
-  Rushton (24:49)
-  SPRT (22:54, 25:33, 31:5)
-  Schnuerch (31:22)
-==> spelling is correct
+0 errors ✔ | 0 warnings ✔ | 0 notes ✔
 
-Found the following (possibly) invalid DOIs:
-  DOI: 10.2307/2332385
-    From: DESCRIPTION
-    Status: Forbidden
-    Message: 403
-  DOI: 10.2307/2333131
-    From: DESCRIPTION
-    Status: Forbidden
-    Message: 403
-  DOI: 10.2307/2334026
-    From: DESCRIPTION
-    Status: Forbidden
-    Message: 403
+R CMD check succeeded
 
-==> DOIs are correct!
+## Reverse Dependencies
+0 reverse dependencies
 
-0 errors √ | 0 warnings √ | 1 note x
-
-## last CRAN feedback
-Please add () behind all function names in the description texts (DESCRIPTION file). e.g: 'seq_ttest' --> seq_ttest()
-==> DONE
-
-Please write references in the description of the DESCRIPTION file in the form authors (year) <doi:...> 
-==> DONE
-
-Please add \value to .Rd files regarding exported methods and explain the functions results in the documentation. 
-==> DONE
+## Change of licence from GPL to AGPL
+all authors of the package accepted the change
+(see open issue: https://github.com/MeikeSteinhilber/sprtt/issues/33)

inst/examples/draw_sample_mixture.R

@@ -10,7 +10,7 @@ data
 data <- sprtt::draw_sample_mixture(
   k_groups = 4,
   f = 1.2, # very large effect size
-  max_n = 2,
+  max_n = 4,
   counter_n = 1000, # increase of counter is necessary
   verbose = TRUE # prints more information to the console
 )