From 557689575439c082e6e0f5f74ffaec60872f3ace Mon Sep 17 00:00:00 2001
From: Alboukadel Kassambara <alboukadel.kassambara@gmail.com>
Date: Sat, 13 Feb 2021 21:35:18 +0100
Subject: [PATCH] dunn_test doc updated #50

---
 NEWS.md          |  1 +
 R/dunn_test.R    | 21 ++++++++++++++-------
 man/dunn_test.Rd | 20 +++++++++++++-------
 3 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/NEWS.md b/NEWS.md
index 2664446..86d09d4 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -9,6 +9,7 @@
 
 ## Bug fixes
 
+- The `dunn_test()` documentation is updated to describe the discrepancy between the default behaviour of the `rstatix::dunn_test()` comapred to other packages (`dunn.test` and `jamovi`). The default of the rstatix::dunn_test() function is to perform a two-sided Dunn test like the well known commercial softwares, such as SPSS and GraphPad. This is not the case for some other R packages (dunn.test and jamovi), where the default is to perform one-sided test (#50). 
 - Now, the function `get_summary_stats()` handles the user defined probabilities for grouped data (#78)
 
 
diff --git a/R/dunn_test.R b/R/dunn_test.R
index 202a508..c407545 100644
--- a/R/dunn_test.R
+++ b/R/dunn_test.R
@@ -5,18 +5,25 @@ NULL
 #'@description Performs Dunn's test for pairwise multiple comparisons of the
 #'  ranked data. The mean rank of the different groups is compared. Used for
 #'  post-hoc test following Kruskal-Wallis test.
+#'
+#'  The default of the \code{rstatix::dunn_test()} function is to perform a
+#'  two-sided Dunn test like the well known commercial softwares, such as SPSS
+#'  and GraphPad. This is not the case for some other R packages
+#'  (\code{dunn.test} and \code{jamovi}), where the default is to perform
+#'  one-sided test. This discrepancy is documented at
+#'  \href{https://github.com/kassambara/rstatix/issues/50}{https://github.com/kassambara/rstatix/issues/50}.
+#'
 #'@inheritParams t_test
 #'@return return a data frame with some of the following columns: \itemize{
 #'  \item \code{.y.}: the y (outcome) variable used in the test. \item
 #'  \code{group1,group2}: the compared groups in the pairwise tests. \item
 #'  \code{n1,n2}: Sample counts. \item \code{estimate}: mean ranks difference.
-#'  \item \code{estimate1, estimate2}: show the mean rank values of
-#'  the two groups, respectively.
-#'  \item \code{statistic}: Test statistic (z-value) used to compute the
-#'  p-value. \item \code{p}: p-value. \item \code{p.adj}: the adjusted p-value.
-#'  \item \code{method}: the statistical test used to compare groups. \item
-#'  \code{p.signif, p.adj.signif}: the significance level of p-values and
-#'  adjusted p-values, respectively. }
+#'  \item \code{estimate1, estimate2}: show the mean rank values of the two
+#'  groups, respectively. \item \code{statistic}: Test statistic (z-value) used
+#'  to compute the p-value. \item \code{p}: p-value. \item \code{p.adj}: the
+#'  adjusted p-value. \item \code{method}: the statistical test used to compare
+#'  groups. \item \code{p.signif, p.adj.signif}: the significance level of
+#'  p-values and adjusted p-values, respectively. }
 #'
 #'  The \strong{returned object has an attribute called args}, which is a list
 #'  holding the test arguments.
diff --git a/man/dunn_test.Rd b/man/dunn_test.Rd
index a53c854..d739319 100644
--- a/man/dunn_test.Rd
+++ b/man/dunn_test.Rd
@@ -27,13 +27,12 @@ return a data frame with some of the following columns: \itemize{
  \item \code{.y.}: the y (outcome) variable used in the test. \item
  \code{group1,group2}: the compared groups in the pairwise tests. \item
  \code{n1,n2}: Sample counts. \item \code{estimate}: mean ranks difference.
- \item \code{estimate1, estimate2}: show the mean rank values of
- the two groups, respectively.
- \item \code{statistic}: Test statistic (z-value) used to compute the
- p-value. \item \code{p}: p-value. \item \code{p.adj}: the adjusted p-value.
- \item \code{method}: the statistical test used to compare groups. \item
- \code{p.signif, p.adj.signif}: the significance level of p-values and
- adjusted p-values, respectively. }
+ \item \code{estimate1, estimate2}: show the mean rank values of the two
+ groups, respectively. \item \code{statistic}: Test statistic (z-value) used
+ to compute the p-value. \item \code{p}: p-value. \item \code{p.adj}: the
+ adjusted p-value. \item \code{method}: the statistical test used to compare
+ groups. \item \code{p.signif, p.adj.signif}: the significance level of
+ p-values and adjusted p-values, respectively. }
 
  The \strong{returned object has an attribute called args}, which is a list
  holding the test arguments.
@@ -42,6 +41,13 @@ return a data frame with some of the following columns: \itemize{
 Performs Dunn's test for pairwise multiple comparisons of the
  ranked data. The mean rank of the different groups is compared. Used for
  post-hoc test following Kruskal-Wallis test.
+
+ The default of the \code{rstatix::dunn_test()} function is to perform a
+ two-sided Dunn test like the well known commercial softwares, such as SPSS
+ and GraphPad. This is not the case for some other R packages
+ (\code{dunn.test} and \code{jamovi}), where the default is to perform
+ one-sided test. This discrepancy is documented at
+ \href{https://github.com/kassambara/rstatix/issues/50}{https://github.com/kassambara/rstatix/issues/50}.
 }
 \details{
 DunnTest performs the post hoc pairwise multiple comparisons