Fix describe error

describe will no pull the correct p-value for minimal effects tests from TOSTt objects (originally was pulling max rather than min)
Lakens · Apr 16, 2024 · b7b9539 · b7b9539
1 parent 67ab29f
commit b7b9539
Show file tree

Hide file tree

Showing 5 changed files with 16 additions and 8 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -20,6 +20,7 @@ build/js
 NUL
 ^CRAN-RELEASE$
 ^cran-comments\.md$
+^CODE_OF_CONDUCT\.md$
 ^CRAN-SUBMISSION$
 .covrignore
 ^papers

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,5 +1,5 @@
 Package: TOSTER
-Version: 0.8.1
+Version: 0.8.2
 Title: Two One-Sided Tests (TOST) Equivalence Testing
 Description: Two one-sided tests (TOST) procedure to test equivalence for t-tests, correlations, differences between proportions, and meta-analyses, including power analysis for t-tests and correlations. Allows you to specify equivalence bounds in raw scale units or in terms of effect sizes. See: Lakens (2017) <doi:10.1177/1948550617697177>.
 Authors@R: c(

diff --git a/NEWS.md b/NEWS.md
@@ -3,6 +3,10 @@ NEWS
 
 **TOSTER R package and jamovi module**
 
+# TOSTER v0.8.2
+
+- Fixed error with `describe` method for minimal effects test for `TOSTt` objects.
+
 # TOSTER v0.8.1
 
 - Small correction to the displayed equation for Cohen's ds standard error. Thank you to Matthew B Jané for finding this error.

diff --git a/R/htest.R b/R/htest.R
@@ -29,11 +29,17 @@ as_htest = function(TOST) {
     stop("Class cannot be converted to htest with this function.")
   }
 
-
+  alt_text = ifelse(grepl("equ", TOST$hypothesis,
+                          ignore.case = TRUE),
+                    "equivalence",
+                    "minimal.effect")
   # get row
 
   TOSTp = TOST$TOST[2:3, ]
-  TOSTp = TOSTp[which.max(TOSTp$p.value), ]
+  TOSTp = switch(alt_text,
+                 "equivalence" = TOSTp[which.max(TOSTp$p.value), ],
+                 "minimal.effect" = TOSTp[which.min(TOSTp$p.value), ]
+  )
 
   # assign
   statistic <- switch(class(TOST),
@@ -91,10 +97,7 @@ as_htest = function(TOST) {
   alt_bound <-
     ifelse(grepl("Lower", which_row), "lower", "upper")
 
-  alt_text = ifelse(grepl("equ", TOST$hypothesis,
-                          ignore.case = TRUE),
-                    "equivalence",
-                    "minimal.effect")
+
 
 
     conf.int <- c(TOST$effsize$lower.ci[1],

diff --git a/vignettes/robustTOST.Rmd b/vignettes/robustTOST.Rmd
@@ -322,7 +322,7 @@ ses_calc(formula = extra ~ group,
 boot_ses_calc(formula = extra ~ group,
          data = sleep,
          paired = TRUE,
-         R = 1990,
+         R = 199,
          boot_ci = "perc", # recommend percentile bootstrap for paired SES
          ses = "r") 
 ```