Merge branch 'main' into desc-main-update-to-latest-easystats-1711931742

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: effectsize
 Title: Indices of Effect Size
-Version: 0.8.6.6
+Version: 0.8.7.1
 Authors@R: 
     c(person(given = "Mattan S.",
              family = "Ben-Shachar",
@@ -105,7 +105,7 @@ VignetteBuilder:
 Encoding: UTF-8
 Language: en-US
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3.9000
+RoxygenNote: 7.3.1
 Config/testthat/edition: 3
 Config/testthat/parallel: true
 Config/Needs/website:

NEWS.md

@@ -1,25 +1,25 @@
-# effectsize 0.8.7.xxx
+# effectsize 0.8.7.x
+
+## Bug fixes
+
+- `hedges_g()`, `vd_a()`, `wmw_odds()`, and `cliffs_delta()` no longer require `{effectsize}` to be loaded to work ( #636 ).
+
+# effectsize 0.8.7
 
 - This release changes the licensing model of `{effectsize}` to an MIT license.
 
 ## New features
 
-- `cohens_d()` and `glass_delta()` gain an `adjust` argument for applying Hedges' small-sample bias correction (`hedges_g()` is now an alias for `cohens_d(adjust = TRUE)`).
-
+- `cohens_d()` and `glass_delta()` gain an `adjust` argument for applying Hedges' small-sample bias correction (`hedges_g()` is now an alias for `cohens_d(adjust = TRUE)`).  
 - `repeated_measures_d()` to compute standardized mean differences (SMD) for repeated measures data.
-  - Also supported in `effectsize(<t.test(paired = TRUE)>)`
+  - Also supported in `effectsize(<t.test(paired = TRUE)>)`  
+- New function: `interpret_fei()`
 
 ## Bug fixes
 
 - Minor stability fix to ncp-based CI methods ( #628 )
 - `nnt()` now properly accepts the `y` argument.
 
-# effectsize 0.8.7
-
-## New features
-
-- New function: `interpret_fei()`
-
 # effectsize 0.8.6
 
 This is a minor update to bring `effectsize` in-line with the formula methods 

R/cohens_d.R

@@ -160,7 +160,7 @@ hedges_g <- function(x, y = NULL, data = NULL,
                      ci = 0.95, alternative = "two.sided",
                      verbose = TRUE, ...) {
   cl <- match.call()
-  cl[[1]] <- quote(cohens_d)
+  cl[[1]] <- quote(effectsize::cohens_d)
   cl$adjust <- TRUE
   eval.parent(cl)
 }

R/common_language.R

@@ -340,7 +340,7 @@ vd_a <- function(x, y = NULL, data = NULL,
                  ci = 0.95, alternative = "two.sided",
                  verbose = TRUE, ...) {
   cl <- match.call()
-  cl[[1]] <- quote(p_superiority)
+  cl[[1]] <- quote(effectsize::p_superiority)
   cl$parametric <- FALSE
   eval.parent(cl)
 }
@@ -353,7 +353,7 @@ wmw_odds <- function(x, y = NULL, data = NULL,
                      ci = 0.95, alternative = "two.sided",
                      verbose = TRUE, ...) {
   cl <- match.call()
-  cl[[1]] <- quote(rank_biserial)
+  cl[[1]] <- quote(effectsize::rank_biserial)
   out <- eval.parent(cl)
 
   rb_to_wmw_odds(out)
@@ -362,6 +362,7 @@ wmw_odds <- function(x, y = NULL, data = NULL,
 
 
 
+
 # Utils -------------------------------------------------------------------
 
 #' @keywords internal

R/rank_diff.R

@@ -220,7 +220,7 @@ cliffs_delta <- function(x, y = NULL, data = NULL,
     insight::format_error("This effect size is only applicable for two independent samples.")
   }
 
-  cl[[1]] <- quote(rank_biserial)
+  cl[[1]] <- quote(effectsize::rank_biserial)
   cl$x <- x
   cl$y <- y
   eval.parent(cl)

R/utils_validate_input_data.R

@@ -12,7 +12,7 @@
     if (length(x) != 3L) {
       insight::format_error(
         "Formula must have one of the following forms:",
-        "          y ~ group   (independant samples)",
+        "          y ~ group   (independent samples)",
         "          y ~ 1       (one sample)",
         "  Pair(x,y) ~ 1       (paired samples)"
       )

cran-comments.md

@@ -6,7 +6,7 @@
 
 ## Test environments
 
-* local installation: R 4.3.1 on Windows
+* local installation: R 4.3.2 on Windows
 * GitHub Actions
     - Windows:        release
     - macOS:          release

inst/WORDLIST

@@ -49,7 +49,6 @@ Falk
 Faraggi
 Fei
 Fo
-Fum
 Funder
 GFI
 Gelman
@@ -82,8 +81,6 @@ Kiesser
 Koo
 Kruschke
 LMM
-Labelled
-labelled
 Lajeunesse
 Lakens
 Landis
@@ -126,6 +123,7 @@ Penfield
 PloS
 Psychometrika
 Psychonomic
+Pustejovsky
 RFI
 RMR
 RMSEA
@@ -137,17 +135,21 @@ Ringle
 Rosenthal
 Rothstein
 Rouder
+Rouder's
 Routledge
 Ruscio
 SDs
 SEM
+SMD
 SRMR
 Sarstedt
 Sawilowsky
 Schumacker
 Schweder
 Shachar
+Shadish
 Shmekels
+Speckman
 Steiger
 Szodorai
 Szumilas
@@ -172,6 +174,7 @@ anova
 arXiv
 arcsin
 biserial
+blogspot
 bmwiernik
 brglm
 brms
@@ -189,21 +192,24 @@ doi
 dynamicfit
 easystats
 effectSize
+effectsize’
 et
 fixest
 frac
 friedman
 ggstatsplot
-github
 glmmadmb
 gtsummary
 homoscedasticity
+http
 https
+independant
 infty
 intraclass
-io
+jeffrouder
 joss
 kruskal
+labelled
 lifecycle
 lm
 mattansb
@@ -233,7 +239,6 @@ rescale
 rmANOVA
 sd
 semipartial
-shinyapps
 statswiki
 strengejacke
 th

vignettes/statistical_power.Rmd

@@ -79,7 +79,7 @@ So this is where we focus in this vignette, and pay special attention to the eas
 The following section walks through a simple applied example to ensure 1) the concepts surrounding and involved in power are clear and digestible, and 2) that the role and value of the `effectsize` package are likewise clear and digestible.
 Understanding both of these realities will allow for more complex extensions and applications to a wide array of research problems and questions. 
 
-# Example: Comparing Means of Independant Samples
+# Example: Comparing Means of Independent Samples
 
 In addition to relying on the _easystats_ `effectsize` package for effect size calculation, we will also leverage the simple, but excellent `pwr` package for the following implementation of power analysis [@champley2017]. 
 
@@ -164,7 +164,7 @@ Given the prevalence of calculating effect sizes for different applications and
 There are many conversions available in the package. 
 Take a look [here](https://easystats.github.io/effectsize/reference/index.html#effect-size-conversion).
 
-This can also be dne directly by the user using the `t_to_d()` function:
+This can also be done directly by the user using the `t_to_d()` function:
 
 ```{r}
 t_to_d(