Merge pull request #391 from easystats/API

NEW: (partial) API

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: effectsize
 Title: Indices of Effect Size and Standardized Parameters
-Version: 0.5.0.2
+Version: 0.5.0.9
 Authors@R: 
     c(person(given = "Mattan S.",
              family = "Ben-Shachar",
@@ -53,9 +53,9 @@ Depends:
 Imports:
     bayestestR (>= 0.10.5),
     insight (>= 0.14.3),
-    parameters (>= 0.15.0),
+    parameters (>= 0.15.0.1),
     performance (>= 0.8.0),
-    datawizard (>= 0.2.0),
+    datawizard (>= 0.2.1.9001),
     stats,
     utils
 Suggests:
@@ -85,6 +85,9 @@ Suggests:
     spelling,
     testthat,
     tidymodels
+Remotes:
+    easystats/parameters,
+    easystats/datawizard
 VignetteBuilder: 
     knitr
 Encoding: UTF-8

NAMESPACE

@@ -40,19 +40,20 @@ S3method(rb_to_cles,numeric)
 S3method(standardize,Surv)
 S3method(standardize,bcplm)
 S3method(standardize,clm2)
-S3method(standardize,coxme)
-S3method(standardize,coxph)
 S3method(standardize,default)
 S3method(standardize,mediate)
-S3method(standardize,mlm)
 S3method(standardize,wbgee)
 S3method(standardize,wbm)
+S3method(standardize_info,default)
 S3method(standardize_parameters,bootstrap_model)
 S3method(standardize_parameters,bootstrap_parameters)
 S3method(standardize_parameters,default)
 S3method(standardize_parameters,mediate)
 S3method(standardize_parameters,model_fit)
 S3method(standardize_parameters,parameters_model)
+export(.es_aov_simple)
+export(.es_aov_strata)
+export(.es_aov_table)
 export(F_to_d)
 export(F_to_epsilon2)
 export(F_to_eta2)

NEWS.md

@@ -1,11 +1,12 @@
-# effectsize 0.5.0.1
+# effectsize 0.5.0.9
 
 ## Breaking Changes
 
 - `pearsons_c()` effect size column name changed to `Pearsons_c` for consistency. 
 
 ## New features
 
+- `eta_squared()` family now supports `afex::mixed()` models.
 - `cles()` for estimating common language effect sizes.
 - `rb_to_cles()` for converting rank-biserial correlation to Probability of superiority.
 
@@ -15,7 +16,9 @@
 
 ## Bug fixes
 
-- `eta_squared()`: fixed a bug that caused `afex_aov` models with more than 2 within-subject factros to return incorrect effect sizes for the lower level factors ( #389 ).
+- `standardize()` for multivariate models standardizes the (multivariate) response.
+- `standardize()` for models with offsets standardizes offset variables according to `include_response` and `two_sd` ( #396 ).
+- `eta_squared()`: fixed a bug that caused `afex_aov` models with more than 2 within-subject factors to return incorrect effect sizes for the lower level factors ( #389 ).
 
 # effectsize 0.5.0
 

R/docs_extra.R

@@ -141,3 +141,12 @@
 #' @rdname effectsize_CIs
 #' @name effectsize_CIs
 NULL
+
+
+#' `effectsize` API
+#'
+#' Read the [*Support functions for model extensions*](https://easystats.github.io/effectsize/articles/effectsize_API.html) vignette.
+#'
+#' @rdname effectsize_API
+#' @name effectsize_API
+NULL

R/effectsize.BFBayesFactor.R

@@ -55,7 +55,7 @@ effectsize.BFBayesFactor <- function(model, type = NULL, verbose = TRUE, test =
       mu <- 0
       D <- samps$delta
     } else {
-      mu <- as.numeric(gsub("Null, mu=", "", model@denominator@shortName))
+      mu <- model@numerator[[1]]@prior$mu
       D <- (samps$mu - mu) / sqrt(samps$sig2)
     }
 

R/effectsize.htest.R

@@ -115,7 +115,7 @@ effectsize.htest <- function(model, type = NULL, verbose = TRUE, ...) {
     return(out)
   } else if (grepl("One-way", model$method)) {
     # one way anove ----
-    if (approx <- grepl("not assuming", model$method, fixed = TRUE) && verbose) {
+    if ((approx <- grepl("not assuming", model$method, fixed = TRUE)) && verbose) {
       warning("`var.equal = FALSE` - effect size is an approximation.", call. = FALSE)
     }