easystats/effectsizePublic

NotificationsYou must be signed in to change notification settings
Fork24
Star349

🐉 Compute and work with indices of effect size and standardized parameters

License

Unknown, MIT licenses found

Licenses found

349 stars 24 forks Branches Tags Activity

Star

Notifications

You must be signed in to change notification settings

Branches Tags

Folders and files

Name		Name	Last commit message	Last commit date
Latest commit History 1,919 Commits
.github		.github
.vscode		.vscode
R		R
WIP		WIP
data-raw		data-raw
data		data
dev		dev
inst		inst
man		man
papers		papers
pkgdown		pkgdown
tests		tests
vignettes		vignettes
.Rbuildignore		.Rbuildignore
.gitattributes		.gitattributes
.gitignore		.gitignore
.lintr		.lintr
DESCRIPTION		DESCRIPTION
LICENSE		LICENSE
LICENSE.md		LICENSE.md
NAMESPACE		NAMESPACE
NEWS.md		NEWS.md
README.Rmd		README.Rmd
README.md		README.md
air.toml		air.toml
cran-comments.md		cran-comments.md
effectsize.Rproj		effectsize.Rproj
effectsize.code-workspace		effectsize.code-workspace

Repository files navigation

effectsize: Indices of Effect Size

Significant is just not enough!

The goal of this package is to provide utilities to work with indices ofeffect size and standardized parameters, allowing computation andconversion of indices such as Cohen’sd,r, odds-ratios, etc.

Installation

Run the following to install the stable release ofeffectsize fromCRAN:

install.packages("effectsize")

Or you can install the latest development version fromR-universe:

install.packages("effectsize",repos="https://easystats.r-universe.dev/")

Documentation

Click on the buttons above to access the packagedocumentation and theeasystats blog, andcheck-out these vignettes:

Effect Sizes
Effect Sizes Conversion
Plotting Functions for the ‘effectsize’Package
Automated Interpretation of Indices of EffectSize

Features

This package is focused on indices of effect size. Check out the packagewebsite fora full list of features and functions provided byeffectsize.

library(effectsize)options(es.use_symbols=TRUE)# get nice symbols when printing! (On Windows, requires R >= 4.2.0)

Tip:
Instead oflibrary(effectsize), uselibrary(easystats).Thiswill make all features of the easystats-ecosystem available.
To stay updated, useeasystats::install_latest().

Effect Size Computation

The package provides functions to compute indices of effect size.

Standardized Differences (Cohen’sd, Hedges’g, Glass’delta)

cohens_d(mpg~am,data=mtcars)## Cohen's d |         95% CI## --------------------------## -1.48     | [-2.27, -0.67]#### - Estimated using pooled SD.hedges_g(mpg~am,data=mtcars)## Hedges' g |         95% CI## --------------------------## -1.44     | [-2.21, -0.65]#### - Estimated using pooled SD.glass_delta(mpg~am,data=mtcars)## Glass' Δ (adj.) |         95% CI## --------------------------------## -1.10           | [-1.80, -0.37]

effectsize also provides effect sizes forpaired standardizeddifferences,rank tests,common language effect sizes and more…

Contingency Tables

# Dependencephi(mtcars$am,mtcars$vs)## ϕ (adj.) |       95% CI## -----------------------## 0.00     | [0.00, 1.00]#### - One-sided CIs: upper bound fixed at [1.00].cramers_v(mtcars$am,mtcars$cyl)## Cramer's V (adj.) |       95% CI## --------------------------------## 0.46              | [0.00, 1.00]#### - One-sided CIs: upper bound fixed at [1.00].# Goodness-of-fitfei(table(mtcars$cyl),p= c(0.1,0.3,0.6))## פ‎    |       95% CI## -------------------## 0.27 | [0.17, 1.00]#### - Adjusted for uniform expected probabilities.## - One-sided CIs: upper bound fixed at [1.00].

ANOVAs (Eta², Omega², …)

model<- aov(mpg~factor(gear),data=mtcars)eta_squared(model)## # Effect Size for ANOVA#### Parameter    |   η² |       95% CI## ----------------------------------## factor(gear) | 0.43 | [0.18, 1.00]#### - One-sided CIs: upper bound fixed at [1.00].omega_squared(model)## # Effect Size for ANOVA#### Parameter    |   ω² |       95% CI## ----------------------------------## factor(gear) | 0.38 | [0.14, 1.00]#### - One-sided CIs: upper bound fixed at [1.00].epsilon_squared(model)## # Effect Size for ANOVA#### Parameter    |   ε² |       95% CI## ----------------------------------## factor(gear) | 0.39 | [0.14, 1.00]#### - One-sided CIs: upper bound fixed at [1.00].

And more…

Effect Size Conversion

The package also provides ways of converting between different effectsizes.

d_to_r(d=0.2)## [1] 0.0995oddsratio_to_riskratio(2.6,p0=0.4)## [1] 1.59

And for recovering effect sizes from test statistics.

F_to_d(15,df=1,df_error=60)## d    |       95% CI## -------------------## 1.00 | [0.46, 1.53]F_to_r(15,df=1,df_error=60)## r    |       95% CI## -------------------## 0.45 | [0.22, 0.61]F_to_eta2(15,df=1,df_error=60)## η² (partial) |       95% CI## ---------------------------## 0.20         | [0.07, 1.00]#### - One-sided CIs: upper bound fixed at [1.00].

Effect Size Interpretation

The package allows for an automated interpretation of different indices.

interpret_r(r=0.3)## [1] "large"## (Rules: funder2019)

Different sets of “rules of thumb” are implemented (guidelines aredetailedhere)and can be easily changed.

interpret_cohens_d(d=0.45,rules="cohen1988")## [1] "small"## (Rules: cohen1988)interpret_cohens_d(d=0.45,rules="gignac2016")## [1] "moderate"## (Rules: gignac2016)

Citation

In order to cite this package, please use the following citation:

Ben-Shachar M, Lüdecke D, Makowski D (2020). effectsize: Estimation ofEffect Size Indices and Standardized Parameters.Journal of OpenSource Software,5(56), 2815. doi: 10.21105/joss.02815

Corresponding BibTeX entry:

@Article{,  title = {{e}ffectsize: Estimation of Effect Size Indices and Standardized Parameters},  author = {Mattan S. Ben-Shachar and Daniel Lüdecke and Dominique Makowski},  year = {2020},  journal = {Journal of Open Source Software},  volume = {5},  number = {56},  pages = {2815},  publisher = {The Open Journal},  doi = {10.21105/joss.02815},  url = {https://doi.org/10.21105/joss.02815}}

Contributing and Support

If you have any questions regarding the the functionality of thepackage, you may either contact us via email or alsofile anissue. Anyone wishingto contribute to the package by adding functions, features, or inanother way, please followthisguideand ourcode ofconduct.