Researchers are often interested determining if there is a negligible relationship among variables. For example, is the correlation between anxiety and well-being negligible or is the difference in the means males and females on IQ negligible. There are a collection of tests for evaluating the presence of a negligible association that within the framework of 'negligible effect testing' or 'equivalence testing' (the latter term is older and often does not apply to modern types of analyses, such as negligible correlation).

**The negligible package can be installed via CRAN or github (the github version will generally be the most up-to-date, but also most prone to bugs)**

*Install the Package from CRAN:*

install.packages("negligible")

*Install the Package from github:*

1) Install the devtools package (if necessary). In R, paste the following into the console:

install.packages('devtools')

2) Load the devtools package and install from the Github source code:

library('devtools')

install_github('cribbie/negligible')

3) Load the newly installed package by calling

library(negligible)

**Examples of functions within the negligible package:**

*neg.cat:* Testing for the presence of a negligible association between two categorical variables. What is negligible is quantified in terms of Cramer's V.

*neg.cfi*: This function performs one of six equivalence tests for the CFI fit index. These tests allow a researcher to evaluate if model fit is negligibly different from CFI = 1. These inferential results can supplement the descriptive results for model fit.

*neg.cor*: A negligible association test based on Pearson's *r* and resampling.

*neg.esm*: Evaluates whether substantial mediation (negligible direct effect) is present via negligible effect (equivalence) testing and David Kenny's method for assessing full mediation.

*neg.indvars*: This function evaluates whether the difference in the population variances of J independent groups can be considered negligible (i.e., the population variances can be considered equivalent).

*neg.intcont*: This function evaluates whether the interaction between two continuous predictor variables is negligible.

*neg.paired*: This function evaluates whether the difference in the means of 2 dependent populations can be considered negligible (i.e., the population means can be considered equivalent).

*neg.reg*: This function evaluates whether a certain predictor variable in a multiple regression model can be considered statistically and practically negligible.

*neg.rmsea*: This function performs one of four negligible effects tests based on the RMSEA model fit index. These tests allow a researcher to evaluate if model fit is negligibly different from RMSEA = 0. These inferential results can supplement the descriptive results for model fit.

*neg.twocors*: This function evaluates whether the difference between two correlation coefficients can be considered statistically and practically negligible. The correlations can be independent (e.g., same variables, different groups) or dependent [e.g., r(x,y) vs r(x,z)].

*neg.twoindmeans*: This function allows researchers to test whether the difference between the means of two independent populations is negligible.

*negligible* Package Vignette

Coming Soon!