effsize.range.plot: Plotting Effect Size (Cliff's Delta) with Confidence Interval

In lindayi/distcomp: Plotting Distribution Differences

Description

Plotting Effect Size (Cliff's Delta) with Confidence Interval, and calculate Cliff's Delta effect size.

Usage

effsize.range.plot(dist1, dist2, threshold = c(0.147, 0.330, 0.474), transparency = 150, col = viridis(4))

Arguments

dist1	the first distribution for comparison
dist2	the second distribution for comparison
threshold	A list of 3 doubles that represents the threshold for negligible, small, medium, and large effect size.
transparency	an integer range between 0-255 that represents the transparency of the colors
col	a vector with four colors for the four effect size segments (negligible, small, medium, large). By default using the viridis color palettes which is colorblind-friendly.

Value

A list of class effsize. See cliff.delta for details.

Author(s)

Maintainer: Dayi Lin http://lindayi.me

References

Norman Cliff (1996). Ordinal methods for behavioral data analysis. Routledge.

Romano, J., Kromrey, J. D., Coraggio, J., Skowronek, J., & Devine, L. (2006, October). Exploring methods for evaluating group differences on the NSSE and other surveys: Are the t-test and Cohen<e2><80><99>sd indices the most appropriate choices. In annual meeting of the Southern Association for Institutional Research.

Please cite the following paper when using this function for visualizing Cliff's Delta effect size:

Lin, D., Bezemer, C. P., & Hassan, A. E. (2018). An empirical study of early access games on the Steam platform. Empirical Software Engineering, 23(2), 771-799.

Examples

temp.dist1 = rnorm(100,1,2)
temp.dist2 = rnorm(100,-1,2)
effsize.range.plot(temp.dist1, temp.dist2)

lindayi/distcomp documentation built on May 20, 2019, 11:59 a.m.