This is intended as the effect size version of an ANOVA. For effect_sd, the effect size is the standard deviation of some coefficients about their mean. For effect_rssm, it is the root sum of squared differences from the mean. For effect_rss, it is simply the square root of the sum of squared coefficients.

effect_sd(coef)

effect_rss(coef)

Arguments

coef The column numbers of the design matrix for the relevant coefficients.

Value

An object defining how to calculate an effect size.

Details

effect_rssm may be better suited to comparing effect sizes from designs with differing numbers of coefficients, such as differential exon usage.