psychmeta (version 2.3.4)

correct_glass_bias: Correct for small-sample bias in Glass' \(\Delta\) values

Description

Correct for small-sample bias in Glass' \(\Delta\) values

Usage

correct_glass_bias(delta, nc, ne, use_pooled_sd = rep(FALSE,
  length(delta)))

Arguments

delta

Vector of Glass' \(\Delta\) values.

nc

Vector of control-group sample sizes.

ne

Vector of experimental-group sample sizes.

use_pooled_sd

Logical vector determining whether the pooled standard deviation was used (TRUE) or not (FALSE; default).

Value

Vector of d values corrected for small-sample bias.

Details

The bias correction is estimated as:

$$\Delta_{c}=\Delta_{obs}\frac{\Gamma\left(\frac{n_{control}-1}{2}\right)}{\Gamma\left(\frac{n_{control}-1}{2}\right)\Gamma\left(\frac{n_{control}-2}{2}\right)}$$

where \(\Delta\) is the observed effect size, \(\Delta_{c}\) is the corrected estimate of \(\Delta\), and \(n_{control}\) is the control-group sample size.

References

Hedges, L. V. (1981). Distribution theory for Glass<U+2019>s estimator of effect size and related estimators. Journal of Educational Statistics, 6(2), 107<U+2013>128. https://doi.org/10.2307/1164588

Examples

# NOT RUN {
correct_glass_bias(delta = .3, nc = 30, ne = 30)
# }