Tables of Effect Size for Z Score Tests of Differences between Proportions and between Correlation Coefficients

Abstract

Tables are given for the rapid estimation of h, the effect size index for the difference between independent proportions, and of q, the effect size index for the difference between independent correlation coefficients. The tables are accurate to three decimal places and may be used conveniently in conjunction with tables and charts of power and sample size. Formulas for power and sample size estimation are also presented.

One session of TTM-tailored condom use feedback: a pilot study among at-risk women in the Bronx

“…Based on previous research showing a linear relationship between baseline stage and consistent condom use one year later (Evers et al, 1998), we assumed a monotonically increasing linear pattern of outcomes across stages. A linear test of trend on the arcsine corrected proportions (Rossi, 1985), corrected for unequal sample sizes, provided some support for this assumption ( p =.074).…”

Baseline Stage, Severity, and Effort Effects Differentiate Stable Smokers from Maintainers and Relapsers

“…There was a significant difference in the control group for age, with the Maintainers having significantly more adults over the age of 50 years (31.26%) than either Relapsers (21.65%, h =0.219) or the Stable Smokers (23.87%, h = 0.166). The effect size indicator Cohen’s h represents the standardized difference between proportions (Cohen, 1988; Rossi, 1985). Its interpretation is exactly analogous to that of Cohen’s d ( h = 0.20 = small effect size; h = 0.50 = medium effect size; h = 0.80 = large effect size).…”

Prior History of Traumatic Brain Injury Among Persons in the Traumatic Brain Injury Model Systems National Database

“…Cohen’s d , calculated using a weighted pooled SD of both groups, 22,23 was used to calculate the effect size for mean differences, whereas Cohen’s h (based on the arcsine transformation of proportions 22,24 ) was used for differences between proportions. Although multiple methods for determining standardized effect sizes exist, Cohen’s d is the standard method for examining mean differences.…”