Skip to main content
. Author manuscript; available in PMC: 2023 May 1.
Published in final edited form as: Aggress Behav. 2021 Oct 5;48(3):279–289. doi: 10.1002/ab.21996

Table 2.

Power estimates for two-way interaction effect between predictors of various interrelations

Two-tailed p < .05
N r = .05, d = .10 r = .10, d = .20 r = .20, d = .41
r ab 0 .10 .30 .50 0 .10 .30 .50 0 .10 .30 .50
50 6% 4% 5% 5% 9% 9% 8% 7% 20% 25% 24% 17%
100 5% 6% 6% 6% 16% 14% 14% 14% 45% 47% 48% 43%
150 8% 9% 7% 8% 21% 20% 22% 17% 60% 62% 63% 54%
200 10% 12% 10% 9% 30% 26% 24% 24% 79% 78% 76% 71%
250 11% 10% 10% 11% 33% 31% 31% 26% 87% 85% 84% 82%
300 12% 14% 14% 12% 40% 37% 35% 31% 92% 93% 91% 86%
350 14% 13% 12% 13% 41% 40% 38% 35% 94% 95% 94% 92%
400 16% 14% 16% 14% 49% 50% 46% 42% 97% 98% 96% 93%
450 17% 20% 17% 15% 49% 52% 55% 43% 98% 98% 98% 96%
500 19% 19% 21% 16% 56% 62% 54% 52% 99% 100% 99% 98%
750 24% 28% 24% 24% 73% 75% 69% 65% 100% 100% 100% 100%
1,000 30% 32% 31% 28% 86% 84% 86% 78% 100% 100% 100% 100%
2,500 69% 66% 65% 61% 100% 100% 100% 100% 100% 100% 100% 100%
5,000 92% 92% 92% 87% 100% 100% 100% 100% 100% 100% 100% 100%
7,500 98% 99% 98% 95% 100% 100% 100% 100% 100% 100% 100% 100%
10,000 100% 100% 100% 99% 100% 100% 100% 100% 100% 100% 100% 100%
One-tailed p < .05
N r = .05, d = .10 r = .10, d = .20 r = .20, d = .41
r ab 0 .10 .30 .50 0 .10 .30 .50 0 .10 .30 .50
50 10% 9% 9% 9% 16% 17% 14% 13% 31% 37% 35% 31%
100 13% 12% 11% 11% 25% 24% 22% 21% 58% 59% 61% 55%
150 15% 13% 16% 13% 31% 31% 30% 25% 71% 74% 73% 69%
200 18% 16% 16% 15% 39% 39% 35% 32% 86% 87% 86% 81%
250 20% 18% 17% 17% 46% 45% 41% 37% 92% 91% 92% 89%
300 19% 22% 20% 17% 49% 49% 47% 41% 96% 96% 95% 92%
350 24% 20% 21% 19% 53% 57% 54% 47% 97% 98% 96% 96%
400 25% 26% 24% 20% 61% 62% 56% 53% 98% 99% 99% 97%
450 25% 28% 26% 23% 60% 65% 66% 53% 99% 99% 99% 98%
500 28% 26% 28% 23% 67% 72% 64% 62% 100% 100% 100% 99%
750 35% 38% 34% 32% 84% 83% 80% 76% 100% 100% 100% 100%
1,000 40% 46% 42% 40% 92% 91% 91% 86% 100% 100% 100% 100%
2,500 78% 77% 74% 71% 100% 100% 100% 100% 100% 100% 100% 100%
5,000 96% 96% 95% 92% 100% 100% 100% 100% 100% 100% 100% 100%
7,500 99% 100% 99% 98% 100% 100% 100% 100% 100% 100% 100% 100%
10,000 100% 100% 100% 100% 100% 100% 100% 100% 100% 100% 100% 100%

Note: r and d values represent the effect size of the interaction term and these can be interpreted as partial rs; rab represents the correlation between the two predictor variables; for the continuous predictors and the dependent variable, we assumed α = .85; in this table, we present power estimates for analyses with two continuous predictors (both α = .85), given that these results were very highly overlapping with analyses with one continuous predictor (α = .85) and one dichotomous predictor (α = 1).