samplesize.h: Sample size estimation in the differences between proportions

In rpsychi: Statistics for psychiatric research

Description

samplesize.h determines the sample size, when specified the effect size to be detected, desired statistical power, and significance level. samplesize.h always specifies two-sided test.

Usage

samplesize.h(delta, power = 0.8, sig.level = 0.05)

Arguments

delta	a numeric contains the effect size (Cohen's h) to be detected
power	a numeric contains the desired statistical power (default 0.80)
sig.level	a numeric contains the significance level (default 0.05)

Value

Return a numeric containing the appropriate sample size in each group.

Author(s)

Yasuyuki Okumura
Department of Social Psychiatry,
National Institute of Mental Health,
National Center of Neurology and Psychiatry
[e-mail]

References

Cohen J (1988). Statistical power analysis for the behavioral sciences (2nd ed). Hillsdale, NJ: Erlbaum.

See Also

ind.prop, ind.prop.second

Examples

##Cohen (1988) ex.6.7
samplesize.h(delta=.20, power=.90, sig.level=.01)

##Cohen (1988) ex.6.8
samplesize.h(delta=.2828, power=.95, sig.level=.05)

rpsychi documentation built on May 1, 2019, 10:10 p.m.