PMCMRplus (version 1.9.10)

power.dunnett.test: Power Calculations for Balanced Dunnett's Many-to-One Comparison Test

Description

Compute average per-pair power of Dunnetts's multiple comparison test with one control.

Usage

power.dunnett.test(n, groups, delta, within.var, sig.level = 0.05)

Value

Object of class ‘power.htest’, a list of the arguments (including the computed one) augmented with method and note elements.

Arguments

n

Number of observations (per group)

groups

Number of groups (including control)

delta

true difference in means

within.var

Within group variance

sig.level

Significance level (Type I error probability)

Details

The function has implemented the following Eq. to estimate average per-pair power for two-sided tests:

$$1-\beta =1-t(T_{\alpha \rho v},v,\mathrm{ncp})+t(-T_{\alpha \rho v},v,\mathrm{ncp}),$$

with $T_{\alpha \rho v}$ the two-sided $\alpha$ quantile of the multivariate t-distribution, with $v=k(n-1)$ degree of freedom, $k$ the number of groups and correlation matrix ${\rho }_{ij}=0.5(i\ne j)$.

The non-centrality parameter for the non-central student t-distribution is

$$\mathrm{ncp}=|\mathrm{\Delta }|/\sqrt{s_{\mathrm{in}}^{2}2/n}.$$

See Also

TDist qmvt powerMCTests

Examples

set.seed(113)
power.dunnett.test(n = 9, groups = 5, delta = 30,
 within.var = 333.7)

## compare with t-test, bonferroni corrected
power.t.test(n = 9, delta = 30, sd = sqrt(333.7),
sig.level = 0.05 / 4)

if (FALSE) {
## asymptotic Monte-Carlo power analysis
 set.seed(113)
 powerMCTests(mu = c(rep(0,4), 30), n = 9,
 parms = list(mean = 0, sd = sqrt(333.7)),
 test = "dunnettTest", alternative = "two.sided")
}