This function performs the sample size calculation for a linear mixed model
with random slope.
Usage
edland.linear.power(n = NULL, delta = NULL, t = NULL, sig2.s = 0,
sig2.e = 1, sig.level = 0.05, power = NULL,
alternative = c("two.sided", "one.sided"), tol = .Machine$double.eps^2)
Arguments
n
sample size per group
delta
group difference in slopes
t
the observation times
sig2.s
variance of random slope
sig2.e
residual variance
sig.level
type one error
power
power
alternative
one- or two-sided test
tol
numerical tolerance used in root finding.
Details
This function will also provide sample size estimates for linear mixed
models with random intercept only simply by setting sig2.s = 0
Value
The number of subject required per arm to attain the specified
power given sig.level and the other parameter estimates.
Author(s)
Michael C. Donohue, Steven D. Edland
References
Edland, S.D. (2009) Which MRI measure is best for Alzheimer's
disease prevention trials: Statistical considerations of power and sample
size. Joint Stat Meeting Proceedings. 4996-4999.