clusterPower (version 0.7.0)

cpa.irgtt.binary: Power calculations for individually randomized group treatment trials, binary outcome

Description

Compute the power of an individually randomized group treatment trial (IRGTT) design with a binary outcome, or determine parameters to obtain a target power.

Usage

cpa.irgtt.binary(
  alpha = 0.05,
  power = 0.8,
  nclusters = NA,
  nsubjects = NA,
  ncontrols = NA,
  ICC = NA,
  p2 = NA,
  p1 = NA,
  decrease = TRUE,
  tol = .Machine$double.eps^0.25
)

Arguments

alpha

The level of significance of the test, the probability of a Type I error.

power

The power of the test, 1 minus the probability of a Type II error.

nclusters

The number of clusters in the intervention arm.

nsubjects

The number of subjects in each cluster in the intervention arm.

ncontrols

The number of subjects in the control arm.

ICC

The intracluster correlation coefficient, the correlation in outcome measurements between two individuals from the same cluster in the intervention arm.

p2

The expected probability of the outcome in the intervention arm.

p1

The expected probability of the outcome in the control arm.

decrease

Whether or not the proportion in the intervention arm is expected to be less than the proportion in the control arm. If TRUE it is assumed p2 < p1, while FALSE implies p2 > p1.

tol

Numerical tolerance used in root finding. The default provides at least four significant digits.

Value

The computed argument.

Authors

Jonathan Moyer (), Ken Kleinman ()

Details

Exactly one of alpha, power, nclusters, nsubjects, ncontrols, ICC, p2, and p1 must be passed as NA. Note that alpha and power have non-NA defaults, so if those are the parameters of interest they must be explicitly passed as NA.

References

Moerbeek, M. and Wong, W. K. (2008) Sample size formulae for trials comparing group and individual treatments in a multilevel model. Statist. Med., 27:2850-2864. doi: 10.1002/sim.3115.

Examples

# NOT RUN {
# Find the required number of subjects per intervention cluster an IRGTT with alpha = 0.05,
# power = 0.80, nclusters = 23, ncontrols = 146, ICC = 0.05, p2 = 0.397, and p1 = 0.243.

cpa.irgtt.binary(nclusters=23, ncontrols = 146, 
  ICC = 0.05, p2 = 0.397, p1 = 0.243, decrease = FALSE)

# 
# The result, nsubjects = 7.96624, suggests 8 subjects per cluster 
# in the intervention arm should be recruited.
# This means that the total number of subjects in the 
# study is nclusters * nsubjects + ncontrols = 23 * 8 + 146 = 330.

# }