ci.mixed.between: Confidence interval for the "main effect" of a...

In m-Py/propint: Testing for interactions in proportions

Description

This function computes a confidence interval for the main effect of a grouping variable across two levels of a within subject factor when the measure of interest is dichotomous. This for example corresponds to the effectiveness of a treatment on individuals across two different points in time. The confidence interval that is produced is corrected for the within-subjects dependence of the two measures by applying a correction suggested by Donner and Klar (section 2.1; 1993) to the standard error of the difference of proportions.

Usage

ci.mixed.between(ci, group1.measure1, group1.measure2, group2.measure1,
  group2.measure2)

Arguments

ci	The confidence level - pass as a natural number (e.g. 95 for the 95% confidence interval).
group1.measure1	A vector of "successes" (= 1) and "fails" (= 0) for the first measure in group 1
group1.measure2	A vector of "successes" (= 1) and "fails" (= 0) for the second measure in group 1
group2.measure1	A vector of "successes" (= 1) and "fails" (= 0) for the first measure in group 2
group2.measure2	A vector of "successes" (= 1) and "fails" (= 0) for the second measure in group 2

Author(s)

Martin Papenberg [e-mail]

References

Donner, A., & Klar, N. (1993). Confidence interval construction for effect measures arising from cluster randomization trials. Journal of clinical epidemiology, 46(2), 123-131.

m-Py/propint documentation built on July 26, 2019, 8:47 a.m.