steigerTest: Comparison of two dependent correlation coefficients

In JAQuent/compareCorrelations: Comparing correlations coefficients.

Description

This function allows to compare dependent correlation coefficients. It tests whether two correlation coefficients do not differ from each other. The first possible test is to compare the correlation between variable a and variable b with the correlation between variable a and variable b (type 1)

H0: ρ(a,b) = ρ(a,c).

The second possible test is to compare the correlation between variable a and variable b with the correlation between variable c and variable d (type 2)

H0: ρ(a,b) = ρ(c,d).

Usage

steigerTest(r, n, type, alternative = "greater")

Arguments

r	numeric vector or matrix containing the observed correlations. If type 1 , then r must be a vector containing the correlation coefficients in the following order r(a,b), r(a,c), r(b,c). If type 2, then r must be a correlation matrix.
n	numeric scalar indicating the sample size.
type	numeric scalar indicating which type of test. Possible values are 1 and 2 (see description).
alternative	character string indicating the kind of alternative hypothesis. The possible values are "greater" (the default), "less" and "two-tailed".

Value

a list of class "htest" containing the results of the hypothesis test. See the help file for htest.object for details.

Author(s)

Jörn Alexander Quent, [e-mail]

References

Bortz, J., & Schuster, C. (2010). Statistik für Human- und Sozialwissenschaftler. Berlin, Heidelberg: Springer-Verlag Berlin Heidelberg. Retrieved from http://dx.doi.org/10.1007/978-3-642-12770-0

Steiger, J. H. (1980). Tests for comparing elements of a correlation matrix. Psychological Bulletin, 87(2), 245-251. http://doi.org/10.1037/0033-2909.87.2.245

Examples

 r <- matrix(c(1, 0.5, 0.8, 0.5, 0.5, 1, 0.5, 0.7, 0.8, 0.5, 1, 0.6, 0.5, 0.7, 0.6, 1), ncol = 4, nrow = 4)
 results <- steigerTest(r, 103, 2)

JAQuent/compareCorrelations documentation built on May 7, 2019, 6:46 a.m.