pse (version 0.4.7)

sbma: Calculates the Symetrized Blest Measure of Agreement between two samples

Description

The Symetrized Blest Measure of Agreement is an alternative measure of rank correlation (similar to Kendall's Tau and Spearman's Rho). This correlation measure is more sensitive to changes in the order of the first elements of a vector (see examples).

Usage

sbma(sample1, sample2, absolute = TRUE, ...)
# S3 method for default
sbma(sample1, sample2, absolute = TRUE, ...)
# S3 method for LHS
sbma(sample1, sample2, absolute, ...)

Arguments

sample1

The first vector or LHS object to be compared.

sample2

The second vector or LHS object to be compared.

absolute

Logical. Should the absolute values of sample1 and sample2 be used in the calculation?

…

Additional arguments.

Details

This function calculates the SBMA between two samples or two LHS objects. In the second case, what is compared is the values of the "prcc" component of each Hypercube.

References

Maturi, T.A. and Elsayigh, A. 2010. A comparison of correlation coefficients via a three-step bootstrap approach. Journal of Mathematics Research 2(2): 3-10.

Examples

# SBMA is only affected by the rank of the values inside each vector
sbma(c(1,2,3,4), c(2,3,4,5))
# Changes in the first positions: high impact on the SBMA
sbma(c(1,2,3,4), c(2,1,3,4))
cor(c(1,2,3,4), c(2,1,3,4), method="spearman")
# Changes in the last positions: low impact on the SBMA
sbma(c(1,2,3,4), c(1,2,4,3))
cor(c(1,2,3,4), c(1,2,4,3), method="spearman")