Measuring Polarization Updated

I have just updated my R-package to measure agreement, polarization, dispersion — whatever you want to call it — in ordered rating scales to R-Forge. Version 1.40 includes more extensive documentation and a long due update of the package vignette. I’ll push it to CRAN in a moment. Every time I work on this package, it strikes me how many times the ‘problem’ has been solved, how different the approaches are, and sadly how often standard deviations are still used.

New Version of R Package agrmt

This week, a new version of the R package agrmt saw the light of day. I have been contacted because one of the functions in the package didn’t produce the right answers. I really appreciate this (the contacting), because it allowed me to fix the code. It was a matter of mixing up i and j. The first reaction in this case is always the worst: what if I got it all wrong? What if I can’t find the bug? To me, fixing code in my packages is important — not because of the undeniable satisfaction from getting it right — but because it is a small way to give back to the (virtual) community that gave us R and the many packages that come along with it.

The package, by the way, implements measures of agreement (consensus) in ordered rating scales, especially Cees van der Eijk’s (2001) measure of agreement A, but also measures of consensus (dispersion) by Leik, Tatsle and Wierman, Blair and Lacy, Kvalseth, and Berry and Mielke. Moreover, it implements Galtung’s AJUS for R.

Measuring Consensus

I have mentioned Cees van der Eijk’s measure of agreement before, and Leik’s measure of ordinal consensus. Unsurprisingly, others have come across this issue, discontent with the widespread use of standard deviations (inappropriate as this can be). Tastle & Wierman (2007) take a quite different approach, taking the Shannon entropy as the starting point. I have added this to my R package agrmt on R-Forge, and will push it through to CRAN once the documentation is up to scratch. It’s interesting how many different approaches are developed to address the same problem; clearly the different solutions have not spread wide enough to prevent doubling the effort.

Tastle, W., and M. Wierman. 2007. Consensus and dissention: A measure of ordinal dispersion. International Journal of Approximate Reasoning 45 (3): 531-545.