Dual scaling of rating data

TL;DR

This paper compares dual scaling and correspondence analysis for rating data, highlighting differences in preprocessing and proposing a variant of dual scaling that directly uses ratings for improved analysis.

Contribution

It introduces a dual scaling variant that directly applies to ratings and provides a detailed comparison of methods for analyzing rating data.

Findings

Dual scaling can be adapted to ratings without transformation.

Correspondence analysis involves rating doubling, affecting analysis.

The proposed dual scaling variant offers practical advantages.

Abstract

When applied to contingency tables, dual scaling and correspondence are mathematically equivalent methods. For the analysis of rating data, however, the methods differ. To a large extent this is due to differences in preprocessing of the data. In particular, in dual scaling, ratings are either transformed to rank order, or to successive category data before applying a customised dual scaling approach. In correspondence analysis, on the other hand, a so-called doubling of the original ratings is applied before applying the usual correspondence analysis formulas. In this paper, we consider these differences in detail. We propose a dual scaling variant that can be applied directly to the ratings and we compare theoretical as well as practical properties of the different approaches.