A Cautionary Note on the Use of Principal Components Analysis

Publisher Website
Google Scholar
Abstract
This study addresses the issue of the relation between the number of response categories used in survey questions and the quality of measurement. Several hypotheses, derived from relevant theory and research, are tested through a comparison between 7- and 11-category rating scales used in the 1978 Quality of Life Survey. One hypothesis derived from information theory, that rating scales with more response categories transmit a greater amount of information and are therefore inherently more precise in their measurement, is strongly supported. A second hypothesis, that questions with greater numbers of response categories are more vulnerable to systematic measurement errors or shared method variance, is rejected. This study supports the conclusion that questions with more categories are both more reliable and more valid.

This publication has 9 references indexed in Scilit: