Web Survey Bibliography

Title More Is Not Necessarily Better: Effects of Response Categories on Measurement Stability and Validity
Year 2002
Access date 19.04.2004
Abstract Some studies have found that test-retest reliability is linearly related to the number of response categories that are used. In contrast, others have concluded that there is no correspondence between reliability and the number of response categories used. In two separate studies, we varied the number of response categories using a between-subjects design to examine the temporal stability of self-report measurement of attitudes. We report two studies here, the first was administered in a paper-pencil format and varied the number of response categories from 2 to 9 across 5 different topics. The second study was a web-based survey and included an increased range of categories (from 2 to 11) and expanded consideration of other scale types (e.g., unipolar measures of frequency and likelihood versus bipolar measures of liking and agreement) across two different topics. Based on our findings, we discuss the implications for scale development and validity.
Year of publication2002
Bibliographic typeConferences, workshops, tutorials, presentations
Print

Web Survey Bibliography - The American Association for Public Opinion Research (AAPOR) 57th Annual Conference, 2002 (35)