Response Effects Over Time:

Abstract

Two split-ballot experiments on attitude questions—one on inclusion or exclusion of “don't know” options and one on agree/disagree versus forced-choice format—were included in the General Social Survey in 1974 and replicated in 1982. Response effects occurred in each experiment in 1974 and were generally replicated in 1982, but the effects do not interact with time. Despite the significant response effects, both forms for each experiment yield similar conclusions about change over time, as long as question wording is kept constant. However, a borderline interaction with education in the 1974 data for the agree/disagree versus forced-choice experiment replicates more clearly in 1982, indicating that the two forms yield different conclusions about the relation of the question content to education.