Adjustment for Acquiescence in the Assessment of the Construct Equivalence of Likert-Type Score Items

Abstract

Survey research often uses Liker-type score items to measure respondents' attitudes with respect to certain topics. This type of item has been shown to be susceptible to an acquiescent response bias. The purpose of this article is to point out the importance of controlling for this type of response bias when evaluating the equivalence of the construct measured by the items across (cultural) groups. More specifically, it is shown how and when omitting a factor accounting for the acquiescent response bias leads to a biased assessment of the invariance of the loadings of the content factor across the groups under study. On the basis of these results, a procedure for controlling for acquiescence is proposed and illustrated on a large data set of nine West European countries.