Testing the stability of an acquiescence style factor behind two interrelated substantive variables in a panel design

This article addresses the question of to what extent one type of response style, called acquiescence (or agreeing response bias), is stable over time. A structural equation modeling approach is applied to measure the stability of one acquiescence factor behind two concepts among the same respondents for a 4-year period. The data used are representative population surveys in 1995 and 1999 from the Belgian Election Study in which balanced sets of items are used for measuring two inter-related constructs: perceived ethnic threat and distrust in politics. This study provides empirical support that acquiescence is stable and consistent for a 4-year period.