Applying Multilevel Confirmatory Factor Analysis to Measure Stability Over Time

• In Event: Poster Session: Political Methodology

Abstract

Longitudinal analysis has become the standard in political science. Testing whether constructs change over time is essential for longitudinal inference. With this study, I propose utilizing a multilevel confirmatory factor analysis (MCFA) approach to assess statistical stability of multiple indicator measures. For the illustration of the method I use data from the Longitudinal Internet Studies for the Social sciences (LISS). The limitations of the study and implications of the results are discussed.

Author

• Carl Clemens Berning, University of Mainz