Comparing Political Units Over Time: An Overview of Time-Series-Cross-Section Analysis

Abstract

This article overviews time-series-cross-section (TSCS) data analysis in the social sciences, a method that has been gaining in popularity since the late 1990s. The paper outlines the pros and cons of the different strategies to model both the time-series and the cross-sectional dimensions of TSCS data. Most importantly, it is argued throughout that one should follow an iterative process when modeling TSCS data. This means using more general models first and then imposing some restrictions on the basis of theoretical insights and in accordance with the actual structure of the data.