Models for Pooled Cross-Section Time-Series Data

• In Event: 600 - Section on Crime, Law and Deviance Roundtable Session
  In Refereed Roundtable: Table 11. Innovations in Methodology and Analysis

Abstract

Several models are available for the analysis of pooled cross-section time-series (CSTS) data, defined as “repeated observations on fixed units” (Beck and Katz 1995). In this paper, we run the following models: (1) a completely pooled model, (2) fixed effects models, and (3) multi-level/hierarchical linear models. To illustrate these models, we use a Generalized Least Squares (GLS) estimator with cross-section weights (with EViews 8) on the cross-national homicide trends data of 40 countries from 1950 to 2005, which we borrow from published research (Messner et al. 2011). We then describe and discuss those models, their similarities and differences, and what information each can contribute to help answer substantive research questions. We conclude with a discussion of how the models we present may help to mitigate validity threats inherent in pooled cross-section time-series data analysis.

Authors

• Lawrence E. Raffalovich, State University of New York-Albany

• Rakkoo Chung, State University of New York-Albany