Models for Pooled Time-Series Cross-Section Data

Authors

  • Lawrence E Raffalovich University at Albany, SUNY
  • Rakkoo Chung University at Albany, SUNY

DOI:

https://doi.org/10.4119/ijcv-3056

Abstract

Several models are available for the analysis of pooled time-series cross-section (TSCS) 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 and panel-corrected standard errors (with EViews 8) on the cross-national homicide trends data of forty countries from 1950 to 2005, which we source from published research (Messner et al. 2011). We describe and discuss the similarities and differences between the models, 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 time-series cross-section data analysis.

Author Biographies

Lawrence E Raffalovich, University at Albany, SUNY

Department of Sociology

Associate Professor (Emeritus)

Rakkoo Chung, University at Albany, SUNY

Department of Sociology

Ph.D. Candidate (ABD)

Metrics
Views/Downloads
  • Abstract
    850
  • PDF
    669
  • ePUB
    262
  • mobi
    214
Further information

Published

2015-05-28

How to Cite

Raffalovich, L. E., & Chung, R. (2015). Models for Pooled Time-Series Cross-Section Data. International Journal of Conflict and Violence, 8(2), 209–221. https://doi.org/10.4119/ijcv-3056

Issue

Section

Focus: Methodological Issues in Longitudinal of Criminal Violence