How to Analyze Time-Series Cross-Section Data in the Social Sciences. In this paper we present, step by step, a SAS statistical program for the analysis of Time-Series Cross-Section (TSCS) data which gives robust and unbiased regression estimates. Several statistical packages (SHAZAM. SAS. SPSS) offer procedures for the analysis of TSCS data based entirely, or in part, on a particular application of the Generalized Least Squares (GLS) method developed by Parks and Kmenta. In a series of recent articles. Beck and Katz have shown that the GLS estimation method often underestimates substantially the standard error of regression parameters in TSCS models. They suggest a new method for generating adequate correction of the error process in TSCS models. This method consists of using Ordinary Least Squares (OLS) parameter estimates first. and then replacing OLS standards errors (which are biased) with unbiased Panel-Corrected Standard Errors (PCSEs) obtained after correcting both temporal autocorrelation and spatial correlation structures. The paper provides a SAS application of the method suggested by Beck and Katz. The SAS program can be downloaded through our web site.
Beck, Nathaniel, et Jonathan N. Katz , 1995, "What to Do (and Not to Do) with Time-Series Cross-Section Data", American Political Science Review, Vol. 89, pp. 634-647.
2.
Kmenta, Jan, 1986, Elements of Econometrics, second edition, New York: McMillan.
3.
Parks, Richard, 1967, "Efficient Estimation of a System of Regression Equations When Disturbances Are Both Serially and Contemporaneously Correlated", Journal of the American Statistical Association, Vol. 62, pp. 500-509.
4.
SAS Institute, 1984, SAS/ETS User's Guide: Version6Edition, Cary, NC: SAS Institute.
