What to do (and not to do) with Time-Series Cross-Section Data

by: Nathaniel Beck, Jonathan N Katz

The American Political Science Review, Vol. 89, No. 3. (1995), pp. 634-647.

View FullText article

DOI, JSTOR

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

RolandKappe

Find related articles with these CiteULike tags

econometrics, panel

Abstract

We examine some issues in the estimation of time-series cross-section models, calling into question the conclusions of many published studies, particularly in the field of comparative political economy. We show that the generalized least squares approach of Parks produces standard errors that lead to extreme overconfidence, often underestimating variability by 50% or more. We also provide an alternative estimator of the standard errors that is correct when the error structures show complications found in this type of model. Monte Carlo analysis shows that these "panel-corrected standard errors" perform well. The utility of our approach is demonstrated via a reanalysis of one "social democratic corporatist" model.

@article{citeulike:2796255, abstract = {We examine some issues in the estimation of time-series cross-section models, calling into question the conclusions of many published studies, particularly in the field of comparative political economy. We show that the generalized least squares approach of Parks produces standard errors that lead to extreme overconfidence, often underestimating variability by 50\% or more. We also provide an alternative estimator of the standard errors that is correct when the error structures show complications found in this type of model. Monte Carlo analysis shows that these "panel-corrected standard errors" perform well. The utility of our approach is demonstrated via a reanalysis of one "social democratic corporatist" model.}, author = {Beck, Nathaniel and Katz, Jonathan N. }, citeulike-article-id = {2796255}, doi = {10.2307/2082979}, journal = {The American Political Science Review}, keywords = {econometrics, panel}, number = {3}, pages = {634--647}, posted-at = {2008-05-14 01:00:57}, priority = {2}, publisher = {American Political Science Association}, title = {What to do (and not to do) with Time-Series Cross-Section Data}, url = {http://dx.doi.org/10.2307/2082979}, volume = {89}, year = {1995} }

RIS record

TY - JOUR ID - citeulike:2796255 L3 - citeulike-article-id:2796255 TI - What to do (and not to do) with Time-Series Cross-Section Data JF - The American Political Science Review VL - 89 IS - 3 SP - 634 EP - 647 PB - American Political Science Association N2 - We examine some issues in the estimation of time-series cross-section models, calling into question the conclusions of many published studies, particularly in the field of comparative political economy. We show that the generalized least squares approach of Parks produces standard errors that lead to extreme overconfidence, often underestimating variability by 50% or more. We also provide an alternative estimator of the standard errors that is correct when the error structures show complications found in this type of model. Monte Carlo analysis shows that these "panel-corrected standard errors" perform well. The utility of our approach is demonstrated via a reanalysis of one "social democratic corporatist" model. KW - econometrics KW - panel AU - Beck, Nathaniel AU - Katz, Jonathan PY - 1995/// UR - http://dx.doi.org/10.2307/2082979 ER -

RIS BibTeX