Recent Scientific Accomplishments

Prucha’s recent research focuses primarily on the development of estimation methods and testing procedures for models with spatial (cross sectional) interactions for both cross sectional and panel data. For example, in his 2004 paper in the Journal of Econometrics (co-authored with Harry Kelejian), “Estimation of Simultaneous Systems of Spatially Interrelated Cross Sectional Equations,?Prucha considers a simultaneous system of equations that allows for spatial interactions in the endogenous variables, exogenous variables and disturbances. He introduces limited and full information Generalized Method of Moment type estimators for those models that are simple to compute even for large sample sizes, and establishes the large sample properties of those estimators. The model may be viewed as an extension of the widely used single equation Cliff-Ord model. Prucha’s 2001 paper in the Journal of Econometrics (co-authored with Harry Kelejian), “On the Asymptotic Distribution of the Moran I Test Statistic with Applications,?considers a widely used test for spatial correlation. Despite the popularity of the test, available results in the literature concerning the large sample distribution of this statistic have been limited and have been derived under assumptions that do not cover many applications of interest. The paper first gives a general result concerning the large sample distribution of Moran I type test statistics, and then applies this result to derive the large sample distribution of the Moran I test statistic for a variety of important models. In his forthcoming paper in the Journal of Econometrics (co-authored with Mudit Kapoor and Harry Kelejian), “Panel Data Models with Spatially Correlated Error Components,?Prucha formulates a model where the unobserved components are potentially both spatially and time-wise correlated, and develops methods of inference for that model. The model blends specifications typically considered in the spatial literature with those considered in the error components literature. Prucha’s forthcoming paper in the Journal of Econometrics (co-authored with Harry Kelejian), “HAC Estimation in a Spatial Framework,?considers a nonparametric heteroscedasticity and autocorrelation consistent (HAC) estimator of the variance-covariance matrix for a vector of sample moments within a spatial context, and demonstrates the consistency of the estimator under a set of assumptions that should be satisfied by a wide class of spatial models. Prucha’s work in theoretical econometrics has been published in various journals including, Econometrica and the Journal of Econometrics.

Funded Research

Prucha is currently principal investigator (P.I.) (jointly with David Drukker and Harry Kelejian) on an SBIR with Stata Corp. funded by the National Institute of Health on “New Methods and Software for Spatial-Regression Analysis.?The aims of the SBIR are to (i) develop new estimation methods for static and dynamic panel data models with spatial (cross sectional) interactions, and (ii) to implement these methods in Stata to make them conveniently accessible to a wide group of researchers in the social sciences. Prucha has also been PI (jointly with Harry Kelejian) of a National Science Foundation grant on the “Specification and Estimation of Spatial Models,?2000 - 2003.

Future Plans

Prucha’s research plans are to continue his work on the specification of models with spatial (cross sectional) interactions and the development of corresponding methods of inference, as well as to engage in collaborative efforts that use those models in empirical investigations.