Estimation of Dynamic Panel Data Regression Parameters Using Generalized Methods of Moment

Abstract

Panel data is a combination of cross section and time series. There are two panel data models, namely static and dynamic panel data. Because seeing the advantages of the dynamic panel data model which is able to overcome endogeneity problems related to the use of the dependent variable lag where in the static panel data model the use of the dependent variable lag causes the estimation results to be biased and inconsistent, so the author examines the dynamic panel data regression model. In the dynamic data model there is a lag of the dependent variable, this variable is correlated with error. Thus, estimation using OLS will result in a biased and inconsistent estimator. To overcome this, the dynamic panel data model can be estimated using the GMM Blundell-Bond approach. Based on the discussion, the parameter estimation formula for dynamic panel data regression using the Blundell-Bond GMM approach is as follows: