Identification of common factors in panel data growth model

Abstract

Cross sectional dependence may lead to inconsistent and inefficient estimators and as such misleading inferences when standard panel data techniques such as fixed/random effects are employed. Pesaran (2006) suggests incorporating cross sectional averages in panel data models as approximates of unobserved common factor(s) to deal with cross sectional dependence. In the context of a standard panel growth model we investigate whether these unobserved common factors can be identified and we find that institutional variables and life expectancy are able to adequately identify them. (C) 2018 Elsevier B.V. All rights reserved.