On the estimation and testing of predictive panel regressions

H. Karabiyik, Joakim Westerlund, Paresh Narayan

Research output: Contribution to JournalArticleAcademicpeer-review


Hjalmarsson (2010) considers an OLS-based estimator of predictive panel regressions that is argued to be mixed normal under very general conditions. In a recent paper, Westerlund et al. (2016) show that while consistent, the estimator is generally not mixed normal, which invalidates standard normal and chi-squared inference. The purpose of the present paper is to study the consequences of this theoretical result in small samples, which is done using both simulated and real data.
Original languageEnglish
Pages (from-to)115-125
JournalJournal of International Financial Markets, Institutions & Money
Publication statusPublished - 2016


Dive into the research topics of 'On the estimation and testing of predictive panel regressions'. Together they form a unique fingerprint.

Cite this