PANEL PROBIT WITH FLEXIBLE CORRELATED EFFECTS: QUANTIFYING TECHNOLOGY SPILLOVERS IN THE PRESENCE OF LATENT HETEROGENEITY. (26th June 2012)

• Record Type: Journal Article
• Authors: Burda, Martin; Harding, Matthew
• Is Part Of: Journal of applied econometrics. Volume 28:Number 6(2013)
• Page Start: 956
• Page End: 981
• Publication Date: 2012-06-26
• Subjects: Econometrics -- Periodicals; 330.015195
• DOI: 10.1002/jae.2285
• Languages: English
• ISSNs: 0883-7252

Abstract

<abstract abstract-type="main"> <title>SUMMARY</title> <p>In this paper, we introduce a Bayesian panel probit model with two flexible latent effects: first, unobserved individual heterogeneity that is allowed to vary in the population according to a nonparametric distribution; and second, a latent serially correlated common error component. In doing so, we extend the approach developed in Albert and Chib (<italic>Journal of the American Statistical Association</italic> 1993; <bold>88</bold>: 669–679; in <italic>Bayesian Biostatistics</italic>, Berry DA, Stangl DK (eds), Marcel Dekker: New York, 1996), and in Chib and Carlin (<italic>Statistics and Computing</italic> 1999; <bold>9</bold>: 17–26) by releasing restrictive parametric assumptions on the latent individual effect and eliminating potential spurious state dependence with latent time effects. The model is found to outperform more traditional approaches in an extensive series of Monte Carlo simulations. We then apply the model to the estimation of a patent equation using firm‐level data on research and development (R&amp;D). We find a strong effect of technology spillovers on R&amp;D but little evidence of product market spillovers, consistent with economic theory. The distribution of latent firm effects is found to have a multimodal structure featuring within‐industry firm clustering. Copyright © 2012 John Wiley &amp; Sons, Ltd.</p> </abstract>