Panel models with interactive effects
Journal of Econometrics, 2018, vol. 206, issue 2, 645-673
The multiplication of individual specific effects, ▪ and time-specific effects, ▪ provides a more general formulation than the traditionally used additive form to capture the unobserved heterogeneity in panel data modeling. It is also a useful approach for dimension reduction for modeling cross-section dependence. However, ▪ and ▪ are unobservable. We explore the implications for econometric modeling under various formulations of the interactive effects models and suggest a quasi-likelihood approach as a common framework to study issues of estimation and statistical inference when regressors are either strictly exogenous or predetermined and under different combinations of the data size of cross-sectional dimension, N, and time series dimensions, T. We also suggest some computationally simpler estimation methods in light of the quasi-likelihood approach. Monte Carlo studies are conducted to highlight the issues involved.
Keywords: Interactive effects; Static and dynamic models; Initial observations; Asymptotic bias (search for similar items in EconPapers)
JEL-codes: C01 C13 C23 (search for similar items in EconPapers)
References: View references in EconPapers View complete reference list from CitEc
Citations Track citations by RSS feed
Downloads: (external link)
Full text for ScienceDirect subscribers only
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:eee:econom:v:206:y:2018:i:2:p:645-673
Access Statistics for this article
Journal of Econometrics is currently edited by T. Amemiya, A. R. Gallant, J. F. Geweke, C. Hsiao and P. M. Robinson
More articles in Journal of Econometrics from Elsevier
Bibliographic data for series maintained by Dana Niculescu ().