Composite Quasi-Likelihood Estimation of Dynamic Panels with Group-Specific Heterogeneity and Spatially Dependent Errors

Chu, Ba (2017): Composite Quasi-Likelihood Estimation of Dynamic Panels with Group-Specific Heterogeneity and Spatially Dependent Errors.

Abstract

This paper proposes a novel method to estimate large panel data error-correction models with stationary/non-stationary covariates and spatially dependent errors, which allows for known/unknown group-specific patterns of slope heterogeneity. Analysis is based on composite quasi-likelihood (CQL) maximization which performs estimation and classification simultaneously. The proposed CQL estimator remains unbiased in the presence of misspecification of the unobserved individual/group-specific fixed effects; therefore, neither instrumental variables nor bias corrections/reductions are required. This estimator also achieves the `oracle' property as the estimation errors of group memberships have no effect on the asymptotic distributions of the group-specific slope parameters estimates. Classification and estimation involve a large-scale non-convex mixed-integer programming problem, which can then be solved via a new algorithm based on DC (Difference-of-Convex functions) programming - the DCA (DC Algorithm). Simulations confirm good finite-sample properties of the proposed estimator. An empirical application and a software package to implement this method are also provided.

• Item Type: MPRA Paper
• Language: English
• Keywords: Large dynamic panels, Error-correction models (ECM), spatial dependence, common-group time variation (trends), mixing random fields, group-specific heterogeneity, clustering, composite quasi-likelihood (CQL), large-scale non-convex mixed-integer programs, difference of convex (d.c.) functions, DCA, K-means, Variable Neighborhood Search (VNS)
• Subjects: C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C31 - Cross-Sectional Models ; Spatial Models ; Treatment Effect Models ; Quantile Regressions ; Social Interaction Models; C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C33 - Panel Data Models ; Spatio-temporal Models; C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C38 - Classification Methods ; Cluster Analysis ; Principal Components ; Factor Models; C - Mathematical and Quantitative Methods > C5 - Econometric Modeling > C55 - Large Data Sets: Modeling and Analysis

References

Alexiadis, S. (2013): Convergence Clubs and Spatial Externalities: Models and Applications of Regional Convergence in Europe, Advances in Spatial Science. Springer-Verlag, Berlin Heidelberg.

Ando, T., and J. Bai (2016): “Panel Data Models with Grouped Factor Structure Under Unknown Group Membership,” Journal of Applied Econometrics, 31, 163–191.

Arellano, M. (1987): “Computing Robust Standard Errors for Within-Groups Estimators,” Oxford Bulletin of Economics and Statistics, 49(4), 431434.

Bester, C. A., and C. B. Hansen (2016): “Grouped effects estimators in fixed effects models,” Journal of Econometrics, 190(1), 197–208.

Billingsley, P. (1968): Convergence of Probability Measures. John Wiley & Sons, New York, Singapore, Toronto, 1 edn.

Bonhomme, S., T. Lamadon, and E. Manresa (2016): “Discritizing Unobserved Heterogeneity: Approximate Clustering Methods for Dimension Reduction,” mimeo.

Bonhomme, S., and E. Manresa (2015): “Grouped patterns of heterogeneity in panel data,” Econometrica, 83, 1147–1184.

Bonnans, J. F., and A. Shapiro (2000): Perturbation Analysis of Optimization Problems. Springer, New York, Berlin, Heidelberg.

Bradley, P. S., and O. L. Mangasarian (1998): “Feature Selection via Concave Minimization and Support Vector Machines,” in Machine Learning Proceedings of the Fifteenth International Conference(ICML ’98), ed. by J. Shavlik, pp. 82–90, San Francisco, California. Morgan Kaufmann.

Brown, D. E., and C. L. Huntley (1992): “A practical application of simulated annealing to clustering,” Pattern Recognition, 25(4), 401–412.

Bulinski, A., and A. Shashkin (2006): “Strong invariance principle for dependent random fields,” in Dynamics & Stochastics : Festschrift in honor of M. S. Keane, ed. by D. Denteneer, F. den Hollander, and E. Verbitskiy, IMS Lecture Notes - Monograph Series Volume 48, pp. 128–143, Beachwood, Ohio, USA. Institute of Mathematical Statistics.

Bulinski, A., and A. Shashkin (2007): Limit Theorems for Associated Random Fields and Related Systems. World Scientific, Singapore, 1 edn.