×

Bayesian analysis of dynamic panel data by penalized quantile regression. (English) Zbl 1387.62047

Summary: Existing literature on quantile regression for panel data models with individual effects advocates the application of penalization to reduce the dynamic panel bias and increase the efficiency of the estimators. In this paper, we consider penalized quantile regression for dynamic panel data with random effects from a Bayesian perspective, where the penalty involves an adaptive Lasso shrinkage of the random effects. We also address the role of initial conditions in dynamic panel data models, emphasizing joint modeling of start-up and subsequent responses. For posterior inference, an efficient Gibbs sampler is developed to simulate the parameters from the posterior distributions. Through simulation studies and analysis of a real data set, we assess the performance of the proposed Bayesian method.

MSC:

62G08 Nonparametric regression and quantile regression
62F15 Bayesian inference
62J07 Ridge regression; shrinkage estimators (Lasso)

Software:

R
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Abramowitz M, Stegun N (1970) Handbook of mathematical functions. Dover Publication Inc, New York · Zbl 0171.38503
[2] Aghamohammadi A, Mohammadi S (2015) Bayesian analysis of penalized quantile regression for longitudinal data. Stat Papers. doi:10.1007/s00362-015-0737-4 · Zbl 1416.62206
[3] Alhamzawi R, Yu K (2013) Conjugate priors and variable selection for Bayesian quantile regression. Comput Stat Data Anal 64:209-219 · Zbl 1468.62015 · doi:10.1016/j.csda.2012.01.014
[4] Arellano M, Bond S (1991) Some tests of specification for panel data: Monte Carlo evidence and an application to employment equations. Rev Econ Stud 58:277-297 · Zbl 0719.62116 · doi:10.2307/2297968
[5] Barndorff-Nielsen OE, Shephard N (2001) Non-Gaussian Ornstein-Uhlenbeck-based models and some of their uses in financial economics. J R Stat Soc Ser B 63:167-241 · Zbl 0983.60028 · doi:10.1111/1467-9868.00282
[6] Belloni A, Chernozhukov V (2009) L1-penalized quantile regression in high dimensional sparse models. Ann Stat 39:82-130 · Zbl 1209.62064 · doi:10.1214/10-AOS827
[7] Buchinsky M (1998) Recent advances in quantile regression models: a practical guideline for empirical authors. J Hum Resour 33:88-126 · doi:10.2307/146316
[8] Chen RB, Chu CH, Lai TY, Wu YN (2011) Stochastic matching pursuit for Bayesian variable selection. Stat Comput 21:247-259 · Zbl 1254.62027 · doi:10.1007/s11222-009-9165-4
[9] Chernozhukov V, Hansen C (2006) Instrumental quantile regression inference for structural and treatment effects models. J Econom 132:491-525 · Zbl 1337.62353 · doi:10.1016/j.jeconom.2005.02.009
[10] Chernozhukov V, Hansen C (2008) Instrumental variable quantile regression: a robust inference approach. J Econom 142:379-398 · Zbl 1418.62154 · doi:10.1016/j.jeconom.2007.06.005
[11] Chernozhukov V, Fernandez-Val I, Hahn J, Newey W (2013) Average and quantile effects in nonseparable panel models. Econometrica 81:535-580 · Zbl 1274.62580 · doi:10.3982/ECTA8405
[12] Chib S (1995) Marginal likelihood from the Gibbs output. J Am Stat Assoc 90(1313):1321 · Zbl 0868.62027
[13] Diggle PJ, Heagerty P, Liang KY, Zeger SL (2002) Analysis of longitudinal data, 2nd edn. Oxford University Press, Oxford · Zbl 1031.62002
[14] Chib S, Jeliazkov I (2006) Inference in semiparametric dynamic models for binary longitudinal data. J Am Stat Assoc 101:685-700 · Zbl 1119.62337 · doi:10.1198/016214505000000871
[15] Galvao AF, Montes-Rojas GV (2010) Penalized quantile regression for dynamic panel data. J Stat Plan Inference 140:3476-3497 · Zbl 1205.62195 · doi:10.1016/j.jspi.2010.05.008
[16] Galvao AF (2011) Quantile regression for dynamic panel data with fixed effects. J Econom 164:142-157 · Zbl 1441.62695 · doi:10.1016/j.jeconom.2011.02.016
[17] Galvao AF, Lamarche C, Lima L (2013) Estimation of censored quantile regression for panel data with fixed effects. J Am Stat Assoc 108:1075-1089 · Zbl 06224988 · doi:10.1080/01621459.2013.818002
[18] Geraci M, Bottai M (2007) Quantile regression for longitudinal data using the asymmetric Laplace distribution. Biostatistics 8:140-154 · Zbl 1170.62380 · doi:10.1093/biostatistics/kxj039
[19] Gilks WR, Best NG, Tan KKC (1995) Adaptive rejection Metropolis sampling within Gibbs sampling. Appl Stat 44:455-472 · Zbl 0893.62110 · doi:10.2307/2986138
[20] Gupta M, Qu P, Ibrahim JA (2007) Temporal hidden Markov regression model for the analysis of gene regulatory networks. Biostatistics 8:805-820 · Zbl 1267.62091 · doi:10.1093/biostatistics/kxm007
[21] Harding M, Lamarche C (2014) Estimating and testing a quantile regression model with interactive effects. J Econom 178:101-113 · Zbl 1293.62185 · doi:10.1016/j.jeconom.2013.08.010
[22] Heckman, JJ; Manski, CF (ed.); McFadden, D. (ed.), The incidental parameter problem and the problem of initial conditions in estimating a discrete time-discrete data stochastic process, 179-195 (1981), Cambridge
[23] Honore BE, Hu L (2004) Estimation of cross sectional and panel data censored regression models with endogeneity. J Econom 122:293-316 · Zbl 1328.62556 · doi:10.1016/j.jeconom.2003.06.001
[24] Hsiao C (2003) Analysis of panel data, 2nd edn. Cambridge University Press, Cambridge · Zbl 1320.62003 · doi:10.1017/CBO9780511754203
[25] Hu L (2002) Estimation of a censored dynamic panel data model. Econometrica 70:2499-2517 · Zbl 1094.62142 · doi:10.1111/1468-0262.00384
[26] Kass RE, Wasserman LA (1995) Reference Bayesian test for nested hypothesis and its relationship to the Schwarz criterion. J Am Stat Assoc 90:928-934 · Zbl 0851.62020 · doi:10.1080/01621459.1995.10476592
[27] Koenker R (2004) Quantile regression for longitudinal data. J Multivar Anal 91:74-89 · Zbl 1051.62059 · doi:10.1016/j.jmva.2004.05.006
[28] Koenker R (2005) Quantile regression. Cambridge University Press, New York · Zbl 1111.62037 · doi:10.1017/CBO9780511754098
[29] Koenker R, Basset G (1978) Regression quantiles. Econometrica 46:33-50 · Zbl 0373.62038 · doi:10.2307/1913643
[30] Koenker R, Machado J (1999) Goodness of fit and related inference processes for quantile regression. J Am Stat Assoc 94:1296-1309 · Zbl 0998.62041 · doi:10.1080/01621459.1999.10473882
[31] Kozumi H, Kobayashi G (2011) Gibbs sampling methods for Bayesian quantile regression. J Stat Comput Simul 81:1565-1578 · Zbl 1431.62018 · doi:10.1080/00949655.2010.496117
[32] Lamarche C (2010) Robust penalized quantile regression estimation for panel data. J Econom 157:396-498 · Zbl 1431.62161 · doi:10.1016/j.jeconom.2010.03.042
[33] Lee K, Sha N, Dougherty ER, Vannucci M, Mallik BK (2003) Gene selection: a Bayesian variable selection approach. Bioinformatics 19:90-97 · doi:10.1093/bioinformatics/19.1.90
[34] Li T, Zheng X (2008) Semiparametric Bayesian inference for dynamic Tobit panel data models with unobserved heterogeneity. J Appl Econom 23:699-728 · doi:10.1002/jae.1017
[35] Mundlak Y (1978) On the pooling of time series and cross-section data. Econometrica 46:69-85 · Zbl 0397.62066 · doi:10.2307/1913646
[36] Nerlove, M.; Balestra, P.; Mtys, L. (ed.); Sevestre, P. (ed.), Formulation and estimation of econometrics model for panel data, 3-22 (1996), Boston · doi:10.1007/978-94-009-0137-7_1
[37] Park T, Casella G (2008) The Bayesian lasso. J Am Stat Assoc 103:681-686 · Zbl 1330.62292 · doi:10.1198/016214508000000337
[38] R Development Core Team (2011) R: a language and environment for statistical computing. http://www.R-project.org · Zbl 1187.62183
[39] Smith M, Kohn R (1996) Nonparametric regression using Bayesian variable selection. J Econom 75:317-343 · Zbl 0864.62025 · doi:10.1016/0304-4076(95)01763-1
[40] Sun W, Ibrahim JG, Zou F (2010) Genom-wide multiple loci mapping in experimental crosses by the iterative adaptive penalized regression. Genetics 185:349-359 · doi:10.1534/genetics.110.114280
[41] Tierney L (1994) Markov chains for exploring posterior distributions (with discussion). Ann Stat 21:1701-1762 · Zbl 0829.62080 · doi:10.1214/aos/1176325750
[42] Wang J (2012) Bayesian quantile regression for parametric nonlinear mixed effects models. Stat Methods Appl 21:279-295 · Zbl 1329.62150 · doi:10.1007/s10260-012-0190-7
[43] Wooldrige JM (2005) Simple solution to the initial conditions problem in dynamic, nonlinear panel data models with unobserved heterogeneity. J Appl Econom 20:39-54 · doi:10.1002/jae.770
[44] Yi K, Xu S (2008) Bayesian lasso for quantitative trait loci mapping. Genetics 179:1045-1055 · doi:10.1534/genetics.107.085589
[45] Yu K, Moyeed RA (2001) Bayesian quantile regression. Stat Probab Lett 54:437-447 · Zbl 0983.62017 · doi:10.1016/S0167-7152(01)00124-9
[46] Yuan Y, Yin G (2010) Bayesian quantile regression for longitudinal studies with nonignorable missing data. Biometrics 66:105-114 · Zbl 1187.62183 · doi:10.1111/j.1541-0420.2009.01269.x
[47] Zou H (2006) The adaptive lasso and its oracle properties. J Am Stat Assoc 101:1418-1429 · Zbl 1171.62326 · doi:10.1198/016214506000000735
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.