×

Simultaneous inference in structured additive conditional copula regression models: a unifying Bayesian approach. (English) Zbl 1505.62229

Summary: While most regression models focus on explaining distributional aspects of one single response variable alone, interest in modern statistical applications has recently shifted towards simultaneously studying multiple response variables as well as their dependence structure. A particularly useful tool for pursuing such an analysis are copula-based regression models since they enable the separation of the marginal response distributions and the dependence structure summarised in a specific copula model. However, so far copula-based regression models have mostly been relying on two-step approaches where the marginal distributions are determined first whereas the copula structure is studied in a second step after plugging in the estimated marginal distributions. Moreover, the parameters of the copula are mostly treated as a constant not related to covariates and most regression specifications for the marginals are restricted to purely linear predictors. We therefore propose simultaneous Bayesian inference for both the marginal distributions and the copula using computationally efficient Markov chain Monte Carlo simulation techniques. In addition, we replace the commonly used linear predictor by a generic structured additive predictor comprising for example nonlinear effects of continuous covariates, spatial effects or random effects and furthermore allow to make the copula parameters covariate-dependent. To facilitate Bayesian inference, we construct proposal densities for a Metropolis-Hastings algorithm relying on quadratic approximations to the full conditionals of regression coefficients avoiding manual tuning. The performance of the resulting Bayesian estimates is evaluated in simulations comparing our approach with penalised likelihood inference, studying the choice of a specific copula model based on the deviance information criterion, and comparing a simultaneous approach with a two-step procedure. Furthermore, the flexibility of Bayesian conditional copula regression models is illustrated in two applications on childhood undernutrition and macroecology.

MSC:

62-08 Computational methods for problems pertaining to statistics
62F15 Bayesian inference
62H05 Characterization and structure theory for multivariate probability distributions; copulas
62J12 Generalized linear models (logistic models)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Acar, E.F., Craiu, R.V., Yao, F.: Dependence calibration in conditional copulas: a nonparametric approach. Biometrics 67, 445-453 (2011) · Zbl 1217.62068 · doi:10.1111/j.1541-0420.2010.01472.x
[2] Acar, E.F., Craiu, V.R., Yao, F.: Statistical testing of covariate effects in conditional copula models. Electron. J. Stat. 7, 2822-2850 (2013) · Zbl 1280.62052 · doi:10.1214/13-EJS866
[3] Belitz, C., Lang, S.: Simultaneous selection of variables and smoothing parameters in structured additive regression models. Comput. Stat. Data Anal. 53, 61-81 (2008) · Zbl 1452.62029 · doi:10.1016/j.csda.2008.05.032
[4] Belitz, C.; Hübner, J.; Klasen, S.; Lang, S.; Kneib, T. (ed.); Tutz, G. (ed.), Determinants of the socioeconomic and spatial pattern of undernutrition by sex in india: a geoadditive semi-parametric regression approach, 155-179 (2010), Heidelberg · doi:10.1007/978-3-7908-2413-1_9
[5] Brezger, A., Lang, S.: Generalized structured additive regression based on Bayesian P-splines. Comput. Stat. Data Anal. 50, 967-991 (2006) · Zbl 1431.62308 · doi:10.1016/j.csda.2004.10.011
[6] Chakraborty, B.: On multivariate quantile regression. J. Stat. Plan. Inference 110, 109-132 (2003) · Zbl 1030.62046 · doi:10.1016/S0378-3758(01)00277-4
[7] Chaudhuri, P.: On a geometric notion of quantiles for multivariate data. J. Am. Stat. Assoc. 91, 862-872 (1996) · Zbl 0869.62040 · doi:10.1080/01621459.1996.10476954
[8] Craiu, V.R., Sabeti, A.: In mixed company: Bayesian inference for bivariate conditional copula models with discrete and continuous outcomes. J. Multivar. Anal. 110, 106-120 (2012) · Zbl 1244.62031 · doi:10.1016/j.jmva.2012.03.010
[9] Dagum, C.: A new model of personal income distribution: specification and estimation. Econ. Appl. 30, 413-437 (1977)
[10] Fahrmeir, L., Kneib, T.: Bayesian Smoothing and Regression for Longitudinal, Spatial and Event History Data. Oxford University Press, New York (2011) · Zbl 1249.62003 · doi:10.1093/acprof:oso/9780199533022.001.0001
[11] Fahrmeir, L., Kneib, T., Lang, S.: Penalized structured additive regression for space-time data: a Bayesian perspective. Stat. Sin. 14, 731-761 (2004) · Zbl 1073.62025
[12] Fahrmeir, L., Kneib, T., Lang, S., Marx, B.: Regression—Models, Methods and Applications. Springer, Berlin (2013) · Zbl 1276.62046
[13] Fermanian, J., Scaillet, O.: Nonparametric estimation of copulas for time series. J. Risk 5, 25-54 (2003)
[14] Gamerman, D.: Sampling from the posterior distribution in generalized linear mixed models. Stat. Comput. 7, 57-68 (1997) · doi:10.1023/A:1018509429360
[15] Genest, C., Masiello, E., Tribouley, K.: Estimating copula densities through wavelets. Insur. Math. Econ. 44, 170-181 (2009) · Zbl 1167.91015 · doi:10.1016/j.insmatheco.2008.07.006
[16] Gijbels, I., Veraverbeke, N., Omelka, M.: Conditional copulas, association measures and their applications. Comput. Stat. Data Anal. 55, 1919-1932 (2011) · Zbl 1328.62366 · doi:10.1016/j.csda.2010.11.010
[17] Gneiting, T., Katzfuss, M.: Probabilistic forecasting. Annu. Rev. Stat. Appl. 1, 125-151 (2014) · doi:10.1146/annurev-statistics-062713-085831
[18] Hafner, C.M., Manner, H.: Dynamic stochastic copula models: estimation, inference and applications. J. Appl. Econom. 27, 269-295 (2012) · doi:10.1002/jae.1197
[19] Jetz, W., Kreft, H., Ceballos, G., Mutke, J.: Global associations between terrestrial producer and vertebrate consumer diversity. Proc. R. Soc. B 276, 269-278 (2009) · doi:10.1098/rspb.2008.1005
[20] Joe, H.: Multivariate Models and Dependence Concepts. Chapman & Hall/CRC, London (1997) · Zbl 0990.62517 · doi:10.1201/b13150
[21] Kauermann, G., Schellhase, C.: Flexible pair-copula estimation in D-vines using bivariate penalized splines. Stat. Comput. 24, 1081-1100 (2014) · Zbl 1332.62117 · doi:10.1007/s11222-013-9421-5
[22] Kauermann, G., Schellhase, C., Ruppert, D.: Flexible copula density estimation with penalized hierarchical B-splines. Scand. J. Stat. 40, 685-705 (2013) · Zbl 1364.62084 · doi:10.1111/sjos.12018
[23] Klasen, S., Moradi, A.: The nutritional status of elites in India, Kenya, and Zambia: an appropriate guide for developing reference standards for undernutrition? Technical Report. Sonderforschungsbereich 386: Analyse Diskreter Strukturen. Discussion Paper No. 217. http://epub.ub.uni-muenchen.de/view/subjects/160101.html (2000) · Zbl 1431.62308
[24] Klein, N., Kneib, T., Lang, S.: Bayesian structured additive distributional regression. Working papers in economics and statistics 2012-23. Faculty of Economics and Statistics, University of Innsbruck (2013). http://eeecon.uibk.ac.at/wopec2/repec/inn/wpaper/2013-23.pdf
[25] Klein, N., Kneib, T., Klasen, S., Lang, S.: Bayesian structured additive distributional regression for multivariate responses. J. R. Stat. Soc. Ser. C (2015a) · Zbl 1452.62029
[26] Klein, N., Kneib, T., Lang, S.: Bayesian generalized additive models for location, scale and shape for zero-inflated and overdispersed count data. J. Am. Stat. Assoc. 110, 405-419 (2015b) · Zbl 1373.62103
[27] Lambert, P.: Archimedean copula estimation using Bayesian splines smoothing techniques. Comput. Stat. Data Anal. 51, 6307-6320 (2007) · Zbl 1445.62105 · doi:10.1016/j.csda.2007.01.018
[28] Marra, G., Radice, R.: SemiParBIVProbit: Semiparametric Bivariate Probit Modelling. R package version 3.3 (2015)
[29] Omelka, M., Gijbels, I., Veraverbeke, N.: Improved kernel estimation of copulas: weak convergence and goodness-of-fit testing. Ann. Stat. 37, 3023-3058 (2009) · Zbl 1360.62160 · doi:10.1214/08-AOS666
[30] Patton, A.J.: Modelling asymmetric exchange rate dependence. Int. Econ. Rev. 47, 527-556 (2006) · doi:10.1111/j.1468-2354.2006.00387.x
[31] Pitt, M., Chan, D., Kohn, R.: Efficient Bayesian inference for Gaussian copula regression models. Biometrika 93, 537-554 (2006) · Zbl 1108.62027 · doi:10.1093/biomet/93.3.537
[32] Radice, R., Marra, G., Wojtys, M.: Copula regression spline models for binary outcomes. Technical report (submitted) (n.d.) · Zbl 1505.62328
[33] Rigby, R.A., Stasinopoulos, D.M.: Generalized additive models for location, scale and shape (with discussion). J. R. Stat. Soc. Ser. C (Appl. Stat.) 54, 507-554 (2005) · Zbl 1490.62201 · doi:10.1111/j.1467-9876.2005.00510.x
[34] Rue, H., Held, L.: Gaussian Markov Random Fields. Chapman & Hall/CRC, New York/Boca Raton (2005) · Zbl 1093.60003 · doi:10.1201/9780203492024
[35] Segers, J., van den Akker, R., Werker, B.J.M.: Semiparametric Gaussian copula models: geometry and efficient rank-based estimation. Ann. Stat. 42, 1911-1940 (2014) · Zbl 1305.62115 · doi:10.1214/14-AOS1244
[36] Shen, X., Zhu, Y., Song, L.: LinearB-spline copulas with applications to nonparametric estimation of copulas. J. Comput. Stat. Data Anal. 52, 3806-3819 (2008) · Zbl 1452.62356 · doi:10.1016/j.csda.2008.01.002
[37] Sklar, A.: Fonctions de répartition à \[n\] n dimensions et leurs marge. Publications de l’Institut de Statistique de l’Université de Paris 8, 229-231 (1959) · Zbl 0100.14202
[38] Wood, S.: mgcv: Mixed GAM Computation Vehicle with GCV/AIC/REML Smoothness Estimations. R package version 1.8-5 (2015) · Zbl 1452.62356
[39] Wood, S.N.: Generalized Additive Models : An Introduction with R. Chapman & Hall/CRC, New York/Boca Raton (2006) · Zbl 1087.62082
[40] Yee, T.W.: VGAM: Vector Generalized Linear and Additive Models. R package version 0.9-7 (2015) · Zbl 0113.34902
[41] Zellner, A.: An efficient method of estimating seemingly unrelated regression equations and tests for aggregation bias. J. Am. Stat. Assoc. 57, 348-368 (1962) · Zbl 0113.34902 · doi:10.1080/01621459.1962.10480664
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.