Abstract
The selection of fixed effects is studied in high-dimensional generalized linear mixed models (HDGLMMs) without parametric distributional assumptions except for some moment conditions. The iterative-proxy-based penalized quasi-likelihood method (IPPQL) is proposed to select the important fixed effects where an iterative proxy matrix of the covariance matrix of the random effects is constructed and the penalized quasi-likelihood is adapted. We establish the model selection consistency with oracle properties even for dimensionality of non-polynomial (NP) order of sample size. Simulation studies show that the proposed procedure works well. Besides, a real data is also analyzed.
References
Bondell, H. D., Krishna, A., Ghosh, S. K.: Joint variable selection for fixed and random effects in linear mixed-effects models. Biometrics, 66(4), 1069–1077 (2010)
Breheny, P., Huang, J.: Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection. J. Appl. Stat., 5(1), 232 (2011)
Breslow, N. E., Clayton, D. G.: Approximate inference in generalized linear mixed models. J. Amer. Statist. Assoc., 88(421), 9–25 (1993)
Breslow, N. E., Lin, X.: Bias correction in generalised linear mixed models with a single component of dispersion. Biometrika, 82(1), 81–91 (1995)
Brezger, A., Kneib, T., Lang, S.: BayesX: analyzing bayesian structural additive regression models. J. Stat. Softw., 14, 1–22 (2005)
Cai, B., Dunson, D. B.: Bayesian covariance selection in generalized linear mixed models. Biometrics, 62(2), 446–457 (2006)
Evangelou, E., Zhu, Z., Smith, R. L.: Estimation and prediction for spatial generalized linear mixed models using high order Laplace approximation. J. Statist. Plann. Inference, 141(11), 3564–3577 (2001)
Fan, J., Li, R.: Variable selection via nonconcave penalized likelihood and its oracle properties. J. Amer. Statist. Assoc., 96(456), 1348–1360 (2001)
Fan, J., Lv, J.: Nonconcave penalized likelihood with np-dimensionality. IEEE Trans. Inform. Theory, 57(8), 5467–5484 (2011)
Fan, Y., Li, R.: Variable selection in linear mixed effects models. Ann. Statist., 40(4), 2043–2068 (2012)
Fan, Y., Tang, C. Y.: Tuning parameter selection in high dimensional penalized likelihood. J. R. Stat. Soc. Ser. B Stat. Methodol., 75(3), 531–552 (2013)
Groll, A., Tutz, G.: Variable selection for generalized linear mixed models by Li-penalized estimation. Stat. Comput., 24(2), 137–154 (2014)
Hui, F. K., Müller, S., Welsh, A.: Hierarchical selection of fixed and random effects in generalized linear mixed models. Statist. Sinica, 501–518 (2017)
Hui, F. K., Müller, S., Welsh, A.. Joint selection in mixed models using regularized PQL. J. Amer. Statist. Assoc., 112(519), 1323–1333 (2017)
Jiang, J., Rao, J. S., Gu, Z., et al.: Fence methods for mixed model selection. Ann. Statist., 36(4), 1669–1692 (2008)
Laird, N. M., Ware, J. H.: Random-effects models for longitudinal data. Biometrics, 38(4), 963–974 (1982)
Lin, X.: Variance component testing in generalised linear models with random effects. Biometrika, 84(2), 309–326 (1997)
Lv, J., Fan, Y.: A unified approach to model selection and sparse recovery using regularized least squares. Ann. Statist., 37(6A), 3498–3528 (2009)
McCullagh, P., Nelder, J. A.: Generalized Linear Models, Chapman and Hall, London, 1989
McCulloch, C. E.: Maximum likelihood algorithms for generalized linear mixed models. J. Amer. Statist. Assoc., 92(437), 162–170 (1997)
Nelder, J. A., Pregibon, D.: An extended quasi-likelihood function. Biometrika, 74(2), 221–232 (1987)
Rabe-Hesketh, S., Skrondal, A., Pickles, A.: Reliable estimation of generalized linear mixed models using adaptive quadrature. The Stata Journal, 2(1), 1–21 (2002)
Schelldorfer, J., Meier, L., Bühlmann, P.: Glmmlasso: an algorithm for high-dimensional generalized linear mixed models using L1-penalization. J. Comput. Graph. Statist., 23(2), 460–477 (2014)
Tutz, G., Groll, A.: Likelihood-based boosting in binary and ordinal random effects models. J. Comput. Graph. Statist., 22(2), 356–378 (2013)
Wedderburn, R. W.: Quasi-likelihood functions, generalized linear models, and the Gauss-Newton method. Biometrika, 61(3), 439–447 (1974)
Zhang, C. H.: Nearly unbiased variable selection under minimax concave penalty. Ann. Statist., 38(2), 894–942 (2010)
Zou, H., Li, R.: One-step sparse estimates in nonconcave penalized likelihood models. Ann. Statist., 36(4), 1509–1533 (2008)
Acknowledgements
The authors thank the Editors and the referees for their constructive comments and suggestions that substantially improved an earlier manuscript.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by National Natural Science Foundation of China (Grant No. 11671398), State Key Lab of Coal Resources and Safe Mining (China University of Mining and Technology) (Grant No. SKLCRSM16KFB03) and the Fundamental Research Funds for the Central Universities in China (Grant No. 2009QS02)
Rights and permissions
About this article
Cite this article
Zhang, X.Y., Li, Z.X. Selection of Fixed Effects in High-dimensional Generalized Linear Mixed Models. Acta. Math. Sin.-English Ser. 39, 995–1021 (2023). https://doi.org/10.1007/s10114-023-2195-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10114-023-2195-6
Keywords
- Fixed effects selection
- HDGLMMs
- penalized quasi-likelihood
- proxy covariance matrices
- theoretical properties