基于LsoCV准则的退出型缺失纵向数据模型平均估计
LsoCV Criterion-Based Model Averaging for Longitudinal Data with Dropout
摘要: 本文针对随机缺失假设下存在退出缺失的纵向数据，提出一种基于LsoCV准则的模型平均估计方法。该方法采用加权广义估计方程(WGEE)对各候选模型的参数进行估计，并通过去个体交叉验证(LsoCV)准则确定各模型的权重。模拟研究表明，所提出的模型平均方法展现出相较于其他替代方法更好的性能，且其优越性通过应用于PBC数据得到了进一步验证。
Abstract: In this paper, a model averaging estimation method based on the LsoCV criterion is proposed for longitudinal data with dropouts under the assumption of missing at random. This method adopts the weighted generalized estimating equations (WGEE) to estimate the parameters of each candidate model, and determines the weights of each model through the leave-subject-out cross-validation (LsoCV) criterion. Simulation studies reveal that the proposed model averaging method exhibits much better performance compared with other competing methods, and its superiority is further verified by its application to the PBC data.
文章引用：卢文暄, 黄彬, 沈皓明. 基于LsoCV准则的退出型缺失纵向数据模型平均估计[J]. 应用数学进展, 2026, 15(5): 1-9. https://doi.org/10.12677/aam.2026.155202

参考文献

[1] Liang, K. and Zeger, S.L. (1986) Longitudinal Data Analysis Using Generalized Linear Models. Biometrika, 73, 13-22. [Google Scholar] [CrossRef] 
[2] Pan, W. (2001) Akaike’s Information Criterion in Generalized Estimating Equations. Biometrics, 57, 120-125. [Google Scholar] [CrossRef] [PubMed]
[3] Gao, Y., Zhang, X., Wang, S. and Zou, G. (2016) Model Averaging Based on Leave-Subject-Out Cross-Validation. Journal of Econometrics, 192, 139-151. [Google Scholar] [CrossRef] 
[4] Zhao, Z. and Zou, G. (2020) Average Estimation of Semiparametric Models for High-Dimensional Longitudinal Data. Journal of Systems Science and Complexity, 33, 2013-2047. [Google Scholar] [CrossRef] 
[5] Hu, G., Cheng, W. and Zeng, J. (2019) Focused Information Criterion and Model Averaging for Varying-Coefficient Partially Linear Models with Longitudinal Data. Communications in Statistics—Simulation and Computation, 50, 2399-2417. [Google Scholar] [CrossRef] 
[6] Li, N., Fei, Y. and Zhang, X. (2024) Partial Linear Model Averaging Prediction for Longitudinal Data. Journal of Systems Science and Complexity, 37, 863-885. [Google Scholar] [CrossRef] 
[7] Jiang, B., Lv, J., Li, J. and Cheng, M. (2024) Robust Model Averaging Prediction of Longitudinal Response with Ultrahigh-Dimensional Covariates. Journal of the Royal Statistical Society Series B: Statistical Methodology, 87, 337-361. [Google Scholar] [CrossRef] 
[8] Yu, D., Zhang, X. and Liang, H. (2025) Unified Optimal Model Averaging with a General Loss Function Based on Cross-Validation. Journal of the American Statistical Association, 120, 2697-2708. [Google Scholar] [CrossRef] 
[9] Robins, J.M., Rotnitzky, A. and Zhao, L.P. (1995) Analysis of Semiparametric Regression Models for Repeated Outcomes in the Presence of Missing Data. Journal of the American Statistical Association, 90, 106-121. [Google Scholar] [CrossRef] 
[10] Platt, R.W., Brookhart, M.A., Cole, S.R., Westreich, D. and Schisterman, E.F. (2013) An Information Criterion for Marginal Structural Models. Statistics in Medicine, 32, 1383-1393. [Google Scholar] [CrossRef] [PubMed]
[11] Gosho, M. (2016) Model Selection in the Weighted Generalized Estimating Equations for Longitudinal Data with Dropout. Biometrical Journal, 58, 570-587. [Google Scholar] [CrossRef] [PubMed]
[12] Shen, C.W. and Chen, Y.H. (2012) Model Selection for Generalized Estimating Equations Accommodating Dropout Missingness. Biometrics, 68, 1046-1054. [Google Scholar] [CrossRef] [PubMed]
[13] Zhang, X. and Liu, C. (2023) Model Averaging Prediction by k-Fold Cross-Validation. Journal of Econometrics, 235, 280-301. [Google Scholar] [CrossRef] 
[14] Bo, X. and Zhang, W. (2023) Subgroup Analysis for Longitudinal Data via Semiparametric Additive Mixed Effects Model. Journal of Systems Science and Complexity, 36, 2155-2185. [Google Scholar] [CrossRef] 

为你推荐