廣義線性混合模型（generalized linear mixed models; GLMM）不僅可用來描述縱向資料或群聚資料的相關性，亦可用來描述當樣本變異數不如所假設模型所預期時的現象。廣義線性混合模型因為允許預測子的效應可以是隨機的，於是增加了參數估計的困難性。如果要求得廣義線性混合模型的最大概似估計量通常需要高維度的積分。 Breslow and Clayton (1993) 提出了近似的方法以避免高維度的積分。Jiang and Zhang (2001) 可找到參數的一致估計量，可是並不是有效估計（efficient estimation）。在這篇論文中，我們提出一個新的估計方法。我們把在預測子的隨機效應視為遺失數據，再利用多重插補法（multiple imputation）補入一個合理的值。在多重插補法中，我們以Jiang and Zhang (2001)的估計量作為初始估計。之後，我們就可利用完整數據的估計方法來估計參數。我們做了兩個模擬研究並將此方法應用到一個有關種子發芽的資料。

Booth, J. G. & Hobert, J. P. (1999). Maximizing generalized linear mixed model likelihoods with an automated Monte Carlo EM algorithm. J. R. Statist. Soc. B 61, 265-85.
Breslow, N. E. & Clayton, D. G. (1993). Approximate inference in generalized linear mixed models. J. Am. Statist. Assoc. 88, 9-25.
Crowder, M. J. (1978). Beta-binomial anova for proportions. Appl. Statist. 27, 34-37.
Griffiths, D. A. (1973). Maximum likelihood estimation for the beta-binomial distribution and an application to the household distribution of the total number of cases of a disease. Biometrics 29, 637-48.
Rubin, D. B. (1978). Multiple imputation in sample surveys--a phenomenological Bayesian approach to nonresponse. In Proc. Survey Res. Meth. Sect., Am. Statist. Assoc. pp. 20-34. Washington, DC: American Statistical Association.
Rubin, D. B. (1987). Multiple imputation for nonresponse in surveys. New York: Wiley.
Jiang, J. & Zhang, W. (2001). Robust estimation in generalised linear mixed models. Biometrika 88}, 753-65.
Natarajan, R. & Kass, R.E. (2000). Reference bayesian methods for generalized linear mixed models. J. Am. Statist. Assoc. 95, 227-37.
Wang, N. & Robins, J. M. (1998). Large-sample theory for parametric multiple imputation procedures. Biometrika 85, 935-48.
Zeger, S. L., Karim, M. R. (1991). Generalized linear models with random effects: A Gibbs sampling approach. J. Am. Statist. Assoc. 86, 79-86.