Modeling of random effects covariance matrix in marginalized random effects models

다국어 초록 (Multilingual Abstract)

Marginalized random effects models (MREMs) are often used to analyze longitudinal categorical data. The models permit direct estimation of marginal mean parameters and specify the serial correlation of longitudinal categorical data via the random effects. However, it is not easy to estimate the random effects covariance matrix in the MREMs because the matrix is high-dimensional and must be positive-definite. To solve these restrictions, we introduce two modeling approaches of the random effects covariance matrix: partial autocorrelation and the modied Cholesky decomposition. These proposed methods are illustrated with the real data from Korean genomic epidemiology study.

참고문헌 (Reference)

1 최나연, "한국복지패널 자료를 이용한 아동기 공격성에 대한 경시적 자료 분석" 한국데이터정보과학회 25 (25): 1439-1447, 2014

2 전주영, "주변화 변량효과모형의 조사 및 고찰" 한국데이터정보과학회 25 (25): 1263-1272, 2014

3 Pan, J., "On modelling mean-covariance structure in longitudinal studies" 90 : 239-244, 2003

4 Lee, K., "Modelling the random e ects covariance matrix for generalized linear mixed models" 56 : 1545-1551, 2012

5 Daniels, M. J., "Modelling covariance matrices via partial autocorrelations" 100 : 2352-2363, 2009

6 Pan, J., "Modelling conditional covariance in the linear mixed model" 7 : 49-71, 2007

7 Daniels, M. J., "Modeling repeated count data subject to informative dropout" 22 : 1631-1647, 2003

8 Heagerty, P. J., "Misspeci ed maximum likelihood estimates and generalised linear mixed models" 88 : 973-985, 2001

9 Wannamethee, S. G., "Metabolic syndrome vs Framingham risk score for prediction of coronary heart disease, stroke, and type 2 diabetes mellitus" 295 : 819-821, 2006

10 Pourahmadi, M., "Maximum likelihood estimation of generalised linear models for multivariate normal covariance matrix" 87 : 425-435, 2000

11 Heagerty, P. J., "Marginally speci ed logistic-normal models for longitudinal binary data" 55 : 688-698, 1999

12 Heagerty, P. J., "Marginalized transition models and likelihood inference for longitudinal categorical data" 58 : 342-351, 2002

13 Lee, K., "Marginalized random e ects models for multivariate longi-tudinal binary data" 28 : 1287-1300, 2009

14 Lee, K., "Marginalized models for longitudinal ordinal data with application to quality of life studies" 27 : 4359-4380, 2008

15 Lee, K., "Longitudinal nominal data analysis using marginalized models" 54 : 208-218, 2010

16 Lee, K., "Likelihood-based approach for analysis of longitudinal nominal data using marginalized random e ects models" 38 : 1577-1590, 2011

17 Pourahmadi, M., "Joint mean-covariance models with applications to longitudinal data : unconstrained parameterisation" 86 : 677-690, 1999

18 Joe, H., "Generating random correlation matrices based on partial correlations" 97 : 2177-2189, 2006

19 Lee, K., "Flexible marginalized models for bivariate longitudinal ordinal data" 14 : 462-476, 2013

20 Agresti, A., "Categorical Data Analysis" Wiley and Sons 2002

21 Wang, Y., "Bayesian modeling of the dependence in longitudinal data via partial autocorrelations and marginal variances" 116 : 130-140, 2013

22 Daniels, M. J., "Bayesian analysis of covariance matrices and dynamic models for longitudinal data" 89 : 553-566, 2002

23 Breslow, N. E., "Approximate inference in generalized linear mixed models" 88 : 125-134, 1993

24 Fitzmaurice, G. M., "A likelihood-based method for analysing longitudinal binary response" 80 : 141-151, 1993