Abstract
Based on the generalized estimating equation approach, the authors propose a parsimonious mean-covariance model for longitudinal data with autoregressive and moving average error process, which not only unites the existing autoregressive Cholesky factor model and moving average Cholesky factor model but also provides a wide variety of structures of covariance matrix. The resulting estimators for the regression coefficients in both the mean and the covariance are shown to be consistent and asymptotically normally distributed under mild conditions. The authors demonstrate the effectiveness, parsimoniousness and desirable performance of the proposed approach by analyzing the CD4+ cell counts data set and conducting extensive simulations.
Similar content being viewed by others
References
Wang Y G and Carey V, Working correlation structure misspecification, estimation and covariate design: Implications for generalised estimating equations performance, Biometrika, 2003, 90: 29–41.
Diggle P J, Heagerty P, Liang K Y, et al., Analysis of Longitudinal Data, 2nd Edition, Oxford University Press, Oxford, 2002.
Laird N M and Ware J H, Random effects models for longitudinal data, Biometrics, 1982, 38: 963–974.
Liang K Y and Zeger S L, Longitudinal data analysis using generalized linear models, Biometrika, 1986, 73: 13–22.
Pourahmadi M, Joint mean-covariance models with applications to longitudinal data: Unconstrained parameterisation. Biometrika, 1999, 86: 677–690.
Pourahmadi M, Maximum likelihood estimation of generalised linear models for multivariate normal covariance matrix, Biometrika, 2000, 87: 425–435.
Zhang W and Leng C, A moving average cholesky factor model in covariance modeling for longitudinal data, Biometrika, 2012, 99: 141–150.
Wu W B and Pourahmadi M, Nonparametric estimation of large covariance matrices of longitudinal data, Biometrika, 2003, 90: 831–844.
Huang J Z, Liu L, and Liu N, Estimation of large covariance matrices of longitudinal data with basis function approximations, J. Comp. Graph. Statist., 2007, 16: 189–209.
Prentice R L and Zhao L P, Estimating equations for parameters in means and covariances of multivariate discrete and continuous responses, Biometrics, 1991, 47: 825–839.
Pourahmadi M, Cholesky decompositions and estimation of a covariance matrix: Orthogonality of variance-correlation parameters, Biometrika, 2007, 94: 1006–1013.
Pan J and Mackenzie G, Model selection for joint mean-covariance structures in longitudinal studies, Biometrika, 2003, 90: 239–244.
Leng C, Zhang W, and Pan J, Semiparametric mean-covariance regression analysis for longitudinal data, J. Am. Statist. Ass., 2010, 105: 181–193.
Maadooliat M, Pourahmadi M, and Huang J Z, Robust estimation of the correlation matrix of longitudinal data, Stat Comput, 2013, 23(1): 17–28.
Yao W and Li R, New local estimation procedure for a nonpararametric regression function for longitudinal data, J. Roy. Statist. Soc. Ser. B, 2013, 75: 123–138.
Zhang W, Leng C, and Tang C Y, A joint modelling approach for longitudinal studies, J. Roy. Statist. Soc. Ser. B, 2015, 77: 219–238.
Rochen J and Helms R W, Maximum likelihood estimation for incomplete repeated-measures experiments under an ARMA covariance structure, Biometrics, 1989, 45: 207–218.
Lee J C, Lin T I, Lee K J, et al., Bayesian analysis of Box-Cox transformed linear mixed models with ARMA (p, q) dependence, Journal of statistical Planning and Inference, 2005, 133: 435–451.
Wang W and Fan T, ECM-based maximum likelihood inference for multivariate linear mixed models with autoregressive errors, Comput. Statist. Data Anal., 2010, 54: 1328–1341.
Bai Y, Huang J, and Li R, Semiparametric longitudinal model with irregular time autoregressive error process, Stat. Sinica, 2015, 25: 507–527.
Lee K, Baek C, and Daniels M, ARMA Cholesky factor models for the covariance matrix of linear models, Computational Statistics and Data Analysis, 2017, 115: 267–280.
Lutkepohl H, New Introduction to Multiple Time Series Analysis, Springer, 2005.
Ye H and Pan J, Modelling covariance structures in generalized estimating equations for longitudinal data, Biometrika, 2006, 93: 927–941.
Zeger S L and Diggle P J, Semiparametric models for longitudinal data with application to CD4 cell numbers in HIV seroconverters, Biometrics, 1994, 50: 689–699.
McCullagh P, Quasi-likelihood functions, Ann. Statist., 1983, 11: 59–67.
Chiu T Y M, Leonard T, and Tsui K W, The matrix-logarithm covariance model, J. Am. Statist. Ass., 1996, 91: 198–210.
Author information
Authors and Affiliations
Corresponding author
Additional information
This work has been supported by the National Key Research and Development Plan under Grant No. 2016YFC0800100 and the National Science Foundation of China under Grant Nos. 11671374, 71771203, 71631006.
This paper was recommended for publication by Editor YU Zhangsheng.
Rights and permissions
About this article
Cite this article
Wang, J., Chen, Y. & Zhang, W. Parsimonious Mean-Covariance Modeling for Longitudinal Data with ARMA Errors. J Syst Sci Complex 32, 1675–1692 (2019). https://doi.org/10.1007/s11424-019-7354-6
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11424-019-7354-6