Joint mean-covariance models with applications to longitudinal data: unconstrained parameterisation

TLDR

The Cholesky decomposition of the inverse covariance matrix yields a unique unit lower triangular matrix and a diagonal matrix for each covariance matrix. The authors develop an unconstrained parameterisation of covariance matrices using covariates and introduce an extended generalized linear model for joint mean–covariance modelling that subsumes mean–variance heterogeneity, Gabriel’s antedependence, Dempster’s covariance selection, and graphical models. They employ the Cholesky decomposition to express covariance entries as unconstrained regression coefficients and prediction variances, derive the likelihood and maximum‑likelihood estimators under normality, and propose a graphical correlogram‑like method to identify parametric models for nonstationary covariances. The approach is applied to model nonstationary dependence structures and multivariate data, with performance illustrated on real datasets.

Abstract

We provide unconstrained parameterisation for and model a covariance using covariates. The Cholesky decomposition of the inverse of a covariance matrix is used to associate a unique unit lower triangular and a unique diagonal matrix with each covariance matrix. The entries of the lower triangular and the log of the diagonal matrix are unconstrained and have meaning as regression coefficients and prediction variances when regressing a measurement on its predecessors. An extended generalised linear model is introduced for joint modelling of the vectors of predictors for the mean and covariance subsuming the joint modelling strategy for mean and variance heterogeneity, Gabriel's antedependence models, Dempster's covariance selection models and the class of graphical models. The likelihood function and maximum likelihood estimators of the covariance and the mean parameters are studied when the observations are normally distributed. Applications to modelling nonstationary dependence structures and multivariate data are discussed and illustrated using real data. A graphical method, similar to that based on the correlogram in time series, is developed and used to identify parametric models for nonstationary covariances.