State‐space models for multivariate longitudinal data of mixed types
- 1 September 1996
- journal article
- Published by Wiley in Canadian Journal of Statistics
- Vol. 24 (3) , 385-402
Abstract
We propose a class of state‐space models for multivariate longitudinal data where the components of the response vector may have different distributions. The approach is based on the class of Tweedie exponential dispersion models, which accommodates a wide variety of discrete, continuous and mixed data. The latent process is assumed to be a Markov process, and the observations are conditionally independent given the latent process, over time as well as over the components of the response vector. This provides a fully parametric alternative to the quasilikelihood approach of Liang and Zeger. We estimate the regression parameters for time‐varying covariates entering either via the observation model or via the latent process, based on an estimating equation derived from the Kalman smoother. We also consider analysis of residuals from both the observation model and the latent process.Keywords
This publication has 15 references indexed in Scilit:
- A LONGITUDINAL STUDY OF EMERGENCY ROOM VISITS AND AIR POLLUTION FOR PRINCE GEORGE, BRITISH COLUMBIAStatistics in Medicine, 1996
- The simulation smoother for time series modelsBiometrika, 1995
- Monte Carlo EM Estimation for Time Series Models Involving CountsJournal of the American Statistical Association, 1995
- Partial non-Gaussian state spaceBiometrika, 1994
- On kalman filtering, posterior mode estimation and fisher scoring in dynamic exponential family regressionMetrika, 1991
- The Diffuse Kalman FilterThe Annals of Statistics, 1991
- Smoothing and Interpolation with the State-Space ModelJournal of the American Statistical Association, 1989
- A regression model for time series of countsBiometrika, 1988
- Longitudinal data analysis using generalized linear modelsBiometrika, 1986
- APPROXIMATE FILTERING OF PARAMETER DRIVEN PROCESSESJournal of Time Series Analysis, 1982