Abstract
Consider a collection of individual linear regression models, in which each individual parameter vector is independently drawn from a common multivariate normal distribution and is fixed over successive observations on that individual. Maximum likelihood estimators of the mean and dispersion of the parameters and of the disturbance variance are derived. These estimators yield empirical Bayes estimators of the individual parameter veotors. The properties of the estimators are exhibited in the case where the parameter dispersion is known.
Keywords
MathematicsEstimatorStatisticsDispersion (optics)Linear regressionBayesian multivariate linear regressionMultivariate statisticsM-estimatorVariance (accounting)Regression analysisMultivariate normal distribution
Affiliated Institutions
Related Publications
Regression Analysis of Multivariate Incomplete Failure Time Data by Modeling Marginal Distributions
Abstract Many survival studies record the times to two or more distinct failures on each subject. The failures may be events of different natures or may be repetitions of the sa...
Estimation of Finite Mixture Distributions Through Bayesian Sampling
SUMMARY A formal Bayesian analysis of a mixture model usually leads to intractable calculations, since the posterior distribution takes into account all the partitions of the sa...
Longitudinal Data Analysis Using Generalized Linear Models
This paper proposes an extension of generalized linear models to the analysis of longitudinal data. We introduce a class of estimating equations that give consistent estimates o...
Longitudinal data analysis using generalized linear models
This paper proposes an extension of generalized linear models to the analysis of longitudinal data. We introduce a class of estimating equations that give consistent estimates o...
Estimation of Parameters in the Multivariate Normal Distribution with Missing Observations
In this paper a method is developed for estimating the parameters in the multivariate normal distribution in which the missing observavations are not restricted to follow certai...
Publication Info
- Year
- 1973
- Type
- article
- Volume
- 60
- Issue
- 1
- Pages
- 65-72
- Citations
- 82
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
82
OpenAlex
Cite This
Barr Rosenberg
(1973).
Linear regression with randomly dispersed parameters.
Biometrika
, 60
(1)
, 65-72.
https://doi.org/10.1093/biomet/60.1.65
Identifiers
- DOI
- 10.1093/biomet/60.1.65