Estimation in regression models with stationary, dependent errors
- 1 January 1981
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 10 (24) , 2563-2580
- https://doi.org/10.1080/03610928108828210
Abstract
Often the unknown covariance structure of a stationary, dependent, Gaussian error sequence can be simply parametrised. The error sequence can either be directly observed or observed only through a random sequence containing a deterministic regression model. The method of scoring is used here, in conjunction with recursive estimation techniques, to effect the maximum likelihood estimation of the covariance parameters. Sequences of recursive residuals, useful in model diagnostics and data analysis, are obtained in the estimation procedure.Keywords
This publication has 11 references indexed in Scilit:
- Recursive Estimation of the General Linear Model with Dependent ErrorsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1979
- Stochastic Growth Curve AnalysisPublished by JSTOR ,1979
- Techniques for Testing the Constancy of Regression Relationships Over TimeJournal of the Royal Statistical Society Series B: Statistical Methodology, 1975
- Linear Statistical Inference and its ApplicationsPublished by Wiley ,1973
- Multiple Time SeriesWiley Series in Probability and Statistics, 1970
- Computer Experiments with Fractional Gaussian Noises: Part 3, Mathematical AppendixWater Resources Research, 1969
- Fractional Brownian Motions, Fractional Noises and ApplicationsSIAM Review, 1968
- An Algorithm for the Inversion of Finite Toeplitz MatricesJournal of the Society for Industrial and Applied Mathematics, 1964
- A Method of Maximum-Likelihood EstimationJournal of the Royal Statistical Society Series B: Statistical Methodology, 1961
- SOME THEOREMS IN LEAST SQUARESBiometrika, 1950