Abstract
We consider the least squares and the Gaussian maximum likelihood estimators in the regression model with stochastic explanatory variables and autocorrelated errors, possibly nonnormal, in the situation where data contain irregular observations or missing values. We establish the weak consistency and asymptotic normality of the estimators. We compare the efficiency of the least squares estimator of the regression parameter to that of the maximum likelihood estimator for a special case of the model.
Original language | English |
---|---|
Pages (from-to) | 3567-3580 |
Number of pages | 14 |
Journal | Communications in Statistics - Theory and Methods |
Volume | 23 |
Issue number | 12 |
DOIs | |
State | Published - 1 Jan 1994 |
Bibliographical note
Funding Information:The research of the first author was supported by a Grant from Korea Science and Engineering Foundation, and the research of the second author was supported in part by a Grant from the Arts and Sciences Research Fund at Oklahoma State University.
Keywords
- asymptotic normality
- autocorrelated errors
- consistency
- incomplete data
- lead squares estimator
- maximum lilcelihood estimator
- Regression