A note on the efficiency of the cochrane-orcutt estimator of the ar(1) regression model |
| |
| Affiliation: | 1. Department of Biosciences, Durham University, Durham, U.K.;2. College of Life and Environmental Sciences, University of Exeter, Exeter, U.K.;3. Sea Mammal Research Unit, St Andrews University, St Andrews, Fife, U.K.;1. Department of Civil Engineering, Indian Institute of Technology Madras, Chennai, India;2. Department of Agricultural and Biological Engineering, Purdue University, West Lafayette, IN, USA;3. Department of Earth, Atmospheric and Planetary Sciences, Purdue University, West Lafayette, IN, USA |
| |
| Abstract: | This paper shows that the Cochrane-Orcutt transformation which deletes the initial observation of the AR(1) regression model with known autocorrelation is strictly less efficient than a weighted generalized least squares estimator which gives the initial observation less weight than the true model requires, and may be more or less efficient than an estimator which gives the initial observation more weight than required. It also shows that the estimator based on the Cochrane-Orcutt transformation is strictly less efficient than one based on the Prais-Winsten transformation, if the AR(1) process has a finite past. These results give further support to the conclusion that, whenever possible, the estimator based on Prais-Winsten transformation should be used. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
