RecordNumber
66
Author
Takamitsu Sawa
Title of Article
The exact moments of the least squares estimator for the autoregressive model
Title Of Journal
Journal of Econometrics
PublishInfo
Elsevier
Publication Year
1978
Volum
8
Issue Number
2
Page
159-172
Notes
براي دانلود و مشاهده مقاله به قسمت لينكهاي مرتبط مراجعه نماييد
Abstract
Exact mean and variance of the least squares estimate of the stationary first-order autoregressive coefficient, i.e., β in yt=α+βxt+ut are evaluated algebraically as well as numerically. It turns out that the least squares estimate is seriously biased for the sample of two-digits sizes typically dealt with in econometrics if the mean of the process is unknown, i.e., if the equation has a non-zero intercept (α≠0). Kendall's approximation to the mean and Barlett's approximation to the variance are shown to be fairly good. Also, our numerical results confirm Orcutt and Winokur's (Econometrica, Vol. 37) based on Monte Carlo experiments.
URL
http://www.sciencedirect.com/science/article/pii/0304407678900258,/DL/Data Entry/DataEntryForm/EnterDocInfo.aspx,/DL/Data Entry/NewEdit/Documents/Math_English_Electronic_Articles_EditDoc_925.aspx