Fixed Accuracy Estimation of an Autoregressive Parameter
Lai, T. L. ; Siegmund, D.
Ann. Statist., Tome 11 (1983) no. 1, p. 478-485 / Harvested from Project Euclid
For a first order non-explosive autoregressive process with unknown parameter $\beta \in \lbrack -1, 1 \rbrack$, it is shown that if data are collected according to a particular stopping rule, the least squares estimator of $\beta$ is asymptotically normally distributed uniformly in $\beta$. In the case of normal residuals, the stopping rule may be interpreted as sampling until the observed Fisher information reaches a preassigned level. The situation is contrasted with the fixed sample size case, where the estimator has a non-normal unconditional limiting distribution when $|\beta| = 1$.
Publié le : 1983-06-14
Classification:  Stopping rule,  fixed width confidence interval,  uniform asymptotic normality,  62L10
@article{1176346154,
     author = {Lai, T. L. and Siegmund, D.},
     title = {Fixed Accuracy Estimation of an Autoregressive Parameter},
     journal = {Ann. Statist.},
     volume = {11},
     number = {1},
     year = {1983},
     pages = { 478-485},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176346154}
}
Lai, T. L.; Siegmund, D. Fixed Accuracy Estimation of an Autoregressive Parameter. Ann. Statist., Tome 11 (1983) no. 1, pp.  478-485. http://gdmltest.u-ga.fr/item/1176346154/