BOOTSTRAP TEST OF SIGNIFICANCE AND SEQUENTIAL BOOTSTRAP ESTIMATION FOR UNSTABLE 1ST ORDER AUTOREGRESSIVE PROCESSES

被引：48

作者：

BASAWA, IV ^{[1
]}

MALLIK, AK ^{[1
]}

MCCORMICK, WP ^{[1
]}

REEVES, JH ^{[1
]}

TAYLOR, RL ^{[1
]}

机构：

[1] UNIV GEORGIA,DEPT STAT,ATHENS,GA 30602

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 1991年 / 20卷 / 03期

关键词：

AUTOREGRESSIVE PROCESSES; TEST OF CRITICALITY; SEQUENTIAL BOOTSTRAP; UNSTABLE PROCESSES;

D O I：

10.1080/03610929108830545

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

The asymptotic validity of the bootstrap for a test of criticality in a first order autoregressive, AR(1) process is established. To circumvent the asymptotic invalidity of the standard bootstrap least squares estimator for the unstable case, a sequential bootstrap procedure for the estimation of the parameter beta in the AR(1) model, X(t) = beta-X(t-1) + epsilon-t, is studied. The asymptotic validity of the sequential boostrap estimator is established for all \beta\ less-than-or-equal-to 1.

引用

页码：1015 / 1026

页数：12

共 17 条

[1] ON ASYMPTOTIC DISTRIBUTIONS OF ESTIMATES OF PARAMETERS OF STOCHASTIC DIFFERENCE-EQUATIONS [J].