FIXED-WIDTH INTERVAL ESTIMATION OF THE MINIMUM POINT OF A REGRESSION FUNCTION BASED ON THE KIEFER-WOLFOWITZ PROCEDURE

被引:0
|
作者
MECZARSKI, M [1 ]
机构
[1] CENT SCH PLANNING & STAT,INST ECONOMET,PL-02554 WARSAW,POLAND
关键词
KIEFER-WOLFOWITZ PROCEDURE; CENTRAL LIMIT THEOREM; SEQUENTIAL FIXED-WIDTH INTERVAL ESTIMATION; ASYMPTOTIC CONSISTENCY; ASYMPTOTIC EFFICIENCY; ADAPTIVE PROCEDURE;
D O I
10.1016/0378-3758(92)90160-T
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
A version of the central limit theorem for the Kiefer-Wolfowitz procedure is stated. One constructs an asymptotically consistent fixed-width confidence interval for the minimum of a regression function. It is shown that the first moment of the corresponding stopping rule is finite. Both the construction and properties of the estimates of unknown parameters and an adaptive version of the procedure are presented.
引用
收藏
页码:339 / 349
页数:11
相关论文
共 24 条