Maximum likelihood estimation under misspecified lognormal and Weibull distributions

被引:15
作者
Pascual, FG [1 ]
机构
[1] Washington State Univ, Dept Math, Pullman, WA 99164 USA
[2] Washington State Univ, Dept Stat, Pullman, WA 99164 USA
关键词
asymptotic bias; asymptotic mean square error; distribution misspecification; quasi-maximum likelihood estimators; Type I and II censoring;
D O I
10.1081/SAC-200068380
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
This article provides expressions for computing the asymptotic distribution of maximum likelihood estimators of lognormal and Weibull parameters when the distribution is misspecified and data are Type I or II censored. The results can be used to derive the asymptotic normal distribution of observed bias in estimation of functions of model parameters such as quantiles. The methods are applied to a Type I censored dataset on locomotive controls. The results are used to derive test plans that are bias-robust for estimating quantiles. Values of the proportions failing that minimize asymptotic mean square error and absolute asymptotic bias are tabulated.
引用
收藏
页码:503 / 524
页数:22
相关论文
共 11 条
[1]  
BAI J, 1992, J STAT COMPUT SIM, V42, P151, DOI DOI 10.1080/00949659208811418
[2]   ALGORITHM 573 - NL2SOL - AN ADAPTIVE NON-LINEAR LEAST-SQUARES ALGORITHM [E4] [J].
DENNIS, JE ;
GAY, DM ;
WELSCH, RE .
ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 1981, 7 (03) :369-383
[3]  
ESCOBAR LA, 1994, J R STAT SOC C-APPL, V43, P533
[4]  
ESCOBAR LA, 2000, 200003 IOW STAT U DE
[5]  
Johnson NL, 1994, WILEY SERIES PROBABI, V1
[6]  
Lawless J., 2003, Statistical Models and Methods for Lifetime Data
[7]  
Meeker W., 1998, STAT METHODS RELIABI
[8]  
NELSON W, 1977, 76CRD259 TIS GEN EL
[9]  
Nelson W., 1982, Applied Life Data Analysis, DOI [10.1002/0471725234, DOI 10.1002/0471725234]
[10]  
Nelson WB., 1990, ACCELERATED TESTING