摘要
提出定时截尾数据回归分析方法,建立定时截尾数据回归方程,给出回归系数和标准差的最佳无偏整体估计、百分位值的点估计及其置信限估计.详细讨论了工程中常见的极值分布、Weibull分布、正态分布以及一般位置-尺度分布场合下定时截尾数据的回归分析问题.该方法可以充分利用截尾时刻的试验信息,并将各个状态下的定时截尾数据作为一个整体进行统计分析,具有信息量大、精度高的特点,从而可以在试验时间、经费等有限的情况下对产品进行高精度的寿命预测和可靠性评估.
Regression analysis method for type-Ⅰ censored data was presented. The regression equation for type-Ⅰ censored data was established. The best unbiased integral estimators of the regression coefficients and the standard deviation, the point estimators and confidence intervals of percentiles were given. The regression analysis methods for type-Ⅰ censored data from extreme distribution, Weibull distribution, normal distribution and location-scale distribution were discussed in detail. As the experimental information at the censoring time and the cross information among test data in different states were fully exploited, the presented method could reach a high precision. The method provides a feasible and effective approach to life prediction and reliability estimation of products when the test time or expense are limited.
出处
《航空动力学报》
EI
CAS
CSCD
北大核心
2010年第1期142-147,共6页
Journal of Aerospace Power
基金
国家自然科学基金(10472006)
北京市教育委员会共建项目(XK100060418)
关键词
定时截尾数据
回归分析
极值分布
WEIBULL分布
正态分布
位置一尺度分布
可靠性评估
type-Ⅰ censored data
regression analysis
extreme distribution
Weibull distribution
normal distribution
location-scale distribution
reliability estimation
