论文部分内容阅读
针对加速寿命试验中经常遇到完全数据、定数截尾数据和定时截尾数据混合的情况,提出一种多元混合数据回归分析方法,建立了多元混合回归模型,给出回归系数和标准差的最佳无偏估计,以及百分位值的点估计和置信限估计.该方法不但适用于正态分布,而且还适用于Weibull分布、极值分布等其他各种位置-尺度分布,从而将传统只适用于完全数据的多元回归分析推广到完全数据和截尾数据混合的情况.与传统方法相比,该方法具有信息量大、精度高的优点.
Aiming at the mixed data of complete data, censored data and time-censored data often encountered in accelerated life test, a multivariate mixed data regression analysis method is proposed and a multivariate mixed regression model is established. The regression coefficient and standard deviation Good unbiased estimation, and the estimation of point estimates and confidence limits of percentiles.It is not only suitable for normal distribution, but also for various other location-scale distributions such as Weibull distribution and extreme value distribution, so that the traditional It is suitable for the multiple regression analysis of complete data extended to the case of complete data and censored data mixing.Compared with the traditional method, this method has the advantages of large amount of information and high precision.