STATISTICAL UNCERTAINTIES IN ESTIMATION OF DISTRIBUTION PARAMETERS
This paper discusses the statistical uncertainties in estimation of the mean and the variance of a random variable at different sample sizes. The aim is to provide a practical way to deal with data insufficiency in reliability analysis of engineering structures. Firstly, two statistical uncertainty variates for mean and variance, respectively, are introduced. Then analytical formulae are primarily derived for the estimation of mean and variance for normal and log-normal distributions. After that, Monte-Carlo simulation is employed for the first time to analyze statistical uncertainties for polar I and Weibull distributions. At last, characteristics of statistical uncertainties in parameter estimation are summarized and some remarks are made. The results attained in this paper can meet the need of reliability analysis of engineering structures.
Ming-Xin Xu Cheng-Yong Yang Wai-Fah Chen
School of Civil Engineering and Architecture, Beijing Jiaotong University, Beijing 100044, P. R Chin Tunnel and Underground Engineering Research Center of Ministry of Education, Beijing Jiaotong Univer College of Engineering, University of Hawaii at Manoa, Honolulu HI 96822, USA
国际会议
长沙
英文
108-115
2007-11-19（万方平台首次上网日期，不代表论文的发表时间）