Master of Science (MS)
First Committee Member
Number of Pages
This paper is concerned with the Bayesian approach to estimate the mean when encountered with left-censored data sets. Considering the joint non-informative prior, we derived the posterior probability density function of the mean of left-censored data. However, this density function is not recognizable and we can not analytically integrate it to obtain the normalizing constant. In other words, we can not compute analytically the posterior pdf or posterior moments. Numerical integration involving the adaptive Simpson quadrature rule was used in Mat-lab to obtain the posterior mean and the upper credible limit (UCL). Several numerical examples are given which illustrate the practical application of these results.
Bayesian; Detects; Estimation; Mean; Normal; Presence
University of Nevada, Las Vegas
If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to firstname.lastname@example.org and include clear identification of the work, preferably with URL.
Khago, Ahmed, "Bayesian estimation of the normal mean in the presence of non-detects" (2005). UNLV Retrospective Theses & Dissertations. 1775.
IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/