Award Date
1-1-2005
Degree Type
Thesis
Degree Name
Master of Science (MS)
Department
Mathematical Sciences
First Committee Member
Ashok K. Singh
Number of Pages
48
Abstract
Environmental engineers and scientists often encounter trace level concentrations of contaminants that fall below the detection limit (DL) are reported as 'less than DL'. The common method of dealing with non-detects in a multivariate sample is the substitution method in which each observation 'less than DL' is replaced by a suitable value (0, DL/2 or DL) with DL/2 being the recommended method; In this thesis, the applicability of Kaplan-Meier method, which was developed for estimating the survival function in the presence of right censored data, is investigated. Some simulated examples are presented.
Keywords
Covariance; Detects; Estimation; Matrix; Presence
Controlled Subject
Statistics
File Format
File Size
1546.24 KB
Degree Grantor
University of Nevada, Las Vegas
Language
English
Permissions
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 digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.
Repository Citation
Saravanan, Shanmugapriya, "Estimation of the covariance matrix in presence of non-detects" (2005). UNLV Retrospective Theses & Dissertations. 1906.
http://dx.doi.org/10.25669/dk8b-cl75
Rights
IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/
COinS