Masters Theses
Abstract
"A comparison is made between the estimates of the parameters in a gamma distribution obtained by the method of moments with those obtained by a numerical approximation to the maximum likelihood estimates. The estimates obtained by the numerical approximation had a smaller mean squared error from the true value than the estimates obtained by the method of moments. Modifications to tests of fit are made in order to develop methods to select a distribution from a set of possible distributions for a population with an unknown distribution. These selection methods are compared in their ability to make correct selections. Although the likelihood ratio method was not shown to be significantly better than the other methods, it is recommended for use in selecting a distribution from a set"--Abstract, page ii.
Advisor(s)
Lee, Ralph E., 1921-2010
Committee Member(s)
Sauer, Harry J., Jr., 1935-2008
Bain, Lee J., 1939-
Antle, Charles E.
Department(s)
Mathematics and Statistics
Degree Name
M.S. in Applied Mathematics
Publisher
University of Missouri at Rolla
Publication Date
1965
Pagination
iv, 23 pages
Note about bibliography
Includes bibliographical references (pages 44-47).
Rights
© 1965 Howard Lyndal Colburn, All rights reserved.
Document Type
Thesis - Open Access
File Type
text
Language
English
Subject Headings
Probabilities -- Mathematical modelsMoments method (Statistics)Numerical analysis
Thesis Number
T 1784
Print OCLC #
5968871
Electronic OCLC #
841411474
Recommended Citation
Colburn, Howard Lyndal, "Comparison of methods to select a probability model" (1965). Masters Theses. 7030.
https://scholarsmine.mst.edu/masters_theses/7030