An evaluation of a modified binary search procedure for use with the Bruceton method in sensitivity testing
Loading...
Authors
Hicks, Donald Lee
Subjects
sensitivity testing
Bruceton method
maximum likelihood estimates
computer simulation
Bruceton method
maximum likelihood estimates
computer simulation
Advisors
Tysver, J.B.
Date of Issue
1970-09
Date
September 1970
Publisher
Monterey, CA: Naval Postgraduate School
Language
Abstract
Two methods of obtaining sensitivity data were simulated on an electronic computer for the purpose of comparing the accuracy of the estimates of the parameters of an underlying cumulative normal response function. The first method simulated the standard Bruceton procedure while the second used a modified binary search routine with a portion of the sample in order to obtain maximum likelihood estimates of the input parameters for use in a follow-on Bruceton test. The results showed both methods to be effective in estimating the mean but with slightly more variability in the estimates obtained by the second procedure. Both methods underestimated the standard deviation - again with more variability in the estimates obtained by the second procedure. When the prior parameter estimates were unknown and the applicable stimulus level bounded, the second method yielded estimates favorably comparable to those expected from the Bruceton procedure with suitable prior input estimates.
Type
Thesis
Description
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
Funding
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.