Panning for gold: Enhancing the precision of sensitivity test data

Sensitivity tests apply a range of stimulus values to experimental subjects and record binary responses in order to estimate the distribution of threshold values in the subject population, where thresholds delineate responses from nonresponses. In many applications, such as explosives engineering, i...

Full description

Saved in:
Bibliographic Details
Published in:Statistical analysis and data mining 2017-06, Vol.10 (3), p.166-181
Main Authors: Collins, David H., Weaver, Brian P., Hamada, Michael S.
Format: Article
Language:English
Subjects:
binary regression
data mining
Gold
logistic
MATHEMATICS AND COMPUTING
penalized maximum likelihood
precision
probit
Sensitivity
sensitivity testing analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sensitivity tests apply a range of stimulus values to experimental subjects and record binary responses in order to estimate the distribution of threshold values in the subject population, where thresholds delineate responses from nonresponses. In many applications, such as explosives engineering, individual tests are expensive and are conducted in small runs. Scarcity of data results in nonexistence of estimates, or estimates with low precision. We discuss various methods, such as combining test runs, covariate analysis, and penalized maximum likelihood, for enhancing precision and “mining more gold” from expensive test results.
ISSN:1932-1864
1932-1872
DOI:10.1002/sam.11345