A new explanatory index for evaluating the binary logistic regression based on the sensitivity of the estimated model

We propose a new explanatory index for evaluating the binary logistic regression model based on the sensitivity of the estimated model. We previously formalized the idea of sensitivity and established the principles a statistic should comply with to be considered a sensitivity index. We apply the re...

Full description

Saved in:
Bibliographic Details
Published in:Statistics & probability letters 2017-01, Vol.120, p.135-140
Main Authors: Ramos, Héctor M., Ollero, Jorge, Suárez-Llorens, Alfonso
Format: Article
Language:English
Subjects:
Binary logistic regression
McFadden index
ROC curve
Sensitivity index
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:We propose a new explanatory index for evaluating the binary logistic regression model based on the sensitivity of the estimated model. We previously formalized the idea of sensitivity and established the principles a statistic should comply with to be considered a sensitivity index. We apply the results to a practical example and compare the results with those obtained utilizing other indices.
ISSN:0167-7152
1879-2103
DOI:10.1016/j.spl.2016.08.022