Next Article in Journal
Urban Morphological Change Analysis of Dhaka City, Bangladesh, Using Space Syntax
Previous Article in Journal
Use of the NASA Giovanni Data System for Geospatial Public Health Research: Example of Weather-Influenza Connection
Open AccessArticle

Targeting: Logistic Regression, Special Cases and Extensions

Institute of Geophysics and Geoinformatics, Technische Universität Bergakademie Freiberg, Gustav-Zeuner-Str. 12, Freiberg 09596, Germany
ISPRS Int. J. Geo-Inf. 2014, 3(4), 1387-1411; https://doi.org/10.3390/ijgi3041387
Received: 10 October 2014 / Revised: 25 November 2014 / Accepted: 25 November 2014 / Published: 11 December 2014
Logistic regression is a classical linear model for logit-transformed conditional probabilities of a binary target variable. It recovers the true conditional probabilities if the joint distribution of predictors and the target is of log-linear form. Weights-of-evidence is an ordinary logistic regression with parameters equal to the differences of the weights of evidence if all predictor variables are discrete and conditionally independent given the target variable. The hypothesis of conditional independence can be tested in terms of log-linear models. If the assumption of conditional independence is violated, the application of weights-of-evidence does not only corrupt the predicted conditional probabilities, but also their rank transform. Logistic regression models, including the interaction terms, can account for the lack of conditional independence, appropriate interaction terms compensate exactly for violations of conditional independence. Multilayer artificial neural nets may be seen as nested regression-like models, with some sigmoidal activation function. Most often, the logistic function is used as the activation function. If the net topology, i.e., its control, is sufficiently versatile to mimic interaction terms, artificial neural nets are able to account for violations of conditional independence and yield very similar results. Weights-of-evidence cannot reasonably include interaction terms; subsequent modifications of the weights, as often suggested, cannot emulate the effect of interaction terms. View Full-Text
Keywords: prospectivity modeling; potential modeling; conditional independence; naive Bayes model; Bayes factors; weights of evidence; artificial neural nets; imbalanced datasets; balancing prospectivity modeling; potential modeling; conditional independence; naive Bayes model; Bayes factors; weights of evidence; artificial neural nets; imbalanced datasets; balancing
MDPI and ACS Style

Schaeben, H. Targeting: Logistic Regression, Special Cases and Extensions. ISPRS Int. J. Geo-Inf. 2014, 3, 1387-1411.

Show more citation formats Show less citations formats

Article Access Map

1
Only visits after 24 November 2015 are recorded.
Back to TopTop