Measuring overlap in binary regression.

DOI10.1016/S0167-9473(00)00063-3MaRDI QIDQ5941426zbMATH OpenFDO

Authors Andreas Christmann, Peter Rousseeuw

Publication date 20 August 2001

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0167-9473(00)00063-3

zbMATH Keywords

Linear discriminant analysisLogistic regressionOutliersOverlapProbit regressionRegression depthSeparation

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Generalized linear models (logistic models) (62J12) Linear inference, regression (62J99)

Review text

We show that the recent notion of regression depth can be used as a data-analytic tool to measure the amount of separation between successes and failures in the binary response framework. Extending this algorithm allows us to compute the overlap in data sets which are commonly fitted by logistic or probit regression models. The overlap is the number of observations that would need to be removed to obtain complete or quasi-complete separation, i.e., the situation where the regression parameters are no longer identifiable and the maximum likelihood estimate does not exist. It turns out that the overlap is often quite small. The results are equally useful in linear discriminant analysis.

Recommendations

• On the existence of maximum likelihood estimates in logistic regression models
• scientific article; zbMATH DE number 4096600
• Robustness against separation and outliers in logistic regression
• Separation among distributions related by linear regression
• On the existence of maximum likelihood estimates for weighted logistic regression

Cites work

• A note on A. Albert and J. A. Anderson's conditions for the existence of maximum likelihood estimates in logistic regression models
• Best Subsets Logistic Regression
• Conditionally Unbiased Bounded-Influence Estimation in General Regression Models, with Applications to Generalized Linear Models
• scientific article; zbMATH DE number 45786 (Why is no real title available?)
• scientific article; zbMATH DE number 472968 (Why is no real title available?)
• Least Median of Squares Regression
• Least median of weighted squares in logistic regression with large strata
• Logistic regression diagnostics
• On the existence of maximum likelihood estimates in logistic regression models
• Regression Depth
• Robust trainability of single neurons
• THE ESTIMATION FROM INDIVIDUAL RECORDS OF THE RELATIONSHIP BETWEEN DOSE AND QUANTAL RESPONSE

Cited in

(28)

• Distribution-free tests for polynomial regression based on simplicial depth
• Fast nonparametric classification based on data depth
• Breakdown points of trimmed likelihood estimators and related estimators in generalized linear models.
• Default priors for the intercept parameter in logistic regressions
• On data depth and distribution-free discriminant analysis using separating surfaces
• Robust Wald-type methods for testing equality between two populations regression parameters: a comparative study under the logistic model
• The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
• The existence of maximum likelihood estimate in high-dimensional binary response generalized linear models
• Point separation in logistic regression on Hilbert space-valued variables
• Multivariate and functional classification using depth and distance
• Classifying real-world data with the DD-procedure
• On a strategy to develop robust and simple tariffs from motor vehicle insurance data
• Classification based on the support vector machine, regression depth, and discriminant analysis
• Logistic discrimination using robust estimators: An influence function approach
• An Extended Projection Data Depth and Its Applications to Discrimination
• APPLIED REGRESSION ANALYSIS BIBLIOGRAPHY UPDATE 2000–2001
• DD-classifier: nonparametric classification procedure based on DD-plot
• Separation among distributions related by linear regression
• A solution to separation for clustered binary data
• On Maximum Depth and Related Classifiers
• Depth estimators and tests based on the likelihood principle with application to regression
• On rank distribution classifiers for high-dimensional data
• Detecting and diagnosing prior and likelihood sensitivity with power-scaling
• A goodness-of-fit measure for logistic regression under separation
• Classification based on depth transvariations
• Robustness against separation and outliers in logistic regression
• Implementing the Bianco and Yohai estimator for logistic regression
• Response shrinkage estimators in binary regression

This page was built for publication: Measuring overlap in binary regression.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5941426)