Linear programming algorithms for detecting separated data in binary logistic regression models

Thesis

This thesis is a study of the detection of separation among the sample points in binary logistic regression models. We propose a new algorithm for detecting separation and demonstrate empirically that it can be computed fast enough to be used routinely as part of the fitting process for logistic regression models. The parameter estimates of a binary logistic regression model fit using the method of maximum likelihood sometimes do not converge to finite values. This phenomenon (also known as ...

Expand abstract

Authors: Konis, K

• Publication date: 2007
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: binary data; linear programming; infinite parameters; monotone likelihood; logistic regression
• Subjects: Statistics (see also social sciences); Computationally-intensive statistics