Estimation of Parametric and Semiparametric Logistic Regression Models Using Credit Scoring Data

by Magda M. M. Haggag .

Abstract: : A semiparametric generalized linear model known as a generalized partial linear model (GPLM) is estimated using the profile likelihood method. The Algorithms of the estimation process is derived and applied to credit scoring data which is a typical example for the application of GPLM with a binomially distributed response variable.

Key Words: : credit scoring, generalized linear model, generalized partial linear model, misclassification rates, profile-likelihood, quasi-likelihood, semiparametric estimation

Author:
Magda M. Haggag, magmhag@yahoo.com

Editor: Ke, Weiming,weiming.ke@sdstate.edu

Revised December 23, 2007.

READING THE ARTICLE: You can read the article in portable document (.pdf) format (283919 bytes.)

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 2821 times since November 3, 2007.


Return to the InterStat Home Page.