Cover Image

Mixture or logistic regression estimation for discrimination

When a training sample for a classification rule includes unclassified observations, the estimation can be done by maximum likelihood using both the classified and unclassified data (GM) or (assuming an exponential family) by logistic regression (L) on the classified data only. This paper shows that the choice depends on the separation and shape of the family.
Year of publication:
1994
Authors: O'Neill, Terence J.
Published in:
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 20.1994, 2, p. 139-142
Publisher: Elsevier
Subject: Logistic regression Mixtures Unclassified observations
Type of publication: Article
Source:
Persistent link: https://www.econbiz.de/10005074711
Similar items by person