JSM 2011 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Abstract Details

Activity Number: 344
Type: Contributed
Date/Time: Tuesday, August 2, 2011 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract - #303294
Title: Existence of Maximum Likelihood Estimates in Categorical Regression Models
Author(s): Tezcan Ozrazgat Baslanti*+ and Michael Daniels and Alan Agresti
Companies: University of Florida and University of Florida and University of Florida
Address: Department of Statistics 102 Griffin-Floyd Hall, Gainesville, FL, 32611,
Keywords: existence of maximum likelihood estimates ; categorical response data
Abstract:

It is important to know if the maximum likelihood estimates (MLE) exist or not for a given dataset as some software programs are unable to determine this. We review the existing literature on the existence of MLE for categorical response models such as the multinomial logistic model, the multinomial choice model, and cumulative link models of proportional odds form. We extend the definitions of separation and overlap, given by Albert and Anderson (1984), to the stereotype model and the adjacent-categories logit model. We summarize the existing literature, generalize some results, and examine connections between the different approaches. Combining ideas, we develop new methods of exploring if MLE exists.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2011 program




2011 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.