|
Activity Number:
|
354
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 2, 2016 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economic Statistics Section
|
|
Abstract #321237
|
View Presentation
|
|
Title:
|
A Generalized Ordered Response Model
|
|
Author(s):
|
Kramer Quist* and James McDonald and Carla Johnston
|
|
Companies:
|
Brigham Young University and Brigham Young University and University of California at Berkeley
|
|
Keywords:
|
Semiparametric ;
SGT ;
Categorical Data ;
Big Data ;
Monte Carlo Simulations
|
|
Abstract:
|
The ordered probit and logit models, based on the normal and logistic distributions, respectively can yield biased and inconsistent estimators when the distributions are misspecified. A generalized ordered response model is introduced which can reduce the impact of distributional misspecification. An empirical exploration of various determinants of life satisfaction demonstrates the benefits of allowing for diverse distributional characteristics. We experiment with Monte Carlo estimation techniques to analyze how generalized ordered response model's compare to probit and logit models in various sample sizes.
|
Authors who are presenting talks have a * after their name.
