Semiparametric Analysis in Conditionally Independent Multivariate Mixture Models

The conditional independence assumption is commonly used in multivariate mixture models in behavioral research. We propose an exponential tilt model to analyze data from a multivariate mixture distribution with conditionally independent components. In this model, the log ratio of the density functio...

Full description

Saved in:
Bibliographic Details
Main Authors: Wrobel, T., LEUNG, Denis H. Y., Qin, J., Hettmansperger, T.
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2015
Subjects:
Online Access:https://ink.library.smu.edu.sg/soe_research/1481
https://ink.library.smu.edu.sg/context/soe_research/article/2480/viewcontent/101007_2F978_3_319_22404_6_21.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:The conditional independence assumption is commonly used in multivariate mixture models in behavioral research. We propose an exponential tilt model to analyze data from a multivariate mixture distribution with conditionally independent components. In this model, the log ratio of the density functions of the components is modeled as a quadratic function in the observations. There are a number of advantages in this approach. First, except for the exponential tilt assumption, the marginal distributions of the observations can be completely arbitrary. Second, unlike some previous methods, which require the multivariate data to be discrete, modeling can be performed based on the original data.