|
Activity Number:
|
220
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #304346 |
|
Title:
|
Approximation of Likelihood by the Projection Pursuit Regression for Multi-Parameter Distributions
|
|
Author(s):
|
Ahmet Sezer*+
|
|
Companies:
|
Anadolu University
|
|
Address:
|
, , 26470, Turkey
|
|
Keywords:
|
APPROXIMATION ; LIKELIHOOD ; PROJECTION PURSUIT REGRESSION.
|
|
Abstract:
|
The likelihood functions from independent studies can be easily combined, and the combined likelihood function serves as a meaningful indication of the support the observed data give to the various parameter values. We may have distributions with more than one parameter where various components of the parameter vector have different levels of interest. Projection pursuit regression (PPR) models the regression surface as a sum of general smooth functions of linear combinations of the predictor variables. Log-likelihoods are approximated by the PPR method without eliminating the nuisance parameter(s). We also conduct simulation study to assess the performance of PPR over the modified likelihood methods with respect to MSE, coverage probability and average confidence interval depend on the highest density region of the approximated log-likelihood.
|
- 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 2009 program |
