Activity Number:
|
176
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 13, 2002 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Business & Economics Statistics Section*
|
Abstract - #301016 |
Title:
|
Estimation and Inference in Regression Models with Asymmetric Error Distributions: A Comparison of LAV and LS Procedures
|
Author(s):
|
Terry Dielman*+
|
Affiliation(s):
|
Texas Christian University
|
Address:
|
P.O. Box 298530, Fort Worth, Texas, 76129, USA
|
Keywords:
|
least squares ; least absolute value
|
Abstract:
|
A Monte Carlo simulation is used to compare estimation and inference procedures in least absolute value (LAV) and least squares (LS) regression models with asymmetric error distributions. This paper compares both bias and efficiency of coefficient estimates. Hypothesis tests for coefficients are compared on the basis of empirical level of significance and power. Several approaches to hypothesis testing for coefficients are examined for the LAV regression: likelihood ratio test, Lagrange multiplier test, and the bootstrap test. The standard t-test is used for the LS regression. Factors considered that might influence estimation and test performance include the disturbance distribution, the type of independent variable, and the sample size.
|