|
Activity Number:
|
57
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Government Statistics
|
| Abstract - #304927 |
|
Title:
|
Robust Peters-Belson--Type Estimators of Measures of Disparity and Their Applications in Employment Discrimination Cases
|
|
Author(s):
|
Hiro Hikawa*+ and Efstathia Bura and Joseph L. Gastwirth
|
|
Companies:
|
The George Washington University and The George Washington University/Vertex Pharmaceuticals, Inc. and The George Washington University
|
|
Address:
|
2140 Pennsylvania Ave NW, Washington, DC, 20052,
|
|
Keywords:
|
Disparity studies ; Employment discrimination ; Legal statistics ; Local regression and likelihood estimation
|
|
Abstract:
|
In equal pay discrimination cases, the Peters-Belson (PB) regression method is used to estimate the pay disparities between minority and majority after accounting for major covariates. The PB method first fits a linear regression model for majority. The resulting regression equation is used to predict the salary of each minority. The difference between the actual and predicted salaries estimates the pay disparity and the mean difference estimates a measure of pay disparity. In practice, a linear regression model may not be sufficient to capture the actual salary equation. Thus, we use a local regression model in the PB approach. The statistical properties of the procedure are developed. Simulation studies and re-analysis of real data show that the local PB regression method reflects the true mean function more accurately than the linear model with only a small loss of efficiency.
|
