|
Activity Number:
|
505
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 2, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #309246 |
|
Title:
|
Least Squares Estimation in Linear Regression with Doubly Truncated Data
|
|
Author(s):
|
Xiaodong Luo*+ and Wei-Yann Tsai
|
|
Companies:
|
Mount Sinai School of Medicine and Columbia University
|
|
Address:
|
130 West Kingsbridge Road, Bronx, NY, 10468,
|
|
Keywords:
|
Estimating function ; Least squares estimator ; Double Truncation
|
|
Abstract:
|
We investigate a least squares estimator for regression coefficients of the covariates in the multiple linear regression model with doubly truncated data, where the dependent variable is truncated from above and below. This estimator is a generalization of the estimator for one-sided truncated linear regression proposed by Tsai, Liu and Luo (2006), and is proved to be consistent and have an asymptotic normal distribution. The estimation procedure does not require to calculate the nonparametric estimate of the error distribution. We also discuss the construction of the confidence regions for the regression parameters. A simulation study shows that the estimator performs well with a moderate sample size.
|
