|
Activity Number:
|
401
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #300958 |
|
Title:
|
A New Method for Estimating Regression Parameters with Repeated Runs
|
|
Author(s):
|
Howraa Majeed*+ and Hassan Elsalloukh and Shawki Shaker Hussain
|
|
Companies:
|
University of Arkansas at Little Rock and University of Arkansas at Little Rock and University of Baghdad
|
|
Address:
|
Department of Applied Science, ETAS 575, Little Rock, AR, 72204,
|
|
Keywords:
|
repeated runs ; two phases method ; M-estimation ; outliers ; robust ; simple linear regression
|
|
Abstract:
|
This article deals with the problem of estimating the parameters of the simple linear regression model in the presence of outliers when repeated runs of observations are present in the data. We propose a new method that includes various robust estimators that are based on reflecting the influence of outliers. We name the new method the two phases method. In phase-I we simply employ, at each fixed value of the independent variable, one of the robust estimation methods of the location parameter to estimate the unknown value of the dependent variable. In phase-II, the reduced new observations obtained by phase-I are used to estimate the slope and intercept parameters. This is done using either the ordinary least squares method or one of the robust methods. We finally present simulation results that show the superiority of the new method over the usual least squares (LS) or robust method.
|
