|
Activity Number:
|
353
- Research and Educational Tools
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
|
|
Sponsor:
|
Section on Statistics and Data Science Education
|
|
Abstract #317825
|
|
|
Title:
|
A Least Deviation Estimation Approach for the Analysis of Variance Models
|
|
Author(s):
|
Mian Arif Shams Adnan and Md Shamsuddin*
|
|
Companies:
|
Bowling Green State University and Dhaka
|
|
Keywords:
|
Absolute Deviation;
Outlier;
Relative Coefficient of Determination
|
|
Abstract:
|
Estimates of parameters for the Design of Experiment Models suffer from the exaggeration of the contribution of the extreme observation(s) as well as the outlier(s). Unlike the traditional fitting procedure of Analysis of Variance Models based on the least squares estimates, it uses least deviation method for minimizing the total sum of errors. It also suggests some new measures of fit.
|
Authors who are presenting talks have a * after their name.
