|
Activity Number:
|
343
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Sports
|
| Abstract - #309620 |
|
Title:
|
An Analysis of Judges' Inconsistency in the Athens 2004 Olympics Artistic Gymnastics Events Using the Multiplicative Interaction Model
|
|
Author(s):
|
Wijith Munasinghe*+ and Dallas Johnson
|
|
Companies:
|
Kansas State University and Kansas State University
|
|
Address:
|
Department of Statistics, Manhattan, KS, 66506-0802,
|
|
Keywords:
|
two- way non-replicated experiments ; multiplicative interaction model ; interactions ; AMMI macros
|
|
Abstract:
|
There was a controversial issue in medal standings in the Men's Individual All-Round Artistic Gymnastics event at the Athens 2004 Olympics. The goal of this presentation is to determine whether any of the judges were inconsistent in their scoring when compared to the other judges. The competition data set can be viewed as data from a two-way non-replicated experiments design structure within each individual event. Interaction between judges and gymnasts can be interpreted as inconsistency on the part of the judges. Error to test for interaction cannot be estimated in the usual manner since the absence of replications. One way of handling this problem is to model the data with multiplicative interaction model using AMMI macros recently developed by Lee. These models allow testing for interaction and determining the interaction's structure if such structure exists.
|
