|
Activity Number:
|
413
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Consulting
|
| Abstract - #310038 |
|
Title:
|
Resolving a Multimillion Dollar Contract Dispute with a Latin Square Design
|
|
Author(s):
|
Steven Crunk*+ and William B. Fairley and Marian Hofer and Peter J. Kempthorne
|
|
Companies:
|
San Jose State University and Analysis and Inference, Inc. and California State University, East Bay and Kempthorne Analytics, Inc.
|
|
Address:
|
375 Mullinix Way, San Jose, CA, 95136,
|
|
Keywords:
|
Latin Square ; experimental design ; contract ; dispute ; measure
|
|
Abstract:
|
A major eastern City negotiated a dispute over the performance of new garbage trucks with the vehicle manufacturer. The dispute concerned fulfillment of a contract calling for trucks to hold a "minimum full-load of 12.5 tons." On behalf of the City, and in cooperation with the manufacturer, statisticians developed a Latin Square design to estimate loads. The field experiment controlled for factors such as city districts, day-of-the-week, weight measurement method, instructions to crews, and supervision. To carry out the experiment, 5 pairs of trucks operated on 5 days in 5 districts. The contract spec did not further define the criterion of a "minimum full-load of 12.5 tons." Thus, different measures of contract fulfillment were defined. The experiment demonstrated successful fulfillment of the contract and resolved the dispute.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
