Abstract #301353

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #301353
Activity Number: 171
Type: Contributed
Date/Time: Monday, August 4, 2003 : 2:00 PM to 3:50 PM
Sponsor: Business & Economics Statistics Section
Abstract - #301353
Title: Misuse of the "Modified" t-Statistic in Regulatory Telecommunications
Author(s): John D. Opdyke*+
Companies: DataMineIt
Address: 46 Tioga Way, Suite 302, Marblehead, MA, 01945-1581,
Keywords: modified t ; Telecommunications Act ; parity testing ; performance measurement testing ; OSS testing ; regulatory telecommunications
Abstract:

The 'modified' t-statistic (Brownie et al. 1990) has gained widespread use and acceptance in the telecommunications regulatory arena for performing two-sample hypothesis tests on Bell companies' performance measurement data, with significant financial consequences for the entire industry. Expert testimony from multiple sources has justified use of the 'modified' t in this context primarily based on the following claims: (a) the distribution of the 'modified' t is asymptotically standard normal; (b) the 'modified' t minimizes the potential for test manipulation by including in its denominator only one sample's variance; © the 'modified' t can be used to test Ho: M1< =M2 AND Var1< =Var2 against Ha: M1>M2 OR Var1>Var2; This paper uses both simulation and analytic derivation to show that none of these claims is valid, making statistical inferences based on them incorrect, and policies based on these inferences misguided, largely because the statistic was designed to test a different pair of hypotheses (Ho: M1< =M2 AND Var1< =Var2 against Ha: M1>M2 AND Var1>Var2) in a very different (controlled experimental) setting. This paper briefly surveys alternate tests to accomplish (b) and (c).

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003