| Session Title: Master Teacher Series: Using Equivalence Tests to Prove That Groups Don't Differ: How to Generate "Evidence of Absence" Rather Than "Absence of Evidence" |
| Demonstration Session 409 to be held in Pacific C on Thursday, Nov 3, 2:50 PM to 4:20 PM |
| Sponsored by the Quantitative Methods: Theory and Design TIG |
| Presenter(s): |
| Steven Pierce, Michigan State University, pierces1@msu.edu |
| Abstract: This intermediate session will demonstrate the use of equivalence tests, which are statistical methods designed to use the evidence in the data to explicitly prove that two groups are actually equal on some outcome measure. This departs from the goal of classical statistical methods (e.g., t-tests, chi-square tests, etc.), which aim to use the data to prove that two groups actually differ from one another. The session will explain what kinds of evaluation questions equivalence tests can answer, how these tests work, and why they provide more credible evidence of equivalence than offered by simply finding a non-significant effect with a classical method. The session will offer practical advice on how and when to use equivalence tests in your evaluation work. Because equivalence tests are rarely covered in basic graduate level statistics courses, this session aims to provide the audience with a user-friendly introduction to new statistical methods. |