| Session Title: Missing Data: Its Not Just for Statisticians Anymore |
| Demonstration Session 868 to be held in Baltimore Theater on Saturday, November 10, 3:30 PM to 5:00 PM |
| Sponsored by the Quantitative Methods: Theory and Design TIG |
| Presenter(s): |
| Patrick McKnight, George Mason University, pem@alumni.nd.edu |
| Abstract: Missing data presents problems in all empirical work. The problems get compounded when those efforts move out of the comfortable confines of the laboratory and into the more typical environment of the evaluator. Traditional discussions of missing data tend to view the problems as statistical by nature, however, a better and more logical way to view missing data is as a methodological confound. These discussions are often technical and appeal only to those who find comfort in mathematics. Few evaluators find comfort in equations. So the problem before us is quite simple. Missing data can be a substantial problem and there are few resources to assist evaluators to prevent, treat, or report the problems associated with missing data. The purpose of this demonstration is to demonstrate how to diagnose, treat, and report missing data without using overly technical language. |