| Session Title: Alternative Methods for Analyzing Longitudinal Data: Moving Beyond Hierarchical Linear Models (HLM) and Repeated Measures Analysis of Variance (ANOVA) |
| Expert Lecture Session 647 to be held in Centennial Section B on Friday, Nov 7, 3:25 PM to 4:10 PM |
| Sponsored by the Quantitative Methods: Theory and Design TIG |
| Presenter(s): |
| Patrick McKnight, George Mason University, pmcknigh@gmu.edu |
| Abstract: There is more than one way to analyze longitudinal data but the literature seems to indicate otherwise. Evaluators frequently use longitudinal designs but most tend to favor just one analytic procedure. The two currently favored procedures are hierarchical linear models (HLM) and some variant of repeated measures analysis of variance (RM ANOVA). While these procedures are useful, they do not always address the primary evaluation question. Specifically, many evaluators wish to know whether the participants change over time in ways that can be understood and applied to further program development. Evaluators who are aware of alternative longitudinal analytic procedures such as growth curve modeling can better address that primary question. The purpose of this talk is to introduce this alternative procedure and offer suggestions about the conditions where each procedure may be optimally suited to answer that primary question. |