A Simulation Study Evaluating the Generalized Additive Model for Assessing Intervention Effects With Small Samples

• In Event: Multiple Linear Regression: The General Linear Model SIG Special Topics Paper Session

Abstract

Educational researchers frequently use longitudinal research designs with small samples in order to assess treatment effectiveness. Several statistical methods have been suggested for assessing effectiveness of such interventions when the sample size is small, including generalized additive models (GAM). Prior research has shown that for single sample studies, GAM effectively identifies nonlinear change over time due to the impact of the intervention. The current simulation study extends this earlier work by investigating the performance of GAM in the context of longitudinal research in which a small sample of individuals is divided into multiple treatment groups, and the effectiveness of an intervention is studied over time. Results show that multilevel GAM accounting for study participant is effective at identifying intervention effects.

Authors

• William Holmes Finch, Ball State University

• Maria E. Hernandez Finch, Ball State University