Publication at Faculty of Physical Education and Sport |
2010
Abstract
Mediation and moderation are two theories for investigating a causal relationship. Investigations of this kind are especially valuable in intervention research to obtain information on the process by which a program achieves its effects and whether the program is effective for subgroups of individuals.
This paper describes the conceptual foundation and some methods for statistical testing mediation and moderation effects in a simple dataset. In addition, the more elaborate models are described, especially the use of multilevel regression The application of multilevel regression in mediation analysis is illustrated by a program evaluation example.