A Latent Variable Framework for Power Estimation Within Intervention Contexts |
| |
Authors: | Terry E. Duncan Susan C. Duncan Lisa A. Strycker Fuzhong Li |
| |
Affiliation: | (1) Oregon Research Institute, Eugene, Oregon |
| |
Abstract: | This paper presents a latent growth SEM approach for the estimation of treatment effects, and power to detect such effects, within a true experimental design setting in which subjects are randomly assigned to treatment and control conditions. Power estimation is a critical component of intervention experiment design and the testing of their results. Although researchers have become increasingly sophisticated in applying tests for statistical significance in intervention contexts, few are aware of the power of these tests. The issues raised in this paper are not new; however, reminding researchers to consider these points is important. Exactly how the researcher handles these issues will depend on the questions asked and the resources available, as well as other considerations. Discussion underscores the relationship between the reliability of a study's measures and concomitant increases in power obtained within the SEM framework. |
| |
Keywords: | SEM power analyses intervention context latent growth model measurement error |
本文献已被 SpringerLink 等数据库收录! |