Bridging Advanced Quantitative Methods and Applied Research in the Behavioral, Social and Health Sciences

BRIDGING ADVANCED QUANTITATIVE METHODS WITH APPLIED RESEARCH IN THE BEHAVORIAL, SOCIAL & HEALTH SCIENCES

Training

We currently offer workshops on Multilevel Modeling, Structural Equation Modeling, Structural Equation Models for Longitudinal Data, Mixture Models and Cluster Analysis, and Network Analysis. We also provide individually tailored instruction to groups with specific data analytic needs.

Consulting

We provide consulting services on each phase of the research process, from study design to the application and interpretation of quantitative methods. We offer several modes of consulting to suit a variety of needs.

Informing

We seek to provide you with the information and resources you need to be a knowledgeable user of quantitative methods, including tutorials on commonly used techniques, software demonstrations, discussion of common data analytic concerns, and updates on ongoing developments.

LATEST NEWS

How can I estimate statistical power for a structural equation model?

July 6, 2019
This is a question that often arises when using structural equation models in practice, sometimes once a study is completed but more often in the planning phase of a future study. To think about power, we must first consider ways in which we can make errors in hypothesis testing (Cohen, 1992). Briefly, the Type I error rate is the probability of incorrectly rejecting a true null hypothesis; this is the probability that an effect will be found in a sample when there is truly no effect in the population. In contrast, the Type II error rate is the probability of accepting a false null hypothesis; this is the probability that an effect will not be found in a sample when there truly is an effect in the population. Statistical power is one minus the Type II error rate and represents the probability of correctly rejecting a false null hypothesis; this is the probability that an effect will be found in the sample if an effect truly exists in the population. It is important to determine whether a proposed study will have sufficient power to detect an effect if an effect really exists. Although power is quite easy to compute for simple kinds of tests such as a t-test or for a regression parameter, it becomes increasingly complicated to compute power for complex SEMs. (more…)