|Saturday, February 23|
|PCE2 Mixed Model Power Analysis by Example: Using Free Web-Based Power Software||
Sat, Feb 23, 1:45 PM - 3:30 PM
Brief Description of the Product
GLIMMPSE is an open-source tool for calculating power and sample size for the mixed model and for the general linear multivariate model. GLIMMPSE is free, accessible from a standard web browser, and requires no programming expertise. GLIMMPSE uses a step-by-step interface to allow scientists and other users to produce accurate power calculations for common study designs with minimal time investment. In addition, GLIMMPSE can produce basic power curves, and can generate confidence intervals on power values for fixed designs. GLIMMPSE was developed using the Java Web Services architecture to ensure the stability and scalability of the product.
GLIMMPSE supports designs with only fixed predictors, and designs with fixed predictors and a single normally distributed covariate, with equal or unequal group sizes. GLIMMPSE supports complex study designs including multilevel and longitudinal designs. For longitudinal designs, users may specify a variety of complex covariance structures.
The software was developed at the University of Colorado Denver by a computer science team led by Dr. Sarah Kreidler, with assistance from Dr. Aarti Munjal, Uttara Sakhadeo, and Vijay Chander Akula. Guidance on statistical methods and user interface design was provided by Professor Keith E. Muller and Dr. Deborah Glueck. GLIMMPSE is funded by NIDCR 1 R01 DE020832-01A1 to the University of Florida (Keith E. Muller, PI; Deborah Glueck, University of Colorado site PI). Previous funding was received from an American Recovery and Re-investment Act supplement (3K07CA088811-06S, Deborah Glueck, PI) for NCI grant K07CA088811.