Sample Size Determination for Complex Longitudinal Trials via Monte Carlo Simulation

• Activity Number: 553
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Computing
• Author(s): Simcha Pollack* and Robert Fireworker and Leonard Presby
• Companies: St. Francis Hospital and St. John's University Tobin College of Business and William Paterson University
• Keywords: Power analysis ; experimental design ; Monte Carlo simulation

Abstract

Designing an experiment in almost any area of research necessitates a power analysis for sample size determination. Results from the power analysis enable researchers to plan for the proper sample size so that, if the alternative hypothesis is true, they would have a high probability (power) of reporting statistically significant findings. Programs exist for calculating power when the research design and statistical analysis is relatively standard. However, with more complex designs, it is difficult or impossible to do a power analysis with the available tools. One complex design that has no packaged solution is the longitudinal study with missing data points. The correlation structure (e.g. compound symmetry) between time points greatly affects the findings and must be addressed. The existence of missing data, often occurring in experiments on humans, complicates the statistical analysis and the power analysis. No analytical formula exists to project the proper sample size under these conditions. Using SAS (Statistical Analysis System) code, we demonstrate how to calculate power for this situation and how to easily modify the program to handle an even wider range of models.