Abstract
Internal pilot designs involve conducting interim power analysis (without interim data analysis) to modify the final sample size. Recently developed techniques have been described to avoid the type I error rate inflation inherent to unadjusted hypothesis tests, while still providing the advantages of an internal pilot design. We present GLUMIP 2.0, the latest version of our free SAS/IML software for planning internal pilot studies in the general linear univariate model (GLUM) framework. The new analytic forms incorporated into the updated software solve many problems inherent to current internal pilot techniques for linear models with Gaussian errors. Hence, the GLUMIP 2.0 software makes it easy to perform exact power analysis for internal pilots under the GLUM framework with independent Gaussian errors and fixed predictors.
Highlights
To mirror the results found in Coffey and Muller (1999), we consider the three-group ANOVA example for an internal pilot with the following specifications: 1) a pre-planned sample size of n0 = 81, 2) the first n1 = 39 (13 per group) observations comprise the internal pilot sample (N1=39), 3) both allowing and not allowing the final sample size to decrease if the original variance value overestimates the true variance (NPLUSMIN=39 and NPLUSMIN=81, respectively), 4) no finite upper bound of observations, 5) using Unadjusted Method for sample size re-estimation and testing (RULE=0 and testing technique (TEST)=0)
The results in Coffey and Muller (2001) extend many internal pilot design concepts from the t test setting to the classic general linear univariate model setting
The introduction of the GLUMIP program further extends the practicability of internal pilot designs in two ways: 1
Summary
Internal pilot designs involve conducting interim power analysis (without interim data analysis) to modify the final sample size of a study. Analysis allows adjusting the sample size up or down to help achieve the target power and not waste resources. Such designs differ from traditional (external) pilot studies in that the observations used to estimate the variance are included in the final analysis. The GLUMIP 2.0 software package is designed to accurately assist in planning and implementation of internal pilot designs in the General Linear Univariate Model (GLUM) framework with Gaussian errors and fixed predictors using exact theory for power and type I error rate
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
