American Statistical Association
In this talk, we will discuss designing a study when we suspect the outcome of interest is measured with error. In particular, we consider a specific case where the variance of the error distribution is proportional to the mean of the true measurements leading to nonconstant error. We evaluate how this measurement error affects the sample size and power of a study. Methods for adjusting the required sample size for this error are proposed and assessed in a simulation study.
|Date:||Wednesday, March 7, 2007|
|Time:||4:00 P.M. - 5:00 P.M.|
Memorial Sloan-Kettering Cancer Center
Department of Epidemiology and Biostatistics
307 East 63rd Street
(between First and Second Avenues)
3rd Floor Conference Room
New York, New York
Note: To gain access to the building, please follow the directions by the telephone in the foyer.