Subset Analyses of Prostate Data Examining Weight Gain and Recurrence

• Activity Number: 46
• Type: Contributed
• Date/Time: Sunday, August 4, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Irene Helenowski*+ and Jennifer A. Doll and Timothy M. Kuzel and Borko Jovanovic and Alfred Rademaker and Michael J. Gurley
• Companies: Northwestern University and University of Wisconsin-Milwaukee and Northwestern University and Northwestern Univ-Feinberg School of Medicine and Northwestern University and Northwestern University
• Keywords: subset analyses ; prostate data

Abstract

Data subset analysis is frequently a debatable topic in that investigators have often struggled to optimize results without unwarranted data fishing. Here, we examine several subset approaches in order to determine the relationship between weight gain and prostate cancer recurrence in data from the Northwestern University Prostate SPORE (Grant P50 CA 090386). We will compare and discuss results based on these subsets of these subjects. We conclude by presenting the impact involving statistical and biological justifications for different results depending on the subjects.