JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 639
Type: Topic Contributed
Date/Time: Thursday, August 13, 2015 : 8:30 AM to 10:20 AM
Sponsor: Biopharmaceutical Section
Abstract #316095
Title: Permutation Test in Biomarker Design
Author(s): Qi Gong*
Companies:
Keywords: permutation test ; biomarker ; false positive ; clinical trial
Abstract:

Permutation test is a popular method when the test statistics has a unknown distribution. Basically the subjects are permuted across groups and a new value of test statistics can be calculated. A big set of permuted statistics values can be used to approximate its true distribution. Many authors used permutation test to determine cutoff for biomarker. He (2014) proposed a method to identify multiple potential cutoffs in clinical trials with survival outcomes. Su et al (2013) used a likelihood approach to dichotomize a continuous biomarker. Jiang et al (2007) provided a biomarker adaptive threshold phase III design. However, Huang et al (2006) pointed out that the permutation test may inflate the false positive rate when comparing two means and the two distributions are not identical. Although the aforementioned authors used more complicated statistics in the permutation test, some of their simulation results do show inflated type 1 error. The performance of permutation test should be studied further especially when the test statistics is likelihood based or even more complicated.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home