|
Activity Number:
|
232
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #301386 |
|
Title:
|
Some Challenges Encountered in the Analysis of Biomarker Data
|
|
Author(s):
|
Stephen W. Looney*+ and Joseph L. Hagan
|
|
Companies:
|
Medical College of Georgia and LSU Health Sciences Center
|
|
Address:
|
Department of Biostatistics, Augusta, GA, 30912-4900,
|
|
Keywords:
|
normality ; homoscedasticity ; correlation coefficient ; measures of agreement ; t-test ; McNemar test
|
|
Abstract:
|
In this presentation, we provide a description of some challenges that are often encountered in the analysis of biomarker data, and offer recommendations on how best to deal with those challenges. The statistical issues that we consider are illustrated with examples taken from the biomarker literature and include: assessment of distributional assumptions, assessment of homogeneity assumptions, comparison of correlation coefficients, and comparison of biomarkers. Our recommendations are based on published statistical evidence and we indicate how widely available statistical software can be used to carry out the recommended analyses.
|
