When working with high-dimensional biological data the so-called multiple hypothesis testing problem emerges. That is, when many separate tests are performed, several will be significant by chance provoking false positive results. Many statistical methods have been developed to deal with this problem. An important topic concerning multiple hypothesis testing efforts applied to high-throughput experiments is the intrinsic inter-dependency in gene effects. Here we simulate data resembling the testing scenario used in a well-known data set from breast cancer microarray studies. The objective of the study is to see the impact of high correlation within gene blocks onto the multiple-testing correction methods as Sequential Bonferroni (SB), Benjamini and Hochberg FDR (BH) and Sequential Goodness of Fit (SGoF).
Type of Publication:
Rocha M.P., Rodríguez J.M.C., Fdez-Riverola F., Valencia A.
5th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2011). Advances in Intelligent and Soft Computing