Bioinformatics Seminar
Time: 11AM
Venue: Davis Auditorium Hybrid
29 June 2021
P-values, false discovery rates and fold-change cutoffs
Gordon SmythWEHI Bioinformatics
This talk will discuss some issues relating to p-values, multiple testing and effect sizes. Why p-values are still of value. Why 0.05 became the commonly accepted cutoff and why that shouldn't be a problem. How the false discovery rate has a Bayesian interpretation and how it relates to p-values. Why Benjamini-Hochberg FDR control breaks down if the genes are reordered. Why this has implications for fold-change cutoffs in gene expression analyses.