Multiple Comparisons and the False Discovery Rate | TN-CTSI Seminar TOMORROW

|

TN-CTSI seminar series on statistical reasoning in biomedical research: The Division of Biostatistics in the Department of Preventive Medicine and the Biostatistics, Epidemiology and Research Design Unit of TN-CTSI invite you to attend a seminar series on statistical reasoning in biomedical research. This 6-seminar series emphasizes conceptual aspects over technical details.

Time: May 21st 12:00-1:00PM

Location: Simulation Building Room 102

Presented by Saunak Sen, PhD

Multiple Comparisons and the False Discovery Rate

With the advent of high-throughput technologies, making multiple
comparisons has become quite common, even inevitable.  Without
adjustment, multiple comparisons can inflate the false positive rate,
threatening the replicability of scientific findings.  We will discuss
how to frame the multiple comparisons issue, and review some methods
for multiple comparison adjustments. We will begin with considering
situations when we have, and when we don’t have to adjust for multiple
comparisons. Then we will learn about two types of adjustments in the
evidence in p-values – the Family Wise Error Rate (FWER), and the
False Discovery Rate (FDR) — and when to apply each.

Additional Seminars in the Series:

May 28th The Perfect Doctor: An introduction to Causal Inference (Fridtjof Thomas, PhD)

June 4th Enhancing Statistical Methods in Grants and Papers (Saunak Sen, PhD)