Introduction to Power and Sample Size
Brown Bag Lecture by Dr. Fiona Callaghan | 4/17/2012 11AM-12PM | 7th Floor Conference Room, Bldg 38A
Abstract: Power and sample size calculations are an essential component to any study where the researcher wishes to gather evidence against a hypothesis. Without enough sample size, an experiment may have little to no chance of producing evidence to disprove a hypothesis, which results in a waste of time and resources, as well as potentially leading to misleading claims of “negative” results. Therefore, before the study takes place, it is important to calculate how many subjects one would require in order to have a good chance of seeing at least a minimally “clinically interesting” response, or the equivalent for that area of research. I will discuss the fundamental concepts underlying classical hypothesis testing, and then work through examples for analyzing basic one- and two-sample experiments.
Bio: Dr. Fiona Callaghan joined the CSB at the Lister Hill Center in 2010. Her research focuses on survival analysis, epidemiology, classification methods, and methods for using natural language processing in statistical modeling. Prior to joining CSB, Dr Callaghan worked in the Department of Clinical and Translational Science at the University of Pittsburgh, the Robotics Institute at Carnegie Mellon University, and at the Food and Drug Administration on various drug safety projects including the 2010 meta-analysis of the diabetes drug Avandia. Dr. Callaghan graduated with a BS in Mathematics and BA (Hons) in Philosophy from the University of Canterbury, New Zealand. Dr. Callaghan also has an MA in philosophy and an MS in Statistics from Carnegie Mellon University, and a PhD in Biostatistics from the University of Pittsburgh.