Continuous study outcomes. One sample, two sample and correlated data problems
Bernard Rosner, PhD, Harvard Medical School and School of Public Healthhttps://www.hsph.harvard.edu/bernard-rosner/
Description
"Session 3: Continuous study outcomes. One sample, two sample and correlated data problems, by Dr. Bernard Rosner"
We will discuss power and sample size calculations for continuous outcomes. Both paired-sample and independent-sample designs will be considered, including both person-level and eye-level endpoints. A special feature of power and sample size estimation for eye-level endpoints which we will cover is how to account for correlated eye data. Also, relative efficiency of eye-level vs. person-level endpoints will also be discussed.