February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Session 1- Fixed Sample Design: 100
Case Study: Statistical Design Issues
Defining the comparison group (cont.)
Single comparison group treated with placebo
·not interested in studying dose response
·no similar current therapy
·avoid bias with assessment of softer endpoints
Randomized
·allow  causal inference