February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Hypotheses groupbox varies with probability model
General principles
·Specify summary measures for each arm
-Treatment, comparison
-(Sometimes may log transform)
-Can specify just the value for treatment arm
-Default for the comparison group is the null
value for treatment group
·Specify variance
·Specify type of test
-Greater, less, two-sided, (one-sided) equivalence