February, 2003
© 2000 Scott S. Emerson, M.D., Ph.D.
Session 4: 19
Adjustment for Stopping Rules
Failure to adjust estimates and P values for stopping rule is tantamount to repeated significance testing
·P values will tend to be wrong
·Estimates will tend to be biased toward extreme
·Confidence intervals will have the wrong coverage probabilities
(No effect on Bayesian analysis)