Most large randomized clinical trials have a data monitoring committee that
periodically examines efficacy and safety results. A typical data monitori
ng committee meets every 6 months, but the interim monitoring guidelines fo
r many trials specify formal analyses that are years apart. In this article
we argue that study protocols should include monitoring guidelines with fo
rmal looks at each data monitoring committee meeting. Such guidelines are s
hown to reduce the average duration of a trial with negligible effect on po
wer and estimation bias. Some of the common statistical monitoring guidelin
es require extreme evidence to stop a trial early and do not distinguish be
tween stopping a trial during active accrual and follow-up stages. We propo
se practical solutions for these issues. (C) Elsevier Science Inc. 1999.