Conference Schedule

8:15 – 9:00
Registration and Continental Breakfast

9:00 – 9:10
Introductory Remarks
Boris Iglewicz, Temple University

9:10 – 9:50
On the Use of Stochastic Curtailment in Sequential Clinical Trials
Scott S. Emerson, University of Washington

9:50 – 10:30
A Conditional Power Approach to the Evaluation of Predictive Power
Gordon Lan, Johnson & Johnson (with Michael Proschan)

10:30 – 10:55

10:55 – 11:35
Parameter Estimation in Adaptive Group Sequential Clinical Trials
Cyrus Mehta, Cytel Inc., Harvard University

11:35 – 12:15
Sequential Monitoring of Randomization Tests
William F. Rosenberger, George Mason University

12:15 – 1:30

1:30 – 1:45
Colin Begg, Cornell University, MSKCC

1:45 – 2:30
Panel Discussion

2:30 – 3:25
Panel and Audience Discussion

3:25 – 3:30
Closing Remarks


Scott S. Emerson, University of Washington

Many different criteria have been proposed for the selection of a stopping rule for group sequential trials. These include both scientific (e.g., estimates of treatment effect) and statistical (e.g., frequentist type I error, Bayesian posterior probabilities, stochastic curtailment) measures of the evidence for or against beneficial treatment effects. Because a stopping rule based on one of those criteria induces a stopping rule based on all other criteria, the usefulness of any particular scale depends on the ease with which it allows a clinical trialist to search for sequential sampling plans having desirable operating characteristics. In this talk I examine the use of such measures as conditional power and predictive power in the definition of stopping rules, especially as they apply to decisions to terminate a study early for “futility”. I illustrate that stopping criteria based on stochastic curtailment are relatively more difficult to interpret on the scientifically relevant scale of estimated treatment effects, as well as with respect to commonly used statistical measures such as unconditional power. I further argue that neither conditional power nor predictive power adhere to the standard optimality criteria within either the frequentist or Bayesian data analysis paradigms. I conclude with some remarks about the use of stochastic curtailment when adaptively re-designing trials.

Gordon Lan, Johnson & Johnson (with Michael Proschan)

We consider the use of a standard Brownian motion process on the unit interval [0,1] to predict the final outcome of a medical study during interim data analyses. The drift parameter theda is zero under the null hypothesis, and is positive under alternative hypotheses. Many of the test statistics in two-sample comparisons can be converted to the Brownian motion with a linear drift. For a fixed amount of information, the drift theda is determined by the standardized treatment difference D. For a given drift theda, the  conditional power (CP) of a positive study during interim analysis is easy to visualize and simple to evaluate. A more sophisticated way to predict the future outcome is the use of the predictive power (PP) which considers the drift parameter as random and takes a weighted average of the CPs. Unfortunately, the evaluation of PP involves the integration of CPs, and many clinicians found that hard to follow. We propose the use of CP under a modified current trend as an alternative method to evaluate PP for the prediction of clinical trial outcomes.  We will also discuss CP and PP for sequential designs and the choice of prior and posterior distributions under Bayesian settings.   Joint work with Peter Hu, Johnson & Johnson.

Cyrus Mehta, Cytel Inc. (Cytel is the developer of the StatXact, LogXact and East software packages.), Harvard University

There has been a considerable amount of recent research on making data dependent mid course corrections to the sample size of an on-going clinical trial. To a great degree this research has focused on the problem of preserving the type-1 error. The related problems of parameter estimation and p-value computation have not been well investigated. This severely limits the applicability of the methods to actual studies. We will present methods for computing exact and conservative confidence intervals, median unbiased point estimates and p-values based following a group sequential test in which adaptive changes are made along the way. The method is based on extending the dual tests of repeated confidence intervals (Jennison and Turnbull, 1989), and of stage-wise adjusted confidence intervals (Tsiatis, Rosner and Mehta, 1984) to the adaptive setting.


William F. Rosenberger, George Mason University

Randomization provides a basis for inference, but it is rarely taken advantage of.  We discuss randomization tests based on the family of linear rank tests in the context of sequential monitoring of clinical trials.  Such tests are applicable for categorical, continuous, and survival time outcomes.  We prove the asymptotic joint normality of sequentially monitored test statistics, which allows the computation of sequential monitoring critical values under the Lan-DeMets procedure. Since randomization tests are not based on likelihoods, the concept of information is murky. We give an alternate definition of randomization and show how to compute it for different randomization procedures. The randomization procedures we discuss are the permuted block design, stratified block design, and stratified urn design. We illustrate these results by reanalyzing a clinical trial in retinopathy. Joint work with Yanqiong Zhang, Merck, and R. T. Smythe, Oregon State University.


Scott Emerson, M.D., Ph.D., Professor of Biostatistics at the University of Washington, is an active researcher in the design, monitoring and analysis of group sequential trials.A major focus of his statistical research has been in the use of estimation methods to examine the robustness of inference in the setting of poorly specified stopping rules. His applied research has included collaboration on both government and industry sponsored clinical trials in cancer prevention and treatment, cardiovascular disease, liver disease, neurological disease, and arthritis. Currently he serves as the Principal Investigator for the Resuscitation Outcomse Consrortium. He serves on a number of government and industry sponsored advisory boards related to the design and monitoring of clinical trials. Computer programs that he developed for his research into group sequential methodology now form the backbone of S+SeqTrial, an S-Plus module for group sequential trial design. Scott Emerson served as the 1999 President of WNAR and is a Fellow of the American Statistical association.

Gordon Lan, Gordon received his Ph.D. in Mathematical Statistics from Columbia University.  He is currently Senior Director of Statistical Science at Johnson & Johnson Pharmaceutical Research & Development, L.L.C.  Prior to joining Johnson & Johnson in 2005, Gordon held positions at Sanofi-Aventis, Pfizer, George Washington University, and the National Heart, Lung, and Blood Institute of NIH.  Gordon has done some statistical research work on clinical trial design and data analysis. He was elected Fellow of the American Statistical Association in 1992.

Cyrus Mehta, Cytel Inc., Harvard Universit, received his Ph.D. from Massachusetts Institute of Technology in 1973. He is a co-founder and President of Cytel Software Corporation and Adjunct Professor of Biostatistics, Harvard University. Professor Mehta has published extensively in leading statistics journals, including many articles in the group sequential area. He was a co-winner of the 1987 George W. Snedecor Award from the American Statistical Association and is a Fellow of the American Statistical Association. He consults extensively with the biopharmaceutical industry on group sequential and adaptive design, offers workshops on these topics, and sits on several data monitoring committees for these types of clinical trials.

William F. Rosenberger, George Mason University, serves as Professor and Chair of the Department of Statistics, He received his Ph.D. from George Washington University in 1992. Professor Rosenberger is a Fellow of The American Statistical Association and has written extensively in the design of clinical trials and randomization, including response-adaptive randomization, areas. Two recent books are: The Theory of Response-Adaptive Randomization in Clinical Trials, Wiley (2006, with Hu); Randomization in Clinical Trials; Theory and Practice, Wiley (2002, with Lachin).

Colin Begg received his PH.D. from Glasgow University in 1976. He presently serves as Professor of Biostatistics and Public Health, Cornell University, Chair, Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center (MSKCC ), and Chair, Preventive Control and Population Research Program, and as the Eugene W. Kettering Chair at MSKCC.  Colin has published extensively in the clinical trial area and has been elected as a Fellow of the American Statistical Association and member of the International Statistical Institute. Professor Begg has received the 1989 Spiegelman Award and the Statistics Section Award in 2002 from the American Public Health Association.


General – $90
Merck – $40
Bristol-Myers Squibb – $60
Wyeth – $60
Full time graduate students – $25

Registration includes: Continental Breakfast, Lunch, Break. Parking is free.

8:15AM – 9:00AM
Meeting: 9:00AM – 3:30PM

Seating is limited. Please make checks payable to Temple University (Biostatistics) and send to:

Boris Iglewicz, Director,
Biostatistics Research Center,
Department of Statistics, Temple University,
1810 N. 13th Street,
Philadelphia, PA 19122-6083

Please include your name, the name of your company, and either your email address, fax #, or address. We must receive checks by Wednesday, October 24, 2007. We cannot accept cash or credit card payments.

For additional information, contact Boris Iglewicz, Director, email: or telephone (215) 204-8637.


640 W. Germantown Pike, Plymouth Meeting PA 19462
(610) 834-8300

From Airport: Take 95 South to 476 North to the last exit #20(Germantown Pike-West). Merge with Germantown Pike and follow for 3 lights. Make a right onto Hickory Rd. at the 3rd light. The hotel is the 3rd building on the left.

New York/ New Jersey Turnpike: Take the New Jersey Turnpike to exit #6, which is PA turnpike. Go west to exit #333- Norristown. Follow signs to Plymouth Rd. Go to the 1st light and make a left. Go to the next light and make a right onto Germantown Pike. Go to the second light and make a right on Hickory Rd. The hotel is the second driveway on the left.

Washington D.C., Wilmington, and Delaware: Take I-95 North to Route 476 North. Take Route 476 to the Germantown Pike West exit #20. Go to the third light, Hickory Rd., and make a right. The hotel is the 2nd driveway on the left.

Route 476: Take 476 to the Germantown Pike West exit #20. Go to the third light, Hickory Rd., and make a right. The hotel is the 2nd driveway on the left.

From downtown Philadelphia: I-76 west Plymouth Meeting exit #331B (Route 476). Take Route 476 north to Germantown Pike exit. Go to the third light, Hickory Rd., and make a right. The hotel is the 2nd driveway on the left.