Proper inference from Simon's two‐stage designs

Simon's two-stage designs are very popular for phase II clinical trials. A literature review revealed that the inference procedures used with Simon's designs almost always ignore the actual sampling plan used. Reported P-values, point estimates and confidence intervals for the response rate are not usually adjusted for the design's adaptiveness. In addition, we found that the actual sample size for the second stage is often different from that planned. We present here a method for inferences using both the planned and the actual sample sizes. The conventional and the preferred inference procedures usually yield similar P-values and confidence intervals for the response rate. The conventional inference, however, may contradict the result of the corresponding hypothesis testing.

[1]  Tatsuki Koyama,et al.  Flexible design of two-stage adaptive procedures for phase III clinical trials. , 2007, Contemporary clinical trials.

[2]  John Bather.  Stoppping rules and ordered families of distributions , 1988 .

[3]  Yu Shen,et al.  Estimation of a Parameter and Its Exact Confidence Interval Following Sequential Sample Size Reestimation Trials , 2004, Biometrics.

[4]  Sin-Ho Jung,et al.  Admissible two‐stage designs for phase II cancer clinical trials , 2004, Statistics in medicine.

[5]  P F Thall,et al.  Some extensions and applications of a Bayesian strategy for monitoring multiple outcomes in clinical trials. , 1998, Statistics in medicine.

[6]  T. Chen,et al.  Optimal two-stage designs for phase ii clinical trials with differentiation of complete and partial responses , 2000 .

[7]  P F Thall,et al.  Optimal two-stage designs for clinical trials based on safety and efficacy. , 2001, Statistics in medicine.

[8]  Katherine S Panageas,et al.  An optimal two-stage phase II design utilizing complete and partial response information separately. , 2002, Controlled clinical trials.

[9]  G. Chi,et al.  On Sample Size and Inference for Two‐Stage Adaptive Designs , 2001, Biometrics.

[10]  Jonathan Shuster,et al.  Optimal two-stage designs for single arm Phase II cancer trials , 2002, Journal of biopharmaceutical statistics.

[11]  B. Turnbull,et al.  Group Sequential Methods , 1999 .

[12]  J Whitehead,et al.  Decision Theoretic Designs for Phase II Clinical Trials with Multiple Outcomes , 1999, Biometrics.

[13]  W. London,et al.  One‐ and two‐stage designs for stratified phase II clinical trials , 2005, Statistics in medicine.

[14]  S. Green,et al.  Planned versus attained design in phase II clinical trials. , 1992, Statistics in medicine.

[15]  Xiaoyin Fan,et al.  Conditional and Unconditional Confidence Intervals Following a Group Sequential Test , 2006, Journal of biopharmaceutical statistics.

[16]  M R Conaway,et al.  Designs for phase II trials allowing for a trade-off between response and toxicity. , 1996, Biometrics.

[17]  H. Wieand,et al.  The bias of the sample proportion following a group sequential phase II clinical trial. , 1989, Statistics in medicine.

[18]  R. Simon,et al.  Optimal two-stage designs for phase II clinical trials. , 1989, Controlled clinical trials.

[19]  A A Tsiatis,et al.  Exact confidence intervals following a group sequential test. , 1984, Biometrics.

[20]  Anastasios A Tsiatis,et al.  Adaptive two‐stage designs in phase II clinical trials , 2006, Statistics in medicine.

[21]  D. DeMets,et al.  Exact statistical inference for group sequential trials. , 1991, Biometrics.

[22]  J. Bryant,et al.  Incorporating toxicity considerations into the design of two-stage phase II clinical trials. , 1995, Biometrics.

[23]  T T Chen,et al.  Optimal flexible designs in phase II clinical trials. , 1998, Statistics in medicine.

[24]  Seth M Steinberg,et al.  Early selection in a randomized phase II clinical trial , 2002, Statistics in medicine.

[25]  R. Madsen,et al.  P values for tests using a repeated significance test design , 1982 .

[26]  Hua Jin,et al.  A design of phase II cancer trials using total and complete response endpoints , 2005, Statistics in medicine.

[27]  Sin-Ho Jung,et al.  On the estimation of the binomial probability in multistage clinical trials , 2004, Statistics in medicine.

[28]  John Whitehead,et al.  On the bias of maximum likelihood estimation following a sequential test , 1986 .

[29]  T J Yao,et al.  Optimal two-stage design for a series of pilot trials of new agents. , 1998, Biometrics.

[30]  B. Turnbull,et al.  Group Sequential Methods with Applications to Clinical Trials , 1999 .

[31]  Aiyi Liu,et al.  A Simple and Efficient Bias-Reduced Estimator of Response Probability Following a Group Sequential Phase II Trial , 2005, Journal of biopharmaceutical statistics.

[32]  T. Chen,et al.  Optimal three-stage designs for phase II cancer clinical trials. , 1997, Statistics in medicine.