"Proving the null hypothesis" in clinical trials.

When designing a clinical trial to show whether a new or experimental therapy is as effective as a standard therapy (but not necessarily more effective), the usual null hypothesis of equality is inappropriate and leads to logical difficulties. Since therapies cannot be shown to be literally equivalent, the appropriate null hypothesis is that the standard therapy is more effective than the experimental therapy by at least some specified amount. The problem is presented in terms of a trial in which the outcome of interest is dichotomous; test statistics, confidence intervals, and sample size calculations are discussed. The required sample size may be larger for either null hypothesis formulation than for the other, depending on the specific assumptions made. Reporting results in terms of confidence intervals is especially useful for this type of trial.

[1]  T R Fleming,et al.  One-sample multiple testing procedure for phase II clinical trials. , 1982, Biometrics.

[2]  A. Spriet,et al.  When can 'non significantly different' treatments be considered as 'equivalent'? , 1979, British Journal of Clinical Pharmacology.

[3]  F. Mosteller,et al.  Reporting standards and research strategies for controlled trials , 1980 .

[4]  R. Makuch,et al.  Sample size requirements for evaluating a conservative therapy. , 1978, Cancer treatment reports.

[5]  W. Westlake.  The use of balanced incomplete block designs in comparative bioavailability trails. , 1974, Biometrics.

[6]  A. Dempster,et al.  A Bayesian approach to bioequivalence for the 2 x 2 changeover design. , 1981, Biometrics.

[7]  E. S. Pearson,et al.  On the Problem of the Most Efficient Tests of Statistical Hypotheses , 1933 .

[8]  M. J. R. Healy,et al.  Statistics with Applications to the Biological and Health Sciences , 1971 .

[9]  D. Alling,et al.  A comparison of amphotericin B alone and combined with flucytosine in the treatment of cryptoccal meningitis. , 1979, The New England journal of medicine.

[10]  B. Rodda,et al.  Determining the probability of an important difference in bioavailability , 1980, Clinical pharmacology and therapeutics.

[11]  R Fisher,et al.  Design of Experiments , 1936 .

[12]  Westlake Wj,et al.  Statistical Aspects of Comparative Bioavailability Trials , 1979 .

[13]  C. Dunnett,et al.  Significance testing to establish equivalence between treatments, with special reference to data in the form of 2X2 tables. , 1977, Biometrics.

[14]  W. J. Westlake,et al.  Use of confidence intervals in analysis of comparative bioavailability trials. , 1972, Journal of pharmaceutical sciences.

[15]  G. W. Snedecor.  Statistical Methods , 1964 .

[16]  E. Lehmann.  Testing Statistical Hypotheses , 1960 .

[17]  T C Chalmers,et al.  The importance of beta, the type II error and sample size in the design and interpretation of the randomized control trial. Survey of 71 "negative" trials. , 1978, The New England journal of medicine.

[18]  E. S. Pearson,et al.  On the Problem of the Most Efficient Tests of Statistical Hypotheses , 1933 .

[19]  M A Schneiderman,et al.  The role of hypothesis testing in clinical trials. Biometrics seminar. , 1966, Journal of chronic diseases.

[20]  W. Westlake,et al.  Symmetrical confidence intervals for bioequivalence trials. , 1976, Biometrics.

[21]  C M Metzler,et al.  Bioavailability--a problem in equivalence. , 1974, Biometrics.

[22]  Miller Hs.  SODIUM HEPARIN VS SODIUM WARFARIN IN ACUTE MYOCARDIAL INFARCTION; CONCLUSIONS BASED ON STUDY OF 798 CASES AT 13 HOSPITALS. , 1964 .