Power and Sample Size Determination in Survival Time Studies with Special Regard to the Censoring Mechanism

M. Schumacher

doi:10.1055/s-0038-1635296

Methods of Information in Medicine, Table of Contents

Methods Inf Med 1981; 20(02): 110-115
DOI: 10.1055/s-0038-1635296

Original Article

Schattauer GmbH

Power and Sample Size Determination in Survival Time Studies with Special Regard to the Censoring Mechanism^[*]

POWER- UND STICHPROBENKALKULATION IN ÜBERLEBENSZEITSTUDIEN MIT BESONDERER BERÜCKSICHTIGUNG DER ZENSIERUNG

M. Schumacher

¹From the Institut für Medizinische Dokumentation, Statistik und Datenverarbeitung der Universität Heidelberg, and Sonderforschungsbereich 123 “Stochastische Mathematische Modelle” der Universität Heidelberg

› Author Affiliations

Abstract

When calculating the power and sample size in survival time studies for the comparison of two treatments censoring has to be taken into account.

In most medical applications only vague information about the shape of the underlying distributions is available. Thus, a distribution-free procedure based on the McNemar test is proposed and compared with other methods.

Power- und Stichprobenkalkulationen in Uberlebenszeitstudien zum Vergleich zweier Behandlungen müssen den Einfluß, den der Zensierungsmechanismus ausübt, berücksichtigen.

Bei den meisten Anwendungen im Bereich der Medizin hat man oft nur eine sehr grobe Vorstellung über die Form der zugrundeliegenden Verteilungen. Deshalb wird ein Verfahren vorgeschlagen, das auf dem verteilungsfreien McNemar-Test beruht, und mit anderen Methoden verglichen.

Key-Words:

Survival Time Studies - Random Censorship - Power of 2-Sample Tests - Sample Size Determination - McNemar Test

Schlüssel-Wörter:

Uberlebenszeitstudien - Zufällige Zensierung - Power von Zwei-Stichprobentests - Stichprobenumfänge - McNemar-Test

Full Text

References

References
1 Armitage P. The Comparison of Survival Curves. J. roy. statist. Soc. A 1959; 122: 279-292.
2 Armitage P. Sequential Medical Trials. 2nd Ed. Oxford: Black-well; 1975
3 Bernstein D, Lagakos S. W. Sample Size and Power Determination for Stratified Clinical Trials. J. statist. Comput. Simul 1978; 8: 65-73.
4 Boag J. W, Haybittle J. L, Fowler J. F, Emery E. W. The Number of Patients Required in a Clinical Trial. Brit. J. Radiol 1971; 44: 122-125.
5 Breslow N. E. Analysis of Survival Data under the Proportional Hazards Model. Int. statist. Rev 1975; 43: 44-58.
6 Casagrande J. T, Pike M. C, Smith P. G. An Improved Approximate Formula for Calculating Sample Sizes for Comparing two Binomial Distributions. Biometrics 1978; 34: 483-486.
7 Cochran W. G, Cox G. M. Experimental Designs. 2nd Ed.. New York: Wiley; 1957
8 Cox D. R. Regression Models and Life Tables (with Discussion) . J. roy. statist. Soc. B 1972; 34: 187-220.
9 Fleiss J. L. Statistical Methods for Rates and Proportions. New York: Wiley; 1973
10 George S. L, Desu M. M. Planning the Size and Duration of a Clinical Trial Studying the Time to some Critical Event. J. chron. Dis 1974; 27: 15-24.
11 Gross A. J, Clark V. A. Survival Distributions: Reliability Applications in the Biomedical Sciences. New York: Wiley; 1975
12 Haybittle J. L, Freedman S. Some Comments on the Logrank , Test Statistic in Clinical Trial Applications. Statistician 1979; 28: 199-208.
13 Holt J. D, Prentice R. L. Survival Analysis in Twin Studies and Matched Pair Experiments. Biometrika 1974; 61: 17-80.
14 Lee E. T, Desu M. M, Gehan E. A. A Monte Carlo Study of the Power of some Two-sample Tests. Biometrika 1975; 62: 425-432.
15 Lininger L, Gail M. H, Green S. B, Byar D. P. Comparison of four Tests for Equality of Survival Curves in the Presence of Stratification and Censoring. Biometrika 1979; 66: 419-428.
16 Mcnemar Q. Note on the Sampling Error of the Differences between Correlated Proportions or Percentages. Psychometrika 1947; 12: 153-157.
17 Miettinen O. S. The Matched Pairs Design in the Case of All-or-none Responses. Biometrics 1968; 24: 339-352.
18 Peto R, Peto J. Asymptotically Efficient Rank Invariant Test Procedures (with Discussion) . J. roy. statist. Soc. A 1972; 135: 185-207.
19 Peto R, Pike M. C, Armitage P, Breslow N. E, Cox D. R, Howard S. V, Mantel N, Mcpherson K, Peto J, Smith P. G. Design and Analysis of Randomized Clinical Trials Requiring Prolonged Observation of each Patient. I. Introduction and Design. Brit. J. Cancer 1976; 34: 585-612.
20 Peto R. Design and Analysis of Randomized Clinical Trials. Lecture Given at the 2nd Session on the Planning of Cancer Therapy Studies, Ulm 1979
21 Schoenfeld D. The Asymptotic Properties of Nonparametric Tests for the Censored Two-sample Problem. Techn. Report. Sidney Farber Cancer Institute and Harvard School of Public Health, Boston 1980

Power and Sample Size Determination in Survival Time Studies with Special Regard to the Censoring Mechanism[*]

Power and Sample Size Determination in Survival Time Studies with Special Regard to the Censoring Mechanism^[*]