Sample size in clinical trials with dichotomous endpoints: use of covariables
- 1 January 1998
- journal article
- research article
- Published by Taylor & Francis in Journal of Biopharmaceutical Statistics
- Vol. 8 (3) , 367-375
- https://doi.org/10.1080/10543409808835246
Abstract
In many clinical trials, the primary endpoint is dichotomous. In this article, we examine the possibility of reducing the required sample size by removing variation associated with baseline covariables. Three measures are used to study the size of the reduction. Simulation studies based on a database of head trauma and of stroke patients suggested that a substantial reduction in the sample size can be achieved when the correlation between the endpoint and covariables is strong. A simple ad hoc formula for approximating the required sample size is proposed.Keywords
This publication has 19 references indexed in Scilit:
- Sample size tables for logistic regressionStatistics in Medicine, 1989
- Generalized Linear ModelsPublished by Springer Nature ,1989
- Improved confidence of outcome prediction in severe head injuryJournal of Neurosurgery, 1981
- Sample Size for Logistic Regression with Small Response ProbabilityJournal of the American Statistical Association, 1981
- Regression and ANOVA with Zero-One Data: Measures of Residual VariationJournal of the American Statistical Association, 1978
- Measures of Association for Cross Classifications, IV: Simplification of Asymptotic VariancesJournal of the American Statistical Association, 1972
- An Analysis of Variance for Categorical DataJournal of the American Statistical Association, 1971
- Measures of Association for Cross Classifications III: Approximate Sampling TheoryJournal of the American Statistical Association, 1963
- Measures of Association for Cross Classifications. II: Further Discussion and ReferencesJournal of the American Statistical Association, 1959
- Measures of Association for Cross Classifications*Journal of the American Statistical Association, 1954