Answers are grounded in this paper and cite their sources.
This paper describes how statistical methods have evolved in parallel with activities associated with randomized control trials. In particular we emphasize the pivotal role of two papers published in British Journal of Cancer, and the paper describing the Cox proportional hazards model. In addition, the importance of early papers on estimating the sample size required for trials is highlighted. Later developments including the increasing roles for competing risks, multilevel modelling and Bayesian methodologies are described. The interplay between computer software and statistical methodological developments is stressed. Finally some future directions are indicated.
No takes yet. Share an insight, caveat, or question.
David Machin (2004) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: