Practice abstract
British Dental Journal 193, 557 - 561 (2002)
Published online: 23 November 2002 | doi:10.1038/sj.bdj.4801627
Further statistics in dentistry Part 4: Clinical trials 2
A Petrie1, J S Bulman2 & J F Osborn3
- The rationale underlying the choice of the optimal sample size in a clinical trial
- An explanation of Type I and Type II errors in hypothesis testing and their relevance to the significance level and power of the test
- A discussion of the factors that need to be considered when estimating the optimal sample size
- The use of Altman's nomogram to estimate the required sample sizes of two groups of observations which are to be compared.
Further statistics in dentistry:
- Research designs 1
- Research designs 2
- Clinical trials 1
- Clinical trials 2
- Diagnostic tests for oral conditions
- Multiple linear regression
- Repeated measures
- Systematic reviews and meta-analyses
- Bayesian statistics
- Sherlock Holmes, evidence and evidence-based dentistry
Abstract
The principles which underlie a well-designed clinical trial were introduced in a previous paper.1 The trial should be controlled (to ensure that the appropriate comparisons are made), randomised (to avoid allocation bias) and, preferably, blinded (to obviate assessment bias). However, taken in isolation, these concepts will not necessarily ensure that meaningful conclusions can be drawn from the study. It is essential that the sample size is large enough to enable the effects of interest to be estimated precisely, and to detect any real treatment differences.
- Senior Lecturer in Statistics, Eastman Dental Institute for Oral Health Care Sciences, University College London
- Honorary Reader in Dental Public Health, Eastman Dental Institute for Oral Health Care Sciences, University College London
- Professor of Epidemiological Methods, University of Rome, La Sapienza
Correspondence to: A Petrie1
Senior Lecturer in Statistics, Biostatistics Unit, Eastman Dental Institute for Oral Health Care Sciences, University College London, 256 Gray's Inn Road, London WC1X 8LD
e-mail: a.petrie@eastman.ucl.ac.uk