$McMaster University$

Graduate Program in Statistics

SPEAKER:: Lehana Thabane; Department of Clinical Epidemiology and Biostatistics; McMaster University

ABSTRACT:: In this talk, I present a Bayesian approach to estimation of the number needed to treat (NNT). The use of $NNT$ as a measure of clinical benefit is now becoming commonplace. Various methods of estimation have been proposed, but none of them seem to provide entirely good estimates. Much still remains to be done to understand the statistical properties of $NNT$. Here, I derive the posterior distribution of $NNT$ and use simulations to investigate the general behaviour of the distribution. The posterior mode of the distribution is proposed as a point estimate and results are compared with the conventional method of estimation of NNT done by inversion. The presentation will be geared towards graduate students, with examples to illustrate the different measures of clinical benefit.

About the Speaker: Dr. Thabane is a biostatistician at the Center for Evaluation of Medicines. He is also a clinical trial methodologist with interests in various areas that include nephrology, cancer research, respiratory, cardiology, to mention a few. His areas of statistics research interests include regression models, multivariate analysis, clinical trials, Bayesian & non-Bayesian inference, decision analysis, meta-analysis, design & analysis of experiments, prediction analysis and statistical consulting.
Dr. Thabane did his PhD studies in Statistics (1994 -1998) in the Department of Statistical & Actuarial Sciences at the University of Western Ontario, Canada and MSc in Statistics (1992-1993) in the Department of Probability and Statistics at Sheffield University, England. He obtained his BSc (1986-1990) from the National University of Lesotho. Dr. Thabane comes to his present position from St. Francis Xavier University (STFXU), Nova Scotia where he was Assistant Professor (tenure-track) from 1999-2001. While at STFXU he held various administrative positions as a University Senate Committee member. Prior to this, Dr. Thabane also held Assistant Professorship position (1998-1999) and Lecturership position (1997-1998) in the Department of Statistical & Actuarial Sciences at the University of Western Ontario.

Transparencies: The transparencies are available in pdf format or postscript format.
Note that you may experience a problem with some of the fonts and one page does not seem to be visible at all in the pdf version. I am trying to rectify the problem.

References

Since this is a biostatistics talk, all of the following are from journals held in the Health Sciences Library.

A. Laupacis, D.L. Sackett and R.S. Roberts (1988) An assessment of clinically useful measures of the consequences of treatment. New England Journal of Medicine, 318, 1728-1733.
D.G. Altman (1998) Confidence Intervals for the number needed to treat. British Medical Journal, 317, 1309-12.
D.G. Altman and P.K. Andersen (1999) Calculating the number needed to treat where the outcome is time to an event. British Medical Journal 319, 1492-95.
Walter SD. Number needed to treat (NNT): estimation of a measure of clinical benefit. Statistics in Medicine 20, 3947-62 (2001).
R.J. Cook and D.L. Sackett (1995) The number needed to treat: a clinically useful measure of effect. British Medical Journal, 310, 452-54.
D.L. Sackett (1996) On some clinically useful measures of the effects of treatment. Evidenced-Based Medicine 1, 37-38.
G. Chatellier et al. (1999) The number needed to treat: A clinically useful nomogram in its context. British Medical Journal, 312, 426-29.