Print

Print


Dear Andrew,
Such a distribution certainly corresponds to the Bayesian view of 
statistics, that is, that a confidence interval (or credible 
interval) is a posterior distribution of the likely true results. If 
you wanted empirical evidence of the idea that values near then 
centre are more likely than values near the limits, then you could 
look at results from multicentre trials, and the distribution of 
results between centres. But the result is pretty predictable ...
Paul Glasziou

At 27/03/2006, Andrew Jull wrote:
>In 'User's Guides to the Medical Literature' the fine book edited by 
>Guyatt and Rennie it is noted that values further away from the 
>point estimate are less probable than those closer to the point 
>estimate eg. With a 95%CI 1-16%, the extreme values in the 
>confidence interval are less likely to occur than those around the 
>observed point estimate eg 8%. I have seen this stated elsewhere, 
>and while it makes sense intuitively I have not seen any evidence to 
>support this view. Can anyone direct me to the evidence? Also, does 
>it follow that if a trial is repeated X times, the observed point 
>estimate for each trial be normally distributed within the 
>confidence interval of an adequately powered trial?
>
>
>Andrew Jull RN MA (Appl)
>Research Fellow
>Clinical Trials Research Unit
>School of Population Health
>University of Auckland
>Private Bag 92019
>AUCKLAND
>Phone:  +64 9 373-7599 extn 84744         Fax:      +64 9 373-1710
>Email: 
><mailto:[log in to unmask]>[log in to unmask] 
>Web:    www.ctru.auckland.ac.nz
>
>
>

Paul Glasziou
Department of Primary Health Care &
Director, Centre for Evidence-Based Practice, Oxford
ph: 44-1865-227055