Dear Roger
A very early recognition of the difference between the two types of inference (your 1 and 2) is to be found in
Yates, F. and W. G. Cochran (1938). "The analysis of groups of experiments." Journal of Agricultural Science 28(4): 556-580.
This is an early paper on meta-analysis (although, of course they don't call it that)
They write
.“..it is usually impossible to secure a set of sites selected entirely at random…the deliberate inclusion of sites representing extreme conditions may be of value. Lack of randomness is then only harmful in so far as it results in the omission of certain types and in the consequent arbitrary restriction of the range of conditions. In this respect scientific research is easier than technical research
What they mean is that it is easier to establish causality (that treatments can have an effect) than to predict (what the effects will be in given circumstances)
See Senn, S. J. (2004). "Added Values: Controversies concerning randomization and additivity in clinical trials." Statistics in Medicine 23(24): 3729-3753. for a discussion.
Stephen
Stephen Senn
Professor of Statistics
School of Mathematics and Statistics
Direct line: +44 (0)141 330 5141
Fax: +44 (0)141 330 4814
Private Webpage: http://www.senns.demon.co.uk/home.html
University of Glasgow
15 University Gardens
Glasgow G12 8QW
The University of Glasgow, charity number SC004401
________________________________________
From: Evidence based health (EBH) [[log in to unmask]] On Behalf Of Roger Kerry [[log in to unmask]]
Sent: 30 January 2011 22:00
To: [log in to unmask]
Subject: Re: Can RCT help establish causation?
Dear Ben
If it helps, here is another humble opinion. I think the challenge of causation can be considered in two parts:
1) causation established (or not) in the trial, and
2) the causal inference outside the trial (as many have already discussed).
With reference to 1), framing RCTs as Mill's Methods of Difference (MMOD, philosopher J.S. Mill from his System of Logic) allows a logical appreciation that, given the right conditions, causation can be established. It seems that RCTs have the ability to offer the 'right' conditions, and are therefore a good example of MMOD. This might satisfy your request for a LOGICAL explanation, and help support the scientific activity of conducting RCTs. However, this still does not address Hume's concerns, nor the real challenge for EBM.
EBM is concerned as much with 2), and I think this is where a greater challenge lies (appreciating what others have already said). It seems much harder to provide a LOGICAL (formal or informal) framework which allows causation to 'travel' from a trial to another tempero-spatially distant point (i.e. an intervention decision with a single patient). Even a PHILOSOPHICAL explanation is difficult. I think Nancy Cartwright has probably given this area as good a treatment as anyone so far, philosophically (e.g. http://personal.lse.ac.uk/cartwrig/PDFVarious/CartwrightMunroLimitationsof%20randomizedcontrolledtrials%20in%20predicting%20effectiveness.pdf , and her book 'Hunting Causes and Using Them').
Back to Hume for a moment. It seems (bear in mind I am a complete novice regarding Hume...) that although he concluded that a relationship between a 'cause' and 'effect' could not be established (they are distinct events), this troubled him greatly as he "knew" such a thing must exist. But since, no one has been able to provide a satisfactory explanation.
I am sorry I can offer no more, however this very point is the subject of a research project I am presently involved in (http://www.nottingham.ac.uk/philosophy/people/apxrk ). If you can wait another 3 or 4 years I might be able to give a little more help with your profoundly relevant question!
Best
Roger
Roger Kerry FMACP MSc MCSP
Associate Professor
Postgraduate Manual Therapy Leader
Division of Physiotherapy Education<http://www.nottingham.ac.uk/nmp/people/roger.kerry> / Department of Philosophy (Research Student)<http://www.nottingham.ac.uk/philosophy/people/apxrk>
University of Nottingham
Clinical Sciences Building
Hucknall Road
Nottingham, UK
NG5 1PB
Tel: +44(0)115 82 31790
Fax: +44(0)115 82 31791
[cid:image001.gif@01CBC0C8.E22B6CC0]
[cid:image004.png@01CBC0C9.25EFC0A0]<http://workspace.nottingham.ac.uk/display/PMHWIG/Home>
-----Original Message-----
From: Evidence based health (EBH) [mailto:[log in to unmask]] On Behalf Of Michael Stuart
Sent: 28 January 2011 16:29
To: [log in to unmask]
Subject: Re: Can RCT help establish causation?
The issue of causality and RCTs versus observational studies comes up
often in our discussions. We have summarized our thoughts and some key
references at
http://www.delfini.org/Delfini_Primer_Problems_Obs_Interventions.pdf
Best, Mike
> Dear all
> I'd like to post this question to the group that I have been
> thinking about for some time... Is there a scientific method that
> allows us to LOGICALLY distinguish the cause-effect from the
> coincidence? David Hume, one of the most influential philosophers of
> all times, concluded that there is no such a method. This was
> before RCTs were "invented". Many people have made cogent arguments
> that (a well done) RCT is the ONLY method that can allow us to draw
> the inferences about causation. Because this is not possible in the
> observational studies, RCTs are considered (all other things being
> equal) to provide more credible evidence than non-RCTs. However,
> some philosophers have challenged this supposedly unique feature of
> RCT- they claim that RCTs cannot (on theoretical and logical
> ground) establish the relationship between the cause and effect any
> better than non-RCTs. I would appreciate some thoughts from the group:
> 1. Can RCT distinguish between the cause and effect vs.
> coincidences? (under which -theoretical- conditions?)
> If the answer is "no", is there any other method that can help
> establish the cause and effect relationship?
> I believe the answer to this question is of profound relevance to EBM.
>
> Thanks
> Ben Djulbegovic
>
>
>
>
Michael E Stuart MD
President and Medical Director, Delfini Group
Clinical Asst Professor, UW School of Medicine
6831 31st Ave N.E.
Seattle, Washington 98115
206-854-3680 Mobile Phone
206-527-6146 Home Office
[log in to unmask]
This message and any attachment are intended solely for the addressee and may contain confidential information. If you have received this message in error, please send it back to me, and immediately delete it. Please do not use, copy or disclose the information contained in this message or in any attachment. Any views or opinions expressed by the author of this email do not necessarily reflect the views of the University of Nottingham.
This message has been checked for viruses but the contents of an attachment may still contain software viruses which could damage your computer system: you are advised to perform your own checks. Email communications with the University of Nottingham may be monitored as permitted by UK legislation.
|