Thank you to all,
The responses are very helpful and I have been busy downloading. The free tools look very impressive. I was delighted to find Stata very reasonable on a student purchase. I have mostly used SPSS in the past but note Stata has a great training package so I may take the leap. I tried CMA a few months ago, it looked so easy but it went hopelessly wrong near the end, likely I messed with the options and as a beginner couldn’t map my way back.
Warmest regards,
Amy
From: Evidence based health (EBH) [mailto:[log in to unmask]] On Behalf Of Ahmed M. Abou-Setta, MD
Sent: 20 January 2011 01:28 PM
To: [log in to unmask]
Subject: Re: Meta analysis software
Hi Amy,
Welcome to the world of meta-analysis... and all the head-aches that come with it. Meta-analyzing data is a powerful way of combining data from different data sets but at the same time is usually more complicated that most people imagine. There are certain rules, different approaches, different schools of logic, etc. just as any other form of statistical analysis.
Having said that, as a novice needing a program for scientific, non-commercial purposes then RevMan may be your best bet. The Cochrane Collaboration does a good job in keeping it simple but flexible (sort of). The forest plots are easy to create and present. (FREE)
Comprehensive Meta-Analysis (CMA) is a powerful tool and very flexible. If you don’t know you are doing then stay away from it because you can easily get the options wrong. Also when I last used it, I had major issues with its forest plots, which I was told would be improved in the next version (still waiting for that new version to come out). ($$$)
Meta-Analyst, from the last time I checked was still in Beta-testing, and so I wouldn’t recommend that at the moment, but it does offer the option of running (limited) Bayesian analyses. (FREE)
If you are doing Bayesian analyses, then your best choices would probably be WinBUGS or OpenBUGS. Powerful programs for Bayesian meta-analyses. (FREE)
If you are running Office 2003, then there is a free Excel-based program called Meta-analysis with Explanation (MIX). The Excel 2003 version is free, the 2007 cost money. (2003 à FREE; 2007 à $$)
If you already have SPSS, SAS, STATA, R, and probably others and are comfortable with them, then there are codes that you can run to allow you to run meta-analyses in these general statistical packages.
Of course, the decision you have to make is how much you want to invest (time and money) and what you want the program to do for you.
Good luck.
Ahmed
----------------------------------------------------------------------------------------------
Ahmed M. Abou-Setta, MD, PhD
Post-doctoral Fellow/ Project Co-ordinator
University of Alberta Evidence-based Practice Centre (UA-EPC)
Alberta Research Centre for Health Evidence (ARCHE)
University of Alberta
Aberhart Centre One, Room 8412
11402 University Avenue
Edmonton, Alberta
CANADA T6G 2J3
Tel: (780) 492-6248
Fax: (780) 407-6435
E-mail: [log in to unmask]
Website: http://www.ualberta.ca/ARCHE/
From: Evidence based health (EBH) [mailto:[log in to unmask]] On Behalf Of Dr. Amy Price
Sent: January 20, 2011 9:04 AM
To: [log in to unmask]
Subject: Meta analysis software
Dear all,
I am interested in finding meta analysis software that is easy to learn/use and cost effective and would work when collaborating with others as I wouldn’t want to be the sole MAC in a PC room even if my technology outperformed others integration may be an issue. I also don’t want to pay for bells and whistles I would likely never use. Meta analysis is useful to me for personal use to get a more objective view of the evidence. I find that some researchers write literature reviews like a God but their methods and evidence need work. We learned meta analysis on a DOS based system at a basic level for the MSc. It was relatively easy to use but the tiny black on white DOS screen was brutal http://www.researchmethodsarena.com/dstat-version-110-9781563211386
I have looked at Cochrane, it is free, they offer training and they seem to specialise in offering evidence http://ims.cochrane.org/revman
CMA, slick graphics, fairly expensive http://www.meta-analysis.com/pages/why_use.html
There are also Macros that link from SPSS Would they be useful? http://mason.gmu.edu/~dwilsonb/scrshots/screenshot2.html
There are others I have looked at which may be thorough and professional but I am more at where is the on button stage...I really appreciate your views on this. I have downloaded and shared the Catmanager software link from CEBM and the critical appraisal sheets plus the questionnaire links that Ash supplied were excellent and I have shared these also. I have applied to an EBHC program but in the meantime is there a beginners site(s) the group could suggest where I could learn and become better prepared so I could give all my attention to assignments? I am not an MD. I want to learn EBM as because the communication styles and research emphasis differs there are effective interventions that not practised because of low EBM standards and ineffective protocols which are readily accepted because they are well written. It would be great to share reasoning for adoption in a logical way and learn what is required for my own projects...
Best regards
Amy
Amy Price
Http://empower2go.org
Building Brain Potential