Dear Laszlo (and BUGS list members - since I hope this is of perhaps
wider interest to others on the list)
We have been implementing models for combining individual and aggregated
data in both R and WinBUGS as part of an ongoing research project. Our
project web site is www.bias-project.org.uk and the software page on
that site contains an R package and set of WinBUGS examples to implement
these models. The models are described in more detail in a paper about
to appear in Statistics in Medicine (by Jackson, Best, Richardson -
pre-publication version available from the web site). The models are
similar to some of those discussed by Wakefield (2004).
We are also currently working with Jon Wakefield to implement in WinBUGS
the 'convolution' model for aggregate data that he describes in his 2004
(JRSSA) paper, and an extension of the model to include small samples of
case-control data for some groups/areas. These will be made available on
the bias-project web site as soon as they are ready.
Best wishes
Nicky
-----Original Message-----
From: (The BUGS software mailing list) [mailto:[log in to unmask]] On
Behalf Of Laszlo Molnar
Sent: 23 February 2006 11:46
To: [log in to unmask]
Subject: ecological fallacy
Dear Sirs,
I've read some papers on the ecological fallacy problem written by
Wakefield et al. etc.
Let us suppose that we have simple aggregated data (i.e. thematic maps).
At first we may want to derive conclusions from the aggregated (mapped)
data.
We may then have questions if the conclusions derived are valid.
Then we may want to amend the conclusion derived from the ecological
data with survey data.
Let us suppose that we have also a simple and relatively small sample
survey with some questions and answers in it.
It is possible to combine ecological, aggregated data with individual,
survey data and amend the results with Bayesian reasoning.
Is anybody out there who has any idea about how to combine the
aggregated data with for example 5 % individual level (i.e. survey) data
in terms of an EXAMPLE SCRIPT script for perhaps PKBUGS?
It would be greatly appreciated if someone could send me a SIMPLE DATA
and SCRIPT EXAMPLE of perhaps BUGS or
PKBUGS or R to look and see how it works for managing the ecological
fallacy problem.
With best regards
Laszlo Molnar MD MSc
Szent Imre h u 52
1204 Budapest
Hungary
Tel: +36-1-421-0991
FAX: +36-1-421-5006
M: +36-20-9552-782
E-mail: [log in to unmask]
-------------------------------------------------------------------
This list is for discussion of modelling issues and the BUGS software.
For help with crashes and error messages, first mail
[log in to unmask]
To mail the BUGS list, mail to [log in to unmask]
Before mailing, please check the archive at
www.jiscmail.ac.uk/lists/bugs.html
Please do not mail attachments to the list.
To leave the BUGS list, send LEAVE BUGS to [log in to unmask]
If this fails, mail [log in to unmask], NOT the whole list
-------------------------------------------------------------------
This list is for discussion of modelling issues and the BUGS software.
For help with crashes and error messages, first mail [log in to unmask]
To mail the BUGS list, mail to [log in to unmask]
Before mailing, please check the archive at www.jiscmail.ac.uk/lists/bugs.html
Please do not mail attachments to the list.
To leave the BUGS list, send LEAVE BUGS to [log in to unmask]
If this fails, mail [log in to unmask], NOT the whole list
|