Last year I took a short course on "Small Area Estimation" that provided a
basic understanding of the Bayesian approach to strengthening estimates for
small sub-samples in Survey Data.
I work in an applied research group, and we are interested in developing a
capability for implementing these techniques in order to enhance the quality
of our estimates for small areas and groups. Often we have a wealth of
additional information about the topic in question that can be used to fill
out this kind of modeling.
I would be very interested in feedback or proposals from anyone in a
position to provide a structured (or semi-structured) "cookbook" approach to
this kind of problem solving using WINBUGS or other low-cost technology.
This could take the form of a "distance" learning relationship, or perhaps a
short on-site introductory training session, followed by a period of
distance mentoring.
I would think that taking a sample problem from the research questions of
this type my organization is facing and working through the solution in all
its aspects could provide the "jump start" we need to begin to develop the
capability for this kind of analysis. This could be thought of as a
consulting relationship in which both a solution to a particular research
question and a tutorial on the methodology is provided.
Proximity to the Washington DC region is ideal.
Thanks very much in advance for any proposals or suggestions.
Please reply directly to:
Ed Evans
[log in to unmask] <mailto:[log in to unmask]>
202.434.6277
-------------------------------------------------------------------
To mail the BUGS list, mail to [log in to unmask]
You can search old messages at www.jiscmail.ac.uk/lists/bugs.html
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]
|