Dear Bugs-list,
this question might be simplistic, but I couldn't find any solution yet.
I would like to set up a (generalized) hierarchical linear model, with
control variables on several levels (let's say for students, classes,
schools). The desired output is the posterior predictive distribution for
future observations of student performance based on "existing" parameters.
That is, I would like to know how an existing student in an existing class
etc. performs in the future, given past data and assumed control variates
(-> to obtain partial pooling). I think the case is quite simple, if I can
draw new population parameters from the respective hyperprior distributions
to incorporate class- and school-level covariates. However, then (I think) I
would predict the performance of a "new student/class" etc., not of a
"particular/existing student".
I apologize that the problem description is quite generic, but I would like
to know whether these results are obtainable at all before putting too much
work into it.
A short email with some suggestions or references on how to work this out in
theory and/or with WinBUGS would be great!
Many thanks in advance!!
Andreas
--
_________________________________
Andreas Schertzinger
Mobile: +49 (177) 277-4663
Email: [log in to unmask]
CAMPUS ADDRESS
Schlossplatz 19 - Apt F203
76131 Karlsruhe / Germany
Phone: +49 (721) 530-7957
_________________________________
-------------------------------------------------------------------
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
|