I have two sets of 14 data points that lie on two different estimated
survivorship functions S(t).
One of these groups is a control, the other has been treated, and there are
Type I censored
observations.
If possible, I would like to model these data using the generalized gamma
function
f(t)=(beta/Gam[k])*(t^(beta*k-1)/alpha^(beta*k))*exp(-(t/alpha)^beta) (p.
237 ff in Lawless, for
example) by calculating the posterior densities for the parameters and using
either the means or
medians as the the parameter estimates.
For the generalized gamma, the survivorship function S(t) is an integral of
the incomplete
gamma function. The likelihood function for censored observations turns out
to involve these
integrals in a non-trivial way, so a standard frequentist analysis is
difficult.
What would be the best way to approach this problem using B.U.G.S.?
My apologies if this turns out to be trivial.
David Alan Paul
Battelle Memorial Institute - SDAS
[log in to unmask]
614-424-3176
614-424-4611 (fax)
-------------------------------------------------------------------
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
|