[19111] in s-news-athena
[S] CI's for a genralized logistic model
daemon@ATHENA.MIT.EDU (Gabriel Escarela)
Sat Sep 4 13:23:16 1999
Message-Id: <19990904171830.18177.rocketmail@web127.yahoomail.com>
Date: Sat, 4 Sep 1999 10:18:30 -0700 (PDT)
From: Gabriel Escarela <escarela@yahoo.com>
To: s-news@wubios.wustl.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Dear All,
I would like to know if any of you has created an S-function that
finds confidence bands for the following generalised logistic model
(Cox and Snell, "Analysis of Binary Data", 1989, pp. 155-157)
p_j = exp(b_j*x)/(exp(b_1*x) + ... + exp(b_J*x))
when the estimates and the variance-covariance matrix of the
parameters b_j (j=1,...,J) are given and x is the vector of
covariates.
Several parameters are involved in the formula. If somebody can
suggest a methodology to find good confidence bands for p_j I would
be very grateful.
Thanks in advance.
Gabriel
===
Gabriel Escarela (Mr)
Centre for Applied Statistics
Lancaster University, UK
g.escarela@lancaster.ac.uk
escarela@yahoo.com
http://www.lancs.ac.uk/postgrad/escarela/
__________________________________________________
Do You Yahoo!?
Bid and sell for free at http://auctions.yahoo.com
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
