Date: Mon, 18 Jun 2007 13:26:29 -0300
Reply-To: Hector Maletta <firstname.lastname@example.org>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Hector Maletta <email@example.com>
Subject: Aalen additive survival regression method
Content-Type: text/plain; charset="us-ascii"
I am resending this after getting no echo from a previous posting. Perhaps
some kindly and knowledgeable soul may respond now.
I have been hearing now and then about Aalen's additive regression for event
history analysis for years, but never actually used it or looked into it in
detail. It was proposed by the author in his articles of 1989 (A linear
regression model for the analysis of life times. Statistics in Medicine,
8:907-925) and 1993 (Further results on the non-parametric linear regression
model in survival analysis. Statistics in Medicine 12:1569-1588). There is a
freeware beta package to apply it with S-Plus and R developed by Aalen and
others at the University of Oslo (see
http://www.med.uio.no/imb/stat/addreg/). My questions are:
1. May somebody succinctly explain what are the differences and the
advantages/disadvantages of this approach relative to Cox regression (with
or without time-dependent covariates)?
2. Can this Aalen method be implemented in SPSS without too much programming
effort? Or has it been already implemented?
Thanks in advance.