On Tue, 23 Sep 2008, Terry Therneau wrote:
I don't have a copy of that issue of Biometrics so can't answer the question
directly, but I can tell you what survfit does do. I'm moderately sure that it
is the method found in said paper.
I was asked this (about the R version) a couple of weeks ago.
It is the same in spirit but not in letter. Brookmeyer & Crowley invert a
confidence interval for the median, but they create the confidence
interval on the probability scale, not a transformed scale.
Beware! The quality of this procedure depends on the quality of the original
pointwise bands. There are several methods to generate the bands, and lots of
papers comparing them.
empirical likelihood (Thomas and Grunkmeier): excellent
bootstrap methods: okay to excellent, depending on details of how its done
transformed CI, log, logit, log-log, etc: very good. Different papers rank
different ones of these first in the list.
plain, S(t) +- 1.96* std: poor
There is no excuse for a modern package to use the last of these, given the
literature. Guess which one is the default in SAS?
Probably the one used by Brookmeyer & Crowley.
-thomas
Thomas Lumley Assoc. Professor, Biostatistics
tlumley@u.washington.edu University of Washington, Seattle
|