[R] SSweibull

Thomas Lumley tlumley at u.washington.edu
Wed Jun 27 00:53:24 CEST 2001

On Tue, 26 Jun 2001, Dr. Mirko Luedde wrote:

> Dear Prof Ripley,
> there was no (direct) answer to any of my questions in your post, but
> I think I'm getting the idea! Sorry for my ignorance.
> And I still seem to have a gross misunderstanding about the use of
> `SSweibull(nls)'.
> Is it simply a means to calculate the Weibull
> distribution?
> What's the difference to `pweibull', then?
> Which means could help me estimating the Weibull parameters from
> empirical data?

The survreg() function in the survival package fits Weibull distributions
(and accelarated failure models) to (possibly censored)  data, that is if
your data have a Weibull distribution. This is a location-scale model
parametrised so that (log(y)-mu)/scale has the cdf 1-exp(-exp(y)), the
natural accelerated failure parametrisation rather than the proportional
hazards one.

SSweibull is designed to help with fitting the Weibull growth curve model
to empirical data. This is not the same as fitting a Weibull distribution.
SSweibull is a self-starting (thus the SS) model for use with nls().
That is, nls()  allows you to fit complicated nonlinear models, most of
which require good starting estimates of parameters. The self-starting
models can guess good starting values for nls().


Thomas Lumley			Asst. Professor, Biostatistics
tlumley at u.washington.edu	University of Washington, Seattle

r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list