Re: parametric survival models

[Frank E Harrell Jr <f.harrell@vanderbilt.edu>]

Winkler Manuela wrote:
> Which of the distributions (weibull, extreme, lognormal,
> normal,loglogistic,logistic,logexponential, exponential, lograyleigh) have
> an accelerated failure time representation?
>
> Can anybody give me the formulas to calculate percentiles of survival time
> for logistic, lognormal, normal, extreme and logexponential regression
> models?
>
> Best regards
> Manuela Winkler--
> Mag. Manuela Winkler
> Institut für Botanik, Universität für Bodenkultur
> Gregor-Mendel-Str. 33, A-1180 Wien, Österreich
> Tel.: +43/1/47654-3179 oder 3171   Fax: -4504
> E-mail: mwinkler@edv1.boku.ac.at
>
> --------------------------------------------------------------------
> This message was distributed by s-news@lists.biostat.wustl.edu.  To
> unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with
> the BODY of the message:  unsubscribe s-news
You might want to look at the Quantile function in the Design package, 
which can operate on psm fits (psm is a modified survreg).
--
Frank E Harrell Jr   Professor and Chair           School of Medicine
                     Department of Biostatistics   Vanderbilt University