Nowhere. They are not in Cox's (1972) paper either! (One place is in the
discussion of that paper, but the point is that they are an orthogonal
concept to partial likelihood estimation of the coefficients.)
You use survfit() on a coxph fit object to compute them.
On Sun, 1 Feb 2004, Jim Clark wrote:
> Where are the estimates of the baseline hazard in the output of coxph?
>
> Thanks,
> Jim
>
>
> James S. Clark
> H.L. Blomquist Professor
> Department of Biology and Nicholas School of the Environment
> Duke University
> Durham, NC 27708
> Biology: http://www.biology.duke.edu/research_by_area/eeob/clark.html
> Center on Global Change: http://www.env.duke.edu/cgc/
> Ecology Program: http://www.ecology.duke.edu/
--
Brian D. Ripley, ripley at stats.ox.ac.uk
Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/
University of Oxford, Tel: +44 1865 272861 (self)
1 South Parks Road, +44 1865 272866 (PA)
Oxford OX1 3TG, UK Fax: +44 1865 272595