[R] interpreting Weibull survival regression

[Prof Brian Ripley]

On Mon, 27 Jun 2005, Göran Broström wrote:

> On Sun, Jun 26, 2005 at 11:28:04PM +0100, Prof Brian Ripley wrote:
>>> Here gamma is the usual gamma function, see ?gamma. (I notice in the R
>>> documentation of the Weibull distribution that "E(X) = b Gamma(1+1/a)",
>>> which is an error; the G should be g (lowercase).)
>>
>> It is not an error.  R's function gamma() is said to implement
>> \eqn{\Gamma}{Gamma}: `see ?gamma'!
>
> I see; it's supposed to be mathematics, not R code (of course, since a
> '*' otherwise is missing!). But then the documentation is at least
> somewhat inconsistent, because in the variance expression, 'gamma' is used.

Yes, in the variance expression \Gamma is transliterated as 'gamma'.  That 
is the only case I can find (e.g. the Beta,Chiqsuare,Fdist,GammaDist,
NegBinomial,Tdist Rd files).  I've made the variance expression 
consistent.

-- 
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