Nikos Padazis
> Thanx to Antoine and Nick for their useful responses
> and code. As far as it concerns the Weibull p.d.f. I
> just copied the formula from D. Collett's book
> "Modelling survival data in medical research" page
> 110.
The formula you copied from Collett was in effect
p.d.f. :
f(t)=lambda*gamma*t^(gamma-1)*exp(-lambda*t^gamma)
The price of this formula is,
so far as I can see, complicated dimensions
and therefore units for the scale parameter
lambda.
You can see the consequence in Collett's
formula for the mean on p.111.
I'll record a preference for parameterisations
which allow parameters to be assigned units
easily.
Nick
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
