[R] Problems with fitdistr

[Peter Ehlers]

vikrant wrote:
> Yes I do have zeros in my data. But I m not able to understand y inclusion of
> zeros results in error messages, because range for x in weibull distribution
> is x>=0. Can you please clarify this doubt? 

Well, that's a matter of definition (and is a problem if
the shape parameter is <= 1).

fitdistr() seems to take the range to be x > 0.
As I said, when no start values are provided, fitdistr()
will have a 'problem' with zeros because the first thing
it does is log(x), easy to see in the code.

But try pelwei() in package lmom, as suggested by
Jonathan Hosking.

  -Peter Ehlers