R help - Jan 2011 - fgev_error_matrix_singular

Hello everyone,

I am using fgev from evd package to fitting my data with general  
extreme value distribution. The command I used is simple: y <- fgev(x).
The error is "observed information matrix is singular;" How can I  
solve these problem. I tried all methods in optim and it did not work.  
I fixed values for scale, location and shape. This works, but I have  
lots of different dataset to fit, so is there any automatic ways to  
solve the error? Thanks!

jinrui,

See ?try in order to get the automated process going and for ignoring or 
separately post-processing stuff where the method does not work.

Uwe Ligges


On 15.01.2011 21:48, Jinrui Xu wrote:
>
> Hello everyone,
>
> I am using fgev from evd package to fitting my data with general extreme
> value distribution. The command I used is simple: y <- fgev(x).
> The error is "observed information matrix is singular;" How can I
solve
> these problem. I tried all methods in optim and it did not work. I fixed
> values for scale, location and shape. This works, but I have lots of
> different dataset to fit, so is there any automatic ways to solve the
> error? Thanks!
>
> jinrui,
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.