[R] fgev + negative location parameter for positive data?

From: Shubha Vishwanath Karanth <shubhak_at_ambaresearch.com>
Date: Wed, 16 Jun 2010 12:11:19 +0530


Hi R,  

I have a vector with all positive values and have fit the GEV distribution (shape parameter=0) to the data and I get the negative value of the location parameter. Is this possible?  

library(evd)

r=read.table("clipboard",header=F)[,1]

> length(r)

[1] 2087

> sum(r>=0) #All data points are positive

[1] 2087

> sum(r>=1000000) #All data points are positive

[1] 2087    

Now,

> fgev_fit=fgev(r,std.err = FALSE)

> fgev_fit
 

Call: fgev(x = r, std.err = FALSE)

Deviance: 82397.2  

Estimates

       loc scale shape

-1.977e+07 1.141e+08 1.555e-02  

Optimization Information

  Convergence: successful

  Function Evaluations: 30

  Gradient Evaluations: 5    

When all the values in the data are positive, how can the location parameter of the fit be negative? Or is it something to do with the large deviation? Please let me know, whether my assumptions are correct.      

Thanks and Regards,

Shubha Karanth  

This e-mail may contain confidential and/or privileged i...{{dropped:13}}



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. Received on Wed 16 Jun 2010 - 06:47:44 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Wed 16 Jun 2010 - 07:10:32 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive