[R] extRemes - reading null values

[Benjamin Modra]

Dear all,

Any suggestions on how to import null values for a GPD fit using extRemes?  For a simple timeseries, using NA or leaving the value blank raises this error:
Error in optim(init, gpd.lik, hessian = TRUE, method = method, control = list(maxit = maxit,  : 
  non-finite value supplied by optim
It will run with zero values but I assume this will skew the results (.. or not if its below the threshold????).

Many thanks, Ben



      Stay connected to the people that matter most with a smarter inbox. Take a look http://au.docs.yahoo.com/mail/smarterinbox