[Grad-postdoc-assn] About Verification Package

waqar younas vickyqau at gmail.com
Thu Feb 10 13:28:54 MST 2011


Hi
I am Waqar Younas, PhD student at UNBC, Canada. I was selected in 2010
summer colloquium but i could not come due to visa problems. Right now i am
using R. I learn about the basic data handling in R. I want to use R
verification package.  I have my daily data of obs and prediction in this
format. The obs data has dimension of 120, 396 where 120 is the lead time
and 396 is the total initial time. Whereas the prediction data has the
dimension of 120, 396, 10 where first two dimensions are same as obs data
dimension and the third dimension is of ensemble member. Also i already
removed daily climatology mean from my data. To get probabilistic skill, i
need to change my obs data into binary data set and prediction data in
probabilities. For that i need to use the verify function of verification
package in R (I think my understanding is right). But when i apply this
function, it gives some error as

*If baseline is not included, baseline values  will be calculated from the
sample obs.
Error in e1[[1L]] : subscript out of bounds
In addition: Warning messages:
1: In is.finite(obs) & is.finite(pred) :
  longer object length is not a multiple of shorter object length
2: In max(pred) : no non-missing arguments to max; returning -Inf
3: In min(pred) : no non-missing arguments to min; returning Inf
*
I do not know how to solve this function. Can anyone help me in this regard?


-- 
Best Regards

Waqar Younas
PhD Candidate
Natural Resources and Environmental Studies (NRES)
University of Northern British Columbia (UNBC)
Canada
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.ucar.edu/pipermail/grad-postdoc-assn/attachments/20110210/f224affa/attachment.html 


More information about the Grad-postdoc-assn mailing list