[ncl-talk] t-test

[Serena Illig]

Dear all,

I checked, just out of curiosity.
As far as I understood, the time series on Fig1 are smoothed (spatial)
correlation. They call it pattern correlation coefficients (maybe simply:
https://www.ncl.ucar.edu/Document/Functions/Contributed/pattern_cor.shtml).
So they are correlation coefficients and the threshold level for the 90%
significance (cf. caption Fig. 1) are simply the threshold associated with
the significance of the correlation (using a 2 tailed t-test with n-2,
maybe simply:
https://www.ncl.ucar.edu/Document/Functions/Built-in/rtest.shtml).
I hope this helps.

Serena

.¸. , . .·´¯`·
 ><(((º>     `·.¸.·´¯`·...¸><(((º>¸.¸. , . .·´¯`· ><(((º> .
`·.¸.·´¯`·...¸><(((º>                                                  .

  .
  Serena ILLIG-THEVENIN       LEGOS/IRD       .
                                                                           .
             University of Cape Town - UCT          .
             Department of Oceanography           .
             Private Bag X3, Rondebosch  7701   .
             SOUTH AFRICA                                  .

.
   E-mail     : *serena.illig at ird.fr <serena.illig at ird.fr> *
             .
   Web-site : http://sillig.free.fr                             .
   Fax         : +27 21 650 3979                          .
                                                                    .
                                                 <º)))><..·´



On Thu, Aug 9, 2018 at 8:08 AM Morteza Qadimi <mqadimi at yahoo.com> wrote:

> Hi,
>
> I need to separate CP and EP El Niño years by the method used in a paper (*A
> new method to classify ENSO events into eastern and central Pacific types)*.
> I have obtained an (1D) EOF-based pattern correlation coefficient array
> (say EPC1). Then the author says:
>
> " The EP type El Niño is defined as the case when the EPC1 index is equal
> to or greater than 0.79 which is significant at the 90% confidence level
> from the two-tailed Student’s t-test."
>
> How author has calculated 0.79? Does NCL has a function for that? It has
> been 2 weeks i am asking for a solution. please help me.
> _______________________________________________
> ncl-talk mailing list
> ncl-talk at ucar.edu
> List instructions, subscriber options, unsubscribe:
> http://mailman.ucar.edu/mailman/listinfo/ncl-talk
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.ucar.edu/pipermail/ncl-talk/attachments/20180813/1425c577/attachment.html>