# [ncl-talk] coherence

Dennis Shea shea at ucar.edu
Thu Oct 2 08:17:31 MDT 2014

```Yes.

The "specxy_anal function uses ezfftf.

On Thu, Oct 2, 2014 at 8:01 AM, Xi Chang <xi.chang01 at gmail.com> wrote:

> Hi Dennis and NCL,
>
> In this case, I compute the coherence from the "ezfftf" function for two
> variables X and Y.
>
> how does the dof is computet in specxy_anal? can I use directly the dof
> produced from the "specxy_anal" function for my case?
>
> Thanks
>
> On Thu, Oct 2, 2014 at 3:49 PM, Dennis Shea <shea at ucar.edu> wrote:
>
>> The dof is returned to you
>>
>> dof = *specxy_anal* (x,y,iopt,jave,pct)
>>
>> ^^^
>>
>> On Tue, Sep 30, 2014 at 1:37 PM, Xi Chang <xi.chang01 at gmail.com> wrote:
>>
>>> Dear Dennis and NCL
>>>
>>> thank you for the example. However i cant fint a way how to determine
>>> the degree of freedom (df) in this formulation. I just read the paper and
>>> did not find any info. How if my series is strongly auttocorrelated?
>>> thank you for any hint.
>>>
>>> Chang
>>>
>>>
>>>
>>>
>>> On Tuesday, September 30, 2014, Dennis Shea <shea at ucar.edu> wrote:
>>>
>>>>
>>>> http://www.ncl.ucar.edu/Document/Functions/Built-in/specxy_anal.shtml
>>>>
>>>> there is a whole section on it .... including references.
>>>>
>>>> On Tue, Sep 30, 2014 at 1:12 PM, Xi Chang <xi.chang01 at gmail.com> wrote:
>>>>
>>>>> Hi everyone,
>>>>> would you please suggest me how to determine significance from the
>>>>> coherence resulting from two variables? just cant find any example how to
>>>>> do that.
>>>>>
>>>>> Really appreciate for any hints.
>>>>> thank you
>>>>>
>>>>> Chang
>>>>> _______________________________________________
>>>>> ncl-talk mailing list
>>>>> List instructions, subscriber options, unsubscribe:
>>>>> http://mailman.ucar.edu/mailman/listinfo/ncl-talk
>>>>>
>>>>>
>>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...