[ncl-talk] t-test algorithm?

[Dennis Shea]

Hi Leslie,

The (Student) t-test used by NCL is identical to that in Numerical Recipies.

Se the chapter:   Statistical Description of Data
            section:   Do Two Distributions Have the Same Means or Variances



On Mon, Nov 7, 2016 at 9:26 AM, Lesley Smith - NOAA Affiliate <
lesley.l.smith at noaa.gov> wrote:

> Hi ncl-talk,
> I was using your excellent function ttest with tval_opt = True
> and I'm having a little trouble interpretting the t-values.
> Should the t-values scale with the values of the statistical probabilities?
> Is there a relevant formula or algorithm somewhere that I could look at?
> Thanks for any tips!
> -Lesley
>
> ------------------------------------------------------------
> -----------------------
> Lesley L. Smith, Ph.D.
> Affiliation: CIRES
> Phone: (303) 497-6172
> E-mail: lesley.l.smith at noaa.gov
> Attribution and Predictability Assessments Team
> NOAA/ESRL Physical Sciences Division
> R/PSD1 325 Broadway
> Boulder, CO 80305
>
> _______________________________________________
> 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/20161107/7f994aa0/attachment.html