[ncl-talk] dim_median_n

[Alan Brammer]

Assume so, based on your result and that that's how the median should be
calculated.
I'd be surprised if any program out there didn't calculate it this way.


On Sun, Sep 20, 2015 at 3:08 PM, jbuzan <jbuzan at purdue.edu> wrote:

> Hi Alan,
>
> Is this how NCL calculates the median?
> I think the code is in the binaries, because I didn’t see it in the
> contributed/shea_util.
>
> -Jonathan
>
>
> On Sep 20, 2015, at 3:00 PM, Alan Brammer <abrammer at albany.edu> wrote:
>
> From wikipedia <https://en.wikipedia.org/wiki/Median>.
>  If there is an even number of observations, then there is no single
> middle value; the median is then usually defined to be the mean
> <https://en.wikipedia.org/wiki/Arithmetic_mean> of the two middle values
> [1] <https://en.wikipedia.org/wiki/Median#cite_note-StatisticalMedian-1>
> [2] <https://en.wikipedia.org/wiki/Median#cite_note-2> (the median of {3,
> 5, 7, 9} is (5 + 7) / 2 = 6), which corresponds to interpreting the median
> as the fully trimmed <https://en.wikipedia.org/wiki/Trimmed_estimator>
> mid-range <https://en.wikipedia.org/wiki/Mid-range>.
>
>
> Alan.
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.ucar.edu/pipermail/ncl-talk/attachments/20150920/277cd80f/attachment.html