[ncl-talk] Lepage test in NCL

[Dennis Shea]

FTR: I am not aware of any NCL script/function that computes this
statistic.

===

Of course, NCL can sort a series (rank) so if all elements are unique the
ranks are well defined.
However, what about 'ties' ? Does the Lepage test require special handling
in these cases?

undef("lepage")
function lepage(x:numeric, ndim[1]:integer, na[1]:integer, nb[1]:integer,
....)
local xsort, nab, HK
begin
     nab   = na+nb
     xsort = *dim_pqsort_n*(x,2,nDim)     ; read documentation
      :
     HK = ....
     HK at long_name = "Lepage statistic"
     return(HK)
end

On Wed, Feb 15, 2017 at 12:28 AM, Lyndon Mark Olaguera <
olagueralyndonmark429 at gmail.com> wrote:

> Dear fellow NCL Users,
>
> Has anyone tried to do a Lepage test in ncl?
> For example,Yonetani and McCabe (1994)
>
> [Link to article] http://www.int-res.com/articles/cr/4/c004p013.pdf
>
> If yes, I'll appreciate if anyone can suggest how to do this in ncl.
>
> Many thanks,
>
> Sincerely,
>
> *Lyndon*
>
> _______________________________________________
> 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/20170216/c685df15/attachment.html