[1] Numerical Recipes [Fortran, 1986] p486 describes the test.
The t-statistic used is reasonable "even if the binormal
assumption is not well substantiated"
[2] Climatic Change, WMO Tech Note 79, p66
says "tval" formula is good for xn>=8
Wang, Yi wrote:
> Hi Folks:
>
> I just want to know how reliable rtest is when my sample is only 10. I can
> get a 90% level of -/+ 0.55 and a 80% level of -/+ 0.45.
>
> The website says it should be at least 8.
>
> Does the test assume binomial or normal distributions?
>
> Thanks,
>
_______________________________________________
ncl-talk mailing list
ncl-talk_at_ucar.edu
http://mailman.ucar.edu/mailman/listinfo/ncl-talk
Received on Wed Apr 30 2008 - 08:22:26 MDT
This archive was generated by hypermail 2.2.0 : Wed Apr 30 2008 - 22:04:51 MDT