>Hello. Is there an NCL function or script available for testing the
>significance of a trend (example, 100 years of global av temperature)?
Hi Mike,
Not sure what you used to calculate the trend.
However, regline
http://www.ncl.ucar.edu/Document/Functions/Built-in/regline.shtml
and, regcoef
http://www.ncl.ucar.edu/Document/Functions/Built-in/regcoef.shtml
return the t-statistic [tval] as an attribute.
The number of values used (N) is also returned. These
can be used to evaluate the statistical significance.
Note: If a N are independent then use (N-2) dof.
HTH
D
_______________________________________________
ncl-talk mailing list
ncl-talk@ucar.edu
http://mailman.ucar.edu/mailman/listinfo/ncl-talk
This archive was generated by hypermail 2b29 : Tue May 24 2005 - 14:31:01 MDT