From: Sabeerali(sebi) <sabeerl_at_nyahnyahspammersnyahnyah>
Date: Thu, 3 Sep 2009 12:59:33 +0530


    I am having 2 variables X and Y.The dimension of X is
(time=4,lat=73,lon=144)..and dimension of Y is (lat=73,lon=144,time=23). I
found aveX,aveY,varX,varY which are having dimension (lat=73,lon=144). I
think my sX and sY will be 4 and 23 respectively. I want to do ttest and
plot the values which are significant. In NCL tutorial I found that

Assume * ***. Then:

  alpha = 100.*(1. - *ttest*(aveX,varX,sX, aveY,varY,sY, iflag, False))

 will yield *alpha* dimensioned *nlat* x *mlon*. A significance of 0.05
returned by *ttest* would yield 95% for *alpha*. This is often done for

But in my case dimension of sX, and sY (i.e 4 and 23) is different from
dimension of aveX, varX etc..... (lat=73,lon=144)..But in above example
assuming *aveX*, *varX*, *sX*, *aveY*, *varY*, *sY* are dimensioned *nlat* x

*or can I use the below one?

probt = *ttest*(aveX,varX,sX, aveY,varY,sY, iflag, True)

Any help would be appreciated

ncl-talk mailing list
List instructions, subscriber options, unsubscribe:
Received on Thu Sep 03 2009 - 01:29:33 MDT

This archive was generated by hypermail 2.2.0 : Thu Sep 03 2009 - 21:03:38 MDT