Re: correlation significance

From: Dennis Shea <shea_at_nyahnyahspammersnyahnyah>
Date: Tue, 24 Jan 2006 14:37:21 -0700 (MST)

>I am correlating two time series, both 400 years in length. I did a
>running mean on one of the two series. I would therefore get a
>much smaller equivalent sample size for that series.
>Which N do I use to determine the significance of
>the correlation since both time series have a significantly
>different equivalent sample size?

You must use the smaller sample size.

>Is there a way of doing this using rtest / equiv_sample_size?

prob = rtest(r, N_smaller_of_two, 0)

D

_______________________________________________
ncl-talk mailing list
ncl-talk_at_ucar.edu
http://mailman.ucar.edu/mailman/listinfo/ncl-talk
Received on Tue Jan 24 2006 - 14:37:21 MST

This archive was generated by hypermail 2.2.0 : Fri Jan 27 2006 - 10:26:54 MST