Re: Significance of a linear trend

From: Dennis Shea <shea_at_nyahnyahspammersnyahnyah>
Date: Mon Nov 25 2013 - 07:52:21 MST

Your code looks correct.

You can verfify by looking at tables: t-value vs df

On 11/23/13 5:23 PM, Mahesh Varma wrote:
> Hi,
> I am trying to calculate statistical significance of a linear trend. Could
> any please check if my code is correct? I just want to make sure if the
> trend is significant (>99%).
> Thanks,
> Mahesh
>
> Attached below is the code:
> ----------------------------------------------------
> rc_pdo = regline(time,pdo)
>
> df_pdo= rc_pdo@nptxy-2;degrees of freedom
> prob_pdo= (1 - betainc(df_pdo/(df_pdo+rc_pdo@tval^2), df_pdo/2.0, 0.5) )
>
> if (prob_pdo .ge. 0.99) then
>
> print("PDO TREND IS SIGNIFICANT (>99%)")
>
> end if
>
> ----------------
>
>
>
> _______________________________________________
> ncl-talk mailing list
> List instructions, subscriber options, unsubscribe:
> http://mailman.ucar.edu/mailman/listinfo/ncl-talk
>
_______________________________________________
ncl-talk mailing list
List instructions, subscriber options, unsubscribe:
http://mailman.ucar.edu/mailman/listinfo/ncl-talk
Received on Mon Nov 25 07:52:31 2013

This archive was generated by hypermail 2.1.8 : Wed Dec 04 2013 - 20:42:38 MST