[Met_help] [rt.rap.ucar.edu #90828] History for Lack of Confidence Intervals

[John Halley Gotway via RT]

----------------------------------------------------------------
  Initial Request
----------------------------------------------------------------

John, when running point stat and outputing cnt files, the confidence
intervals are all NA.  Attached in my configuration file.  I have  boot set
to PCTILE.  Do I have a setting wrong?  Do I have to have climo data to get
a confidence interval?

 

Thanks

Bob



----------------------------------------------------------------
  Complete Ticket History
----------------------------------------------------------------

Subject: Lack of Confidence Intervals
From: John Halley Gotway
Time: Thu Jun 27 11:45:30 2019

Bob,

Bootstrapping is a random re-sampling process.  The number of times
that
re-sampling is done is called the number of "replicates".  This is
controlled by the "n_rep" setting in the "boot" dictionary in the
Point-Stat config file.  Setting "n_rep = 0;", which is the default to
make
it run as fast as possible, effectively disables the computation of
bootstrap CI's.  To turn them back on, just increase the number of
replicates in the config file.  Perhaps start with 1000:

boot = {
   interval = PCTILE;
   rep_prop = 1.0;
*   n_rep    = 1000;*
   rng      = "mt19937";
   seed     = "";
}

Thanks,
John

On Thu, Jun 27, 2019 at 10:48 AM robert.craig.2 at us.af.mil via RT <
met_help at ucar.edu> wrote:

>
> Thu Jun 27 10:28:03 2019: Request 90828 was acted upon.
> Transaction: Ticket created by robert.craig.2 at us.af.mil
>        Queue: met_help
>      Subject: Lack of Confidence Intervals
>        Owner: Nobody
>   Requestors: robert.craig.2 at us.af.mil
>       Status: new
>  Ticket <URL:
https://rt.rap.ucar.edu/rt/Ticket/Display.html?id=90828 >
>
>
> John, when running point stat and outputing cnt files, the
confidence
> intervals are all NA.  Attached in my configuration file.  I have
boot set
> to PCTILE.  Do I have a setting wrong?  Do I have to have climo data
to get
> a confidence interval?
>
>
>
> Thanks
>
> Bob
>
>
>

------------------------------------------------
Subject: RE: [Non-DoD Source] Re: [rt.rap.ucar.edu #90828] Lack of Confidence Intervals
From: robert.craig.2 at us.af.mil
Time: Thu Jun 27 12:11:38 2019

Okay, thanks.

-----Original Message-----
From: John Halley Gotway via RT <met_help at ucar.edu>
Sent: Thursday, June 27, 2019 12:46 PM
To: CRAIG, ROBERT J GS-12 USAF ACC 16 WS/WXN
<robert.craig.2 at us.af.mil>
Subject: [Non-DoD Source] Re: [rt.rap.ucar.edu #90828] Lack of
Confidence Intervals

Bob,

Bootstrapping is a random re-sampling process.  The number of times
that re-sampling is done is called the number of "replicates".  This
is controlled by the "n_rep" setting in the "boot" dictionary in the
Point-Stat config file.  Setting "n_rep = 0;", which is the default to
make it run as fast as possible, effectively disables the computation
of bootstrap CI's.  To turn them back on, just increase the number of
replicates in the config file.  Perhaps start with 1000:

boot = {
   interval = PCTILE;
   rep_prop = 1.0;
*   n_rep    = 1000;*
   rng      = "mt19937";
   seed     = "";
}

Thanks,
John

On Thu, Jun 27, 2019 at 10:48 AM robert.craig.2 at us.af.mil via RT <
met_help at ucar.edu> wrote:

>
> Thu Jun 27 10:28:03 2019: Request 90828 was acted upon.
> Transaction: Ticket created by robert.craig.2 at us.af.mil
>        Queue: met_help
>      Subject: Lack of Confidence Intervals
>        Owner: Nobody
>   Requestors: robert.craig.2 at us.af.mil
>       Status: new
>  Ticket <URL:
https://rt.rap.ucar.edu/rt/Ticket/Display.html?id=90828
> >
>
>
> John, when running point stat and outputing cnt files, the
confidence
> intervals are all NA.  Attached in my configuration file.  I have
> boot set to PCTILE.  Do I have a setting wrong?  Do I have to have
> climo data to get a confidence interval?
>
>
>
> Thanks
>
> Bob
>
>
>



------------------------------------------------