Re: [chrony-dev] [GIT] chrony/chrony.git branch, master, updated. 1.25-pre1-18-g20a4340

[ Thread Index | Date Index | More chrony.tuxfamily.org/chrony-dev Archives ]


On Fri, Apr 15, 2011 at 09:08:44AM -0700, Bill Unruh wrote:
> On Fri, 15 Apr 2011, Miroslav Lichvar wrote:
> 
> >On Fri, Apr 15, 2011 at 05:30:28AM -0700, Bill Unruh wrote:
> >>The problem with using the unweighted variance is that it sort of obviates the
> >>use of the weights.
> >
> >It does, but it's used only for the weight calculation.
> >
> 
> Not sure what you mean? Is the standard dev reported the same as at present
> and you just use the unweighted variance to calculate the weights or do you
> just do one variance calculation?

Both are calculated, the unweighted variance is used only in the
following weight calculation, the other in everything else as before.

> The current procedure also underestimates the kstandard dev of the intercep[t
> and the skew, and it should probably be fixed as well.

Ok, how exactly?

> >Yes, I had to change the SD_TO_DIST_RATIO constant from 1.0 to 1.4 to
> >get a similar response in the simulations.
> >
> >Ok, so for 1.25 I think this is good enough, if someone will have a
> >better idea how to do the weighting, it can be implemented later.
> 
> Similar to what?

Similar to the response with weighted varience, but it's actually
about 10% worse.

-- 
Miroslav Lichvar

---
To unsubscribe email chrony-dev-request@xxxxxxxxxxxxxxxxxxxx with "unsubscribe" in the subject.
For help email chrony-dev-request@xxxxxxxxxxxxxxxxxxxx with "help" in the subject.
Trouble?  Email listmaster@xxxxxxxxxxxxxxxxxxxx.


Mail converted by MHonArc 2.6.19+ http://listengine.tuxfamily.org/