[RC5] Stats suggestion

Ben Clifford benc at hawaga.org.uk
Fri Jan 5 20:07:09 EST 2001


On Fri, 5 Jan 2001, Pyke, David wrote:

> But a simple decay factor of .0111 will allow for a weighted average.
> Yesterdays value gets multiplied by .9889 (technically 89/90) and the added
> to today's multiplied by .0111 (1/90) .  This gives today's a full weight
> and the past 89 days a reducing factor with each specific day declining over
> time.
> 
> This gives a much more faster reaction to changes in daily rate and gives an
> average that doesn't take years to get to current average rate.

Yes, this is what I have been talking about for the past day.

You will see in my last message that I gave a couple of different decay
values - yours would be 0.9889 the way that I wrote the formulae, rather
than 0.111; you use both above.

This corresponds to a half life of about 62 days.

My gut feeling is that this is a bit too long - starting at 0, it will
take 62 days to get to half of your real rate, another 62 days to get to
3/4 of your actual rate and another 62 days to get to 7/8 of your actual 
rate. 

That's a six month wait, which I feel is too long; I would be more
comfortable with a half-life nearer the 7-20 day mark. (Of course,
depending on how much space-time is allocated on statsbox, there could be
more than one counter).

-- 
http://www.hawaga.org.uk/travel/ for my rotating world map applet
http://www.hawaga.org.uk/benc_key.txt PGP / GPG key 0x30F06950 - please use it!


--
To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
rc5-digest subscribers replace rc5 with rc5-digest



More information about the rc5 mailing list