|
PureBytes Links
Trading Reference Links
|
Thanks Dennis for putting it so elegantly, I was obviously being very
"tongue in cheek" with my posts, but my point was exactly that - for example
my next "R-point" is next wednesday. Give it +/- 2 days and the chances are
pretty good there will be a turning point next week. No turning point - then
it must be an "inversion" or "continuation".
And to answer Ira since I believe the comment about plane (sic) nastiness
was directed about me- I have nothing against planes, and I actually thought
my posts were pretty funny and not in any way nasty. And to answer Ira's
point about random numbers working over an extended period of time - where
is the proof that Delta works any better than say, choosing every wednesday
+/- 2 days
dave
----- Original Message -----
From: "DH" <catapult@xxxxxxxxxxxxxxxxxx>
To: <realtraders@xxxxxxxxxxxxxxx>
Sent: Wednesday, May 23, 2001 1:55 PM
Subject: Re: [RT] DA moon and Delta
> > So just for fun, I
> > just chose 4 dates in the last 4 weeks - april 23, may 1, 7, 17 and
> > then chose a commodity TY M1. I placed the stars on the dates - pretty
> > impressive!
>
> Yep. At the risk of getting in trouble again for trying to inject a
> little logic into an emotional topic, let's think about it a little. The
> key is that +/- 2 days. Usually, I've seen trading days used for that,
> so that's 5 trading days total, or a week, or a quarter of a lunar
> cycle. If we look at all 4 phases of the moon, we've covered the whole
> month. If we only look at one phase, such as the new moon, that focuses
> it tighter but, if we are willing to accept several different events as
> significant, it still can hardly miss. Bear with me here....
>
> New moon +/- 2 trading days (25% of the month covered)
>
> 25% chance of a high during the period by random chance
> 25% chance of a low during the period by random chance
> -------------------
> 50% chance of a high or a low by random chance within +/- 2 days
>
> Now, if we can find 2 more conditions we consider significant, say a
> "continuation" and [I don't know what else], we have a 100% chance of
> "something" happening within +/- 2 days of the new moon.
>
> Just to be clear, I'm not claiming there is nothing to the moon effect
> or the planet effect or the sunspot effect. It's just that we need to be
> careful how we test it or we can fall into a statistical "can't miss"
> trap that reinforces what we already want to believe.
>
> Eyeballing the chart for correlations is particularly deceptive. System
> traders learn early on that the eye is easily fooled. Plot your favorite
> system as an indicator and your attention focuses in on the "good"
> events and totally misses many of the "bad" events. You will swear the
> system is nearly perfect. It's only when you run the statistics that you
> find all those times it didn't work as expected.
>
> --
> Dennis
>
> To unsubscribe from this group, send an email to:
> realtraders-unsubscribe@xxxxxxxxxxxxxxx
>
>
>
> Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
>
>
---
Outgoing mail is certified Virus Free.
Checked by AVG anti-virus system (http://www.grisoft.com).
Version: 6.0.255 / Virus Database: 128 - Release Date: 5/20/2001
To unsubscribe from this group, send an email to:
realtraders-unsubscribe@xxxxxxxxxxxxxxx
Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
|