|
PureBytes Links
Trading Reference Links
|
Research,
This is true, something that happens 800x's out of 1K is of significance.
This is true for
you since you use a data base composed in probably 2 to 3 min bars, so it
is very pertainent
and makes money and is truth. (OBTW, thanks for sharing that data many
years ago. What a
generous thing to do....)
I have found that the opposite is true for end of day universe of price
behavior.
The smaller the sample of events that I can register for a given outcome,
with end of day data
is more significant it is. But I must admit that I am not making a
mechanical trading system.
I am only seeking the probablility of the 6 directions. Gap up Gap Down Up
Close Range
Down Close Range, Higher close, Lower close.
It is a very curious paradox. Go Figure.... The question is the ratio of
similiar outcomes proportional in
intraday data the same as it is for end of day data? Isn't this a a
fundamental underpinning of technical analysis?
What happens at the 5 min pattern is similiar to what happens at the hourly
pattern.
Regards,
Don Thompson
Subject: [RT] Statistical Significance?
> Hello realtraders,
>
> Statistical Significance?
>
> gentlemen (and oxen) can we agree that there should be greater
> significance in something that occurs 800 times out of 1000 rather
> than 8 out of 10? please can we agree upon this? if so read on, if
> not please continue spearing dinosaur.
>
> ok a few of you made it this far i hope, now if we understand that
> something that happens with greater occurrences than something less
> frequent. then we understand that in the future when comparing
> trading methods - the following.
>
> that a trading method that shows a greater statical reoccurrences ( it
> happened more times than any other method ) is the clear undisputed
> champion of trading methods? not saying that other methods do not
> work, as i have stated before there are ways to do something. but
> there must be a better way or a BEST way to do something at least at
> some point and time.
>
> --
> Best regards,
> Research mailto:research@xxxxxxxxxxxxx
>
>
>
> 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/
>
>
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/
|