|
PureBytes Links
Trading Reference Links
|
I agree.
I use all the Z-Scores from 2 to 21 and also 50 and one them or more
than one of them seems to be have a value of +2/-2 at some point of
time...., but I would use 50 as the default, not 20 as Bollinger
suggests and also I would not use 15 with +1.5/-1.5 as he suggests
but use 15 with +2/-2. I might add 21 to 49 also and maybe a 200
too... Now that we small investors have the same computing power as
the big brokerage and Investment houses with their super-
computers....It might be an overkill.... I want to close the gap
between the small investor and the biggies...
Pal
--- In amibroker@xxxxxxxxxxxxxxx, "MarkF2" <feierstein@xxxx> wrote:
> --- In amibroker@xxxxxxxxxxxxxxx, "palsanand" <palsanand@xxxx>
wrote:
>
> > For BandWidth I use just one period namely 20 bars, but lately I
> > found out that 50 is better because of something to do with 50
> being
> > a better sample size than 20 to approximate a normal (gaussian)
> > distribution and so I am going to modify it. I also use ATR(20)
> for
> > BandWidth calculation and I am going to change it to ATR(50) also.
>
> Actually, the central limit theorem states that the sampling
> distribution of *sample means* approaches a normal distribution with
> increased sample size, regardless of the shape of the population
from
> which the samples are drawn. Increasing *sample size* alone does no
> such thing.
>
> > For calculating Z-Scores the sample size does not matter,
anything
> > from 2 to 50 is ok.
>
> The probabilities in the z table technically apply only to a
> theoretical sample size of infinity. To be exact, you would
actually
> need a separate z table for each different sample size. But the
> difference between a sample size of 50 and an infinite one is small
> (approximately .07 SDs).
------------------------ Yahoo! Groups Sponsor ---------------------~-->
ReplayTV: CNet Ranked #1 over Tivo!
Instant Replay & Pause live TV.
Special Sale: 50% off!
http://us.click.yahoo.com/UUMW7B/.5qGAA/ySSFAA/GHeqlB/TM
---------------------------------------------------------------------~->
Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html
Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/
|