Trading and Statistics

Bingoking · Jun 24, 2008

Quote from ChkitOut:

Who here approaches trading from a purely statistical standpoint.

By that I mean, screw charts and visual patterns.

I'm talking measures of dispersion, variance, standard deviation, probability distributions,
confidence intervals, p-values, z-scores, goodness-of -fit tests, correlation analysis, significance
tests, etc....

Maybe Market Profile would help you. Based on standard deviation. Markets tend to pull back from 2nd & 3rd std deviation back to 1st std deviation. That's a pretty general statement of course. If it were always that easy . . .

Bo_D_ · Jun 25, 2008

Quote from naifwonder:

Just using math without any underlying fundamental premise is, mathematically speaking, a near surefire way to fail. I use stats extensively in the creation of my trading systems, but they all have an underlying fundamental premise to them.

i know traders who make lots of money with a pure statistical approach. isnt that what a systems trader generally does?

what do you mean by funamental premise? how do you factor fundamental data into your trades if your a systems trader?

pneuma · Jun 26, 2008

Quote from naifwonder:

Just using math without any underlying fundamental premise is, mathematically speaking, a near surefire way to fail. I use stats extensively in the creation of my trading systems, but they all have an underlying fundamental premise to them.

I have thousands of profit that would disagree with you on that point.

However, I do a agree that a synergy of fundies and TA can often be very profitable.

More profitable? I don't know, i rarely use fundies to compare.

Tums · Jun 26, 2008

Quote from ChkitOut:
Who here approaches trading from a purely statistical standpoint.
By that I mean, screw charts and visual patterns.
I'm talking measures of dispersion, variance, standard deviation, probability distributions,
confidence intervals, p-values, z-scores, goodness-of -fit tests, correlation analysis, significance
tests, etc....

Do you look at the map, but not the road, when you drive? LOL

Tums · Jun 26, 2008

Quote from ChkitOut:
Who here approaches trading from a purely statistical standpoint.
By that I mean, screw charts and visual patterns.
I'm talking measures of dispersion, variance, standard deviation, probability distributions,
confidence intervals, p-values, z-scores, goodness-of -fit tests, correlation analysis, significance
tests, etc....

Switch to options.
You can trade on greeks alone.

HiFreekTrader · Jun 26, 2008

Some good texts:

Kaufman, Perry J. - Trading Systems and Methods.pdf

BRUCE I. JACOBS, KENNETH N. LEVY - Market neutral strategies.pdf

Timothy Masters - Monte-Carlo Evaluation of Trading Systems.pdf

The Mathematics Of Financial Modeling And Investment Management.pdf

The Limits of Noise Trading: An Experimental Analysis.pdf

What Happened To The Quants In August 2007.pdf

feotrader · Jun 26, 2008

Can you post the link to these documents?

Thanks

Quote from HiFreekTrader:

Some good texts:

Kaufman, Perry J. - Trading Systems and Methods.pdf

BRUCE I. JACOBS, KENNETH N. LEVY - Market neutral strategies.pdf

Timothy Masters - Monte-Carlo Evaluation of Trading Systems.pdf

The Mathematics Of Financial Modeling And Investment Management.pdf

The Limits of Noise Trading: An Experimental Analysis.pdf

What Happened To The Quants In August 2007.pdf

Cutten · Jun 27, 2008

Quote from ChkitOut:

Who here approaches trading from a purely statistical standpoint.

By that I mean, screw charts and visual patterns.

I'm talking measures of dispersion, variance, standard deviation, probability distributions,
confidence intervals, p-values, z-scores, goodness-of -fit tests, correlation analysis, significance
tests, etc....

Well, you can forget anything based on normal or log-normal distributions for starters. Market prices are not normally distributed, this has been known for at least 50 years.

simpleton · Jun 27, 2008

Quote from Cutten:

Well, you can forget anything based on normal or log-normal distributions for starters. Market prices are not normally distributed, this has been known for at least 50 years.

Over short time frames, normal distributions with a bit of negative kurtosis is a good approximation. I agree over longer time frames this is no longer true.

dtrader98 · Jun 27, 2008

Quote from ChkitOut:

Who here approaches trading from a purely statistical standpoint.

By that I mean, screw charts and visual patterns.

I'm talking measures of dispersion, variance, standard deviation, probability distributions,
confidence intervals, p-values, z-scores, goodness-of -fit tests, correlation analysis, significance
tests, etc....
[/q]

Quote from Cutten:

Well, you can forget anything based on normal or log-normal distributions for starters. Market prices are not normally distributed, this has been known for at least 50 years.

More...

Use of sampling statistics and the CLT, generally allow the use of the above tests regardless of the shape of the true population distribution. Few on ET seem to understand that.