You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an alternative browser.
You should upgrade or use an alternative browser.
Let's discuss academic research on mean-reverting trading strategies...
- Thread starter mizhael
- Start date
comment: reading that made me want to shoot myselfQuote from mizhael:
nobody wants to comment on the results?
comment: it looks that they did a good job with the research tho i think that they way they did it left bias in the results.. I can see where some of this is useful and some of this is useless... they could have done this with way less math... and they didnt DIRECTLY curve fit the data.. but when you use anytimeset like that data is basically curve fitted to some extent.. I believe their was a lack of forward walked data and control group... but i didnt read the whole thing cause it was painful so im not sure.
Quote from makloda:
Why don't you start with your comments?
That's because I am afraid I say something incorrect...
Okay, I looked at the S&P 500 during the same period, 2002-2007 and found holding S&P 500 would actually perform better.
But it all depends on the alpha that's generated. Without computing alpha, not sure how much value it adds, even though the sheer performance is below the benchmark.
It is a very very interesting paper but it only tests mean reversion:
"We presented a systematic approach to statistical arbitrage and for constructing
market-neutral portfolio strategies based on mean-reversion."
There are many many approaches to stat-arb that are based on a lot more than mean reversion.
"We presented a systematic approach to statistical arbitrage and for constructing
market-neutral portfolio strategies based on mean-reversion."
There are many many approaches to stat-arb that are based on a lot more than mean reversion.
Quote from comintel:
It is a very very interesting paper but it only tests mean reversion:
"We presented a systematic approach to statistical arbitrage and for constructing
market-neutral portfolio strategies based on mean-reversion."
There are many many approaches to stat-arb that are based on a lot more than mean reversion.
elaborate please?
Quote from mizhael:
elaborate please?
According to Wikipedia:
"Broadly speaking, StatArb is actually any strategy that is bottom-up, beta-neutral in approach and uses statistical/econometric techniques in order to provide signals for execution. Signals are often generated through a contrarian mean-reversion principle, but can also be formed by lead/lag effects, extreme psychological barriers[citation needed], corporate activity, as well as short-term momentum. This is usually referred to as a multi-factor approach to StatArb."
I read this paper,and is basically an extension of LO strategy,which is cited, and is quite easier to understand.
If you know how to automate it, and trade it with medium capitalization stock I think these strategies work,since this market is too small for big hedge funds..
There are some article about this in willmot magazine by Ed Tropp, a pioneer of stat arb,who discovered and used this stuff in the 80s.
Hedge funds don t look for momentum traders ... why for some reasons ..
If you know how to automate it, and trade it with medium capitalization stock I think these strategies work,since this market is too small for big hedge funds..
There are some article about this in willmot magazine by Ed Tropp, a pioneer of stat arb,who discovered and used this stuff in the 80s.
Hedge funds don t look for momentum traders ... why for some reasons ..
Quote from worsttraderever:
I read this paper,and is basically an extension of LO strategy,which is cited, and is quite easier to understand.
If you know how to automate it, and trade it with medium capitalization stock I think these strategies work,since this market is too small for big hedge funds..
There are some article about this in willmot magazine by Ed Tropp, a pioneer of stat arb,who discovered and used this stuff in the 80s.
Hedge funds don t look for momentum traders ... why for some reasons ..
Would it work with small-cap stocks also if traded very lightly?