• C++ Programming for Financial Engineering
    Highly recommended by thousands of MFE students. Covers essential C++ topics with applications to financial engineering. Learn more Join!
    Python for Finance with Intro to Data Science
    Gain practical understanding of Python to read, understand, and write professional Python code for your first day on the job. Learn more Join!
    An Intuition-Based Options Primer for FE
    Ideal for entry level positions interviews and graduate studies, specializing in options trading arbitrage and options valuation models. Learn more Join!

Few thoughts required

Hehe I do understand..But are they really mean reverting? the stochastic DE for a stock price is
2c7d3bf240b750bad2f1492a5efc96ed.png
assuming it grows by u....I assume it is a silly doubt...How do you define the lows and the high??
 

Yike Lu

Finder of biased coins.
The question you should be asking is "How do I figure out if stock prices are mean reverting?"
 
You can define highs and lows using lookback data, a specified window of time. Backtesting gives empirical data of entry and exit signals, it could be specific to sector or other factors.

Certainly there's tests for mean-reversion but a stock is mean-reverting usually in a narrow time range, and it's not necessarily a strong reversion, and may not repeat for some time. You just want to be right more often than wrong, and make more when you win than when you lose. Probabilty, expectation.

Good reference for this sort of thing http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1153505
 
@joel_b: Since you are suggesting papers on statistical arbitrage I am assuming the property of stocks being mean reverting is used more often in High Frequency trading strategy when the equities are range bound or volatile. But as a long term trading strategy is practically difficult to implement cause most of the time for buy low sell high strategy to work we have to be able to predict a recession and an high growth cycles...
@Yike Lu: I guess that would have been a more apt question. Could I also rephrase the question in a such a way, how do we predict the price is going to be range bound?
 
@joel_b: Since you are suggesting papers on statistical arbitrage I am assuming the property of stocks being mean reverting is used more often in High Frequency trading strategy when the equities are range bound or volatile. But as a long term trading strategy is practically difficult to implement cause most of the time for buy low sell high strategy to work we have to be able to predict a recession and an high growth cycles...?

Maybe read it first, me suggesting a paper does not imply it being for high-frequency trading.Are papers only written on high-frequency trading?

You choose your window man. if you read the paper it's a daily close price strategy with a 60 day window i.e. within a quarterly earnings cycle. Predict a recession? Growth cycles? That isn't mean reversion at all, quite the opposite you're talking about momentum strategies.
 
Thanks that helped a lot..The stat arb is a bad doubt cause my only exposure to it is from a book on HFT...I understand it a little better...Thank you Amanda too...Me needs to learn a lot more
 
Top