veeru, we have been playing with least square analysis as well and I feel about it as you do. actually we are a team of three people and I will pass on the orthogonal analysis to our statistic guy. right now it seems that we have profitable tests with sharpe ratios at about 1 or slightly above [over a five year horizon]. we are using automatic pattern recognition for that. it has the advantage that you do not necessarily "see" a trade on the chart. I think this is important because the only reason I can think of why standard tools suck is that it is too obvious. In a to some extent efficient market there is necessarly pairs trading going on. When I look at pairstrading.com and their recommendations I wonder about these pairs trading in completely different sectors. I always try to understand my trading and I have not got the rationale behind these trades - so far. Let's assume they are working - why are they working? Statistically there is at any point of time a number of accidental outliers. This means that there is necessarily a "stupid" pair, that cannot be traded at all but shows significant correlation in recent history. This is actually the reason why I tried so far to keep my hands away from these trades. But if pairstrading.com find it usefull to trade them, I assume they will have reason to do so - meaning it will work. But why. Does it mean that for whatever reason a big trading book has the two stocks in one basket and buys and sells this basket therefore creating the correlation + possibility to trade? Or is it a game that rather refers to a kind of "overall integrity" of the market than to a pure pairs concept? One other thing: if you look at two stocks and build correlations on an intraday basis it seems as if there was a constant decline of correlation throughout the day. I wonder why that is so and if it can be of any help for pairstrading. More in detail: take two stocks and use the 9:45 prices of each day and calculate the correlation. Then take the 10:00 prices and do the same and so forth. I found a significant and constant decline in the computer sector in 2002. This in itself would not mean to much but it contrasts with the fact that each stock has its most volatile period in the morning session. There is biggest volume, even bigger than in the closing range, and there is the period where the market makes more range per time than at any oterh point of time. But it seems as if the market was not only volatile but more aware of market integrity. I find this rather interesting. One argument might be that the market is highly correlated because the biggest nonTradingTime where stocks could not react is just over and now stocks are effected by news in the very same way. Nevertheless, it could mean fo intraday pairs that convergence trades are better placed late during the session (???). Does any one trade on a purely automatic basis intraday? peace
IMO trendsetter is perfectly right in his approach. Unfortunately I am too lazy and love to delegate work to the computer [plus you can hardly handle thirty or fourty positions at one time]. There are pairs trending and others mean reverting. Problem is to find out when [its always the same thing]. I think baskets of stocks will rather trend - I looked at some and had that impression. Another thing. I am always trying to find out how the market is developing. It is obvious that pairstrading has become a standard tool of trading. And this changes the market place. But how can I measure this? Maybe by calculating the average all possible correlations?
Hi, You are absolutely right about pairstrading-related changes in the market place. That is the reason you are seeing companies like FO and ITT or FO and LMT having correlation of greater than 90%. IMHO, correlation is a key to some underwater processes in the market not visible otherwise. For all you know, FO and ITT could be traded by a big hedge fund on a daily basis from support to resistance and back... Knowing the correlation and identifying the oscillatory pattern of price action just bought you a nice ride which is predictable and profitable... BTY, I closed FO/ITT Friday hoping for overbought ratio today or tomorrow. FO tanked without reaching my entry point. Will wait. Still holding BK/MEL. Moderate profit so far. Al
Man: I can't make out much of the methodology used by pairstrade.com. I do agree that sector pairs work the best. Although a variety of factors need to be used as filters even within sector pairs. While unrelated stocks can be highly correlated, do we trade them just on this factor? My answer is no! (We can show high correlations between butterflies flapping in Malaysia & a storm brewing in the Atlantic -- statistics is a tricky subject, anyone read 'Fooled by Randomness' by Taleb, it is an excellent book) One final comment, I've found position trades to turn in better results than just intra-day trades. As an experiment, I traded the same pairs on both styles, and came to this conclusion.
Veeru, have you heard about a hedge fund "Whitebox"? they are doing pairs trading. they choose their pairs fundamentally and then optimise the strategy on the specific pair. this contrasts the view of those, who try to find one strategy for all pairs. isn't your butterfly example a classic finding of chaos theory? peace
Neutral AI especially this FO-ITT pair puzzles me. I have never seen a better chart for pairs trading. It is simply amazingly regular. Maybe your argument with that hedge fund is correct, but why are they doing this? I doubt that one hedge fund could "produce" such a chart without loosing significant amounts of money. There must be something more to it, though i have no idea what that could be. Maybe there is a connection in terms of a potential merger or something like that. A great thing for pairs trading would be to forecast merger activity. Imagine such a trade! Right now it might be interesting to look at all potential candidates for a takeover by microsoft. nevertheless I am not sure about non-connected pairs, though we are currently papertrading such a strategy, using pattern-recognition. another thing. do you have an idea in which circumstances pairstrading works best? bull-market? medium volatility??? peace
I've searched the site a few times...can't find what I'm looking for. a site that offers FREE daily spread charts. Not the typical 2 stocks on one chart that plot their percent changes. I'm looking for stockA - stockb= value. With the value plotted. Thanks in advance. Friday is here! And we have possible overnight snow forecasted up here in the North East!
Bob- wow you're fast...i grabbed a coffee re-fill and bam! Thats why I love this site. Ok, how do I get the data? If I have a DDE software link..maybe with that? I'm not that great with excel....but I'm a quick learner!
pick data from here by using a webquery http://table.finance.yahoo.com/k?s=qqq&g=d then-do the math and then-click on chart wisard and build a chart it may take a while to build a chart, but after you get familiar with it-you wil be fast enough))))))))) also-you can write a macro and it will do it for you automatically Good luck!