Search results

http://quantinvestor.blogspot.com is excellent

Jeff, Does your system use cointegration or correlation? Log returns or non-stationary price series? In my tests, historically cointegrated series (Granger-causality test, error correction model) consistently broke down out of sample. Secondly, choosing an alpha to input to the regression...

Self-confidence, knowledge, experience, discipline and concentration are necessary elements of a trader's personality. It just bothers me when companies like PairCo, daytradepairs.com, et al. sell this BS to naive traders.

I'm not an OpenQuant user so I had to look up GetReturnSeries(). Now it makes sense; differences in returns is stationary having stable statistical properties. Whereas, a price series alone has no finite variance. The exception is if two series are perfectly cointegrated, in which case, the...

segv... I took a cursory glance at your code and basically, please correct me if I'm wrong, it just sorts a universe of stocks by highest correlation and stops after 200 pairs are made. You could generate 1000 random walks and just as easily find correlations in those samples... but the...

There are no exceptions... or you will *****FAIL******

Page 60, on Timber Hill's MM business: "Our strategy is to calculate quotes at which supply and demand for a particular security are likely to be in balance a few seconds ahead of the market and execute small trades at tiny but favorable differentials. Our quotes are based on our proprietary...

What I'm trying to understand is... How much of your success in pairs trading is derived from the probabilities of individual stocks (i.e., directional and volatility view) OR a statistically determined optimal level of correlation that has positive expectancy? So far, I haven't found any...

Your pairs trades are 80% successful? What is the success rate of your long/short portfolio? this thread is getting more and more bizarre...

Doubleclick only did $150 million in revenue? Quality not quantity, I guess :confused:

It's hard to sympathize with securities attorneys :D

Sandy... you're only successful 44% of the time. Have you tried dividing your capital in half and trading the first half long, and using the rest for delta hedging? I've backtested that and found it immensely more successful than attemting to reduce risk with pairs.

Can you explain your methodology a bit? I have studied pairs trading but still can't get past this fact: The result of the correlation between any 2 random variables (stocks) is still random, only with different frequency of oscillation and standard deviation. Is there an optimal...

There is, it's T+3 to withdraw funds!

Nasdaq also requires a $5 min bid, so there's usually a reverse split

yes. you need an event stream processor such as Esper or Coral8 to collect the ticks, aggregate them over a specific time frame, and output after X seconds/minutes/ticks. Obviously there are other ways of doing this, but it's not worth reinventing the wheel.

Start with this <img src="http://www.itbizvision.com/ion/show_image.php?id=261">

It's $16,000.

Jsystemtrader is open source and quite nice, if you use IB. Do a search for it...

Active traders keep the markets efficient by using new information to agree on the best price. Index investing is parisitical because it feeds off the decisions of others. At some threshold, over-indexing will lead to diminishing returns.