Algo Trading ES/NQ Performance Metrics.....which are the best ?

sle said:
You don't really have to go through all of that, you know. Simply take the backtest sample, exclude your trades (under assumptions that both samples have some meat to them) and look if the strategy results (e.g. mean) are statistically significant. Then you could apply the two sample T test or the Wilcoxon rank sum test - both are nice if normality cannot be assumed.

E.g. let's assume your targets are unit (1, 0, -1). If your backtest shows pnl = target * returns, you can create a subset xnl = returns[ target == 0] and run them through a two sample t-test.

PS. of course, beware of the family-wise errors if you are doing any sort of "extensive studies"
More...
Could you point me to some good resources which further describes what you outlined in your post (books, sites, etc)?
 
sle said:
Index rotation is a performance-neutral event by definition. The index manager "sells-out" of the stocks and replaces them with new ones at the market prices.

PS. Granted, because of the index rotation you will see some correlation to the momentum factor, but it has zero "alpha" vs the component stocks.

PPS. If anything, index rotation has (more like "had") alpha with respect to the stocks that are being added or dropped, but that game is so crowded these days
More...

Sle,

I am confused, the OP mentioned ES and NQ as his trading instruments. Are you saying that Netfilx replacing Perrigo or adding Goog as the 101st issue wouldn't facilitate an upward bias in the Nas 100 and thus NQ?

I thought the Q-50 was there specifically for this purpose - a proving ground for issues that would eventually replace laggards.

Old NQ stocks never die, they just relist on the NYSE :)

I know you are much more knowledgeable than I.
 
They said:
I am confused, the OP mentioned ES and NQ as his trading instruments. Are you saying that Netfilx replacing Perrigo or adding Goog as the 101st issue wouldn't facilitate an upward bias in the Nas 100 and thus NQ?
More...
At the level of index mathematics, not really. When the index is calculated, the stock that is being dropped and the stocks that is being added are "sold" and "bought" at the current market price. Imagine a simple index of two stocks (A and B), allocated at 50% each. If we decided to drop A and replace it with C, we would take the value of the index at the time of replacement times the weight of the stock being replaced and swap that dollar value for the new stock.

There is a secondary effect at the stock level which occurs before the actual addition. S&P (or whichever index provider) announces that it's going to swap a stock X for stock Y a little in advance. Since it's expected that all index replicators will rush to sell out of X and buy Y once that change occurs, there is some alpha in putting that trade on before the actual effective date.
 
sle said:
Since it's expected that all index replicators will rush to sell out of X and buy Y once that change occurs, there is some alpha in putting that trade on before the actual effective date.
More...

Seems like there could be a long term strategy based on buying the index when there are many stocks being added to the index that are from sectors which are accepted to run at higher multiples than the stocks that are being replaced or the average multiples of the index itself.

I wonder what is the shortest length of time a stock has been in the Nas 100 and what its net performance was.
 
You know in options algos, yeah, you need to quickly evaluate functions a bit like, say, N(t^-0.5*v^-1*ln(s/k)+/-0.5^v*t^0.5) where N() is the cumulative normal distribution..or similar functions that look like solutions to parabolic pde's. I found series expansions involving hyperbolic sin/cosin converge very quickly (since only real valued exponentials, computer likes). Is it better to define 'i' as an operator formally and then use that? Has anyone tried/got this? Email me trae88@icloud.com (or @tutanota.com if second name is snowden) if you wanna discuss. Thanks!
 
I am curious about the use of algos with options .... I keep thinking most algos are for short-term futures trading.
1) Which underlying instrument(s) are you using ?
2) What is the time-frame ?
3) Average time-in-trade ?
4) Do the commissions seriously deduct from profits ?
5) Are you working with delta, gamma, theta, rho to make the trading decisions ?
TIA.
 
You must log in or register to reply here.
Back
Top