Search results

Depends on what im doing. When analyzing variance ratios you just need a lot of evenly spaced single-variable data, that can be anything. When trading, I use sub-second quote data which feeds into the algorithms, indicators, whatever and that in turn figures out position sizing, etc.

No.. you cant calculate VR with 10 ticks.. you need shitloads of data. Like I said, it is purely an after-the-fact analysis.. if your sample is large enough you might be able to split it in half or something.. but as the number of points decreases the VR accuracy decreases as well.

If some 'thing', whether it be a stock, etf, spread, etc is consistently trending, or consistently mean reverting every single day then you can probably assume it will continue trending or reverting.. But if something trends half the time and mean reverts half the time, you cant look into the...

So I take it that you think it is not possible?

I don't use this for forecasting.. I use it to quantify many days in the past to see if the amount of randomness is stable and then use it to decide what types of rules to use in the near future. Also, I don't use bars.. tick/quote data

Hmm, I guess this is a guy making directional trades.. highly leverged and not hedged? I'm very sensitive to risk and have failsafes to shut my system down if starts drawing down more than the expected amount.. hopefully that won't happen.. the performance should degrade over time and I...

1% is my baseline.. so I can stop spending 12hrs a day crunching away.. and then I'll increase performance at a more relaxed pace.. my goal is to generate a decent amount of money each month and for me to be able to leave the corporate world and never have a 'real job' again. So, I'll keep...

Yes, I optimize on back data and then apply it to out-of-sample data.. some times the out of sample results are better than the in-sample dat that i tuned the parameters with. :p Also, I plot the parameters and the performance is indeed smooth around the optimal parameters a so no worries...

My system is general. I use statistics to verify the underlyings are 'tradeable' and then determine the maxium theoretical profit and then optimize rules to get as close to the maximum theorotical amount as possible while also hedging and limiting drawdown as well.

Yes of course.. do some searches on "cointegration" and prepare to read.. and read.. and then read some more..

600-900% a year is just insane.. like you said, but wow.. 300-400% is incredible. I assume it's all intraday and hedged? Would this thing blow up with another 9/11 or just take it in stride? I'm fairly confident mine would fare just fine but I really need some high frequency data from one of...

Well, some days it is 0.5%.. some days 1.5% so it doesn't exactly gain 1% a day, I'd have to fit a distribution to the returns and then project it into the future to find upper and lower bounds within some interval.. Who is Hull? that sounds really interesting.. As far as backtesting...

General question for intraday automated traders.. no manual intervention except in extreme cases. In your opinion, Is 1% a day return on average possible with 4:1 buying power? This is after accounting for commissions but excluding things like colo fees, exchange fees, etc. Backtesting my...

This applies generally to all intraday automated strategies without going into specifics. Do start trading immediately after market open or do you have blackout periods? Also, do you stop trading before the market officially closes? I've noticed weird stuff during the 1st hour of each day...

Since the defintion of the variance ratio (or modified variance ratio) is the relative difference between 1-period changes vs N-period changes then you just calculate all the variance ratios from 1 to M and plot them. Note: you must use overlapping returns when calculating the N-period...

I see what you are saying.. that is only true if you were to concatenate intra-day returns together and ignore overnight changes.. this is not a good idea. Basically, I calculate a variance ratio profile for each day using intraday data.. and then overlay them.. if they are all very similiar...

To be clear, the variance ratio doesnt depend on any magic numbers and doesnt use highs, lows, etc and can be used on any time frame. I cant speak for these other measures.

What do you mean by "daily version"? The calculation is the same no matter what your frequency of choice is.

I trade exclusively intraday.. overnight returns are problematic due to the low sample size.. would be nice if the markets traded 24/7...but even then there would be seasonal activity. The intraday trend analysis probably has no relation to daily trend analysis.. but that is just a guess, I...

You use logarithms so that the measures make sense over time as the average value drifts around. log(100)-log(50) == log(50)-log(25) 100/50 == 50/25 exp(log(100)-log(50)) ==100/50