Search found 68 matches

by Eventhorizon
Wed Sep 28, 2011 12:03 pm
Forum: Money Management
Topic: When To Start Your System?
Replies: 28
Views: 14457

I'll just throw in my 2c ... I used Winton Diversified Fund's monthly returns to explore the effect of buying in all at once, vs buying in 2 through 12 tranches, each purchase a month apart. I looked at how much equity you would have at the end of the first 12 months. So, going all in, the equity ha...
by Eventhorizon
Fri Sep 23, 2011 12:29 pm
Forum: Testing and Simulation
Topic: CTA performance data
Replies: 28
Views: 12079

stopsAreForWimps, Very interesting work - thank you for your continuing excellent contributions! When trade or periodic returns are compounded, the distribution tends to increasingly resemble a normal distribution, with zero skewness and kurtosis - provided certain conditions are met. Why are you ma...
by Eventhorizon
Wed Sep 14, 2011 7:13 pm
Forum: Testing and Simulation
Topic: Blox for testing entry based on percentage move?
Replies: 5
Views: 2186

I am talking about futures contracts. Simple example, picked at random from the CL (Crude) contract: Actual closes, with a roll on 2005-01-10 ... Date: 2005-01-06, 2005-01-07, 2005-01-10, 2005-01-11 Feb 2005 contract: 45.56, 45.43, NA, NA Mar 2005 contract: NA, 45.67, 45.57, 45.91 => % changes* -0.2...
by Eventhorizon
Tue Sep 13, 2011 9:50 pm
Forum: Testing and Simulation
Topic: Blox for testing entry based on percentage move?
Replies: 5
Views: 2186

Remember you would have to use ratio-adjusted contracts or your percentages will be meaningless.
by Eventhorizon
Tue Aug 30, 2011 12:24 pm
Forum: Testing and Simulation
Topic: Parameter Stepping Methods and Implications
Replies: 14
Views: 5363

Thanks 7432 - that was exactly the clarification I was looking for. Kaufman is taking into account the terrain around the optimum as well as the optimum itself. When doing so, one needs to work in percentage steps to avoid a bias against the lower values in the range. Sorry if I am over-thinking it ...
by Eventhorizon
Tue Aug 30, 2011 12:13 pm
Forum: Testing and Simulation
Topic: Question about the adjustment method of TB futures data
Replies: 5
Views: 1937

The roll method is detailed in the table on the download page.

The back-adjustment method is subtraction (there is a fixed difference between raw close and adjusted close for any given expiry, if it were a ratio adjusted series there would be a fixed ratio).
by Eventhorizon
Mon Aug 29, 2011 2:47 pm
Forum: Testing and Simulation
Topic: Parameter Stepping Methods and Implications
Replies: 14
Views: 5363

I am curious as to the logic Kaufman is using to make the claim that searching the parameter space using equal steps will result in a slower trading system than searching the space using percentage steps. Consider a parameter that could take any value from 0 to infinity. This is your parameter space...
by Eventhorizon
Fri Aug 19, 2011 6:55 pm
Forum: Money Management
Topic: Any idea about how to find the formula for 3 items?
Replies: 5
Views: 4367

I am feeling mean ...

Let me Google that for you

Sorry! :wink:
by Eventhorizon
Mon Aug 15, 2011 9:00 pm
Forum: Money Management
Topic: Optimal f
Replies: 87
Views: 117784

You will enjoy it. Pay particular attention to Sluggo's comment about typos. I have Handbook of Portfolio Mathematics and Leverage Space Trading Model. Both have typos, and both sometimes leave you with a lot of work to do to follow what's going on. Persevere, and ask questions - I would certainly e...
by Eventhorizon
Tue Jul 26, 2011 4:04 pm
Forum: Testing and Simulation
Topic: Good Non Corrleated System
Replies: 5
Views: 2335

Chris,

You would probably want to use Ralph Vince's LSPM to explore part of this issue. Not something you can do in excel, but I could certainly do it for you in R!

PM me if your interested in exploring this further.
by Eventhorizon
Wed Jul 20, 2011 5:08 pm
Forum: Testing and Simulation
Topic: My research says: the markets haven't changed in 31 years
Replies: 14
Views: 5456

Chris, I would echo Moto's point about looking at daily vol. alone, but take the thought in a slightly different direction. I have been working on a tail risk overlay - trying to identify increasing instability in the asset price history and use this as a signal to dial back position sizes. As part ...
by Eventhorizon
Tue Jul 19, 2011 5:00 pm
Forum: Testing and Simulation
Topic: How to interpret Monte Carlo results
Replies: 6
Views: 2417

So the math suggests that in order to make MC CAGR approximately equal to Backtest CAGR Hmmm ... The back test CAGR is what it is. The MC CAGR isn't a single CAGR it is a stochastic function. It is not like a single valued function (y = x^2), the result is a distribution of values. So there isn't r...
by Eventhorizon
Mon Jul 18, 2011 12:45 am
Forum: Testing and Simulation
Topic: How to interpret Monte Carlo results
Replies: 6
Views: 2417

Yes, you would expect that your actual back-test CAGR would be higher than the worst 10% (1 - 90%) of the simulated equity curve CAGRs. Consider an equity curve from a back-test that consists of 3 monthly returns: 0%, -2%, +5%. Over the 3 months the Cumulative Monthly Growth Rate was 0.957% (cubed r...
by Eventhorizon
Sun Jul 17, 2011 3:47 pm
Forum: Testing and Simulation
Topic: How to interpret Monte Carlo results
Replies: 6
Views: 2417

The typical way a monte carlo simulation works under these circumstances is to take the equity curve from your backtest and break it into smaller chunks (monthly returns, for example). Then you assume this represents the population of returns you can expect from your system. You then re-create alter...
by Eventhorizon
Wed Jul 13, 2011 1:09 am
Forum: Testing and Simulation
Topic: Curve Fitting
Replies: 6
Views: 2740

In short, yes - though I would not call it curve fitting: Curve fitting amounts to trying out so many things that you find something that appears to work but is only coincidence. What you are proposing is worse than curve-fitting it is using hindsight to ignore unfavorable outcomes. So how might you...
by Eventhorizon
Fri Jun 03, 2011 9:40 am
Forum: Testing and Simulation
Topic: Robust Optimization Question
Replies: 7
Views: 3558

jameskuah, I am not a professional, but I did sleep at a Holiday Inn Express last night,so here's my 2c. I agree with Chris that you seem to be doing all the right things. I would raise the following issues for consideration: 1) In / Out Of Sample Testing. I have wrestled with this issue at some len...
by Eventhorizon
Thu Jun 02, 2011 8:02 pm
Forum: Testing and Simulation
Topic: Anyone using MatLab, Octave, SciPy, the Language R
Replies: 22
Views: 11946

Here's another vote for R. 1) huge library of free code. 2) vectorize your problem and it is incredibly fast. 3) reasonable graphics with a little effort. I find it easy to transfer stuff between TBB and R as both can easily read and generate text files. I like the ease of use / reporting / graphics...
by Eventhorizon
Fri May 13, 2011 9:55 am
Forum: Data Providers and other non testing software
Topic: WARNING: CSI Dollar Index price bug
Replies: 8
Views: 4307

You will find a similar issue in the unadjusted closes for the Euro and ND. The Euro series is in Dmark 1998-12-31 and prior. ND is out by a factor of 10 for the entire series. On the Euro / Dmark issue, I believe CSI's position is "We report the unadjusted data as it was - if you want to convert it...
by Eventhorizon
Sat May 07, 2011 2:22 pm
Forum: Testing and Simulation
Topic: Input Parameter Rounding
Replies: 0
Views: 1704

Input Parameter Rounding

Just an FYI on an obscure issue that probably affects only me, but might be of use to someone out there ... When you enter a floating / percent parameter value (convert % inputs into decimals i.e. 1% = 0.01), TBB does some rounding: 1) If the number is greater than 10^5, the value is rounded to the ...
by Eventhorizon
Thu Apr 14, 2011 10:22 am
Forum: Money Management
Topic: Liz Cheval and Negative Correlation
Replies: 3
Views: 3191

CyTrend: I am not sure i understand how the asset can have "no long-term return" but have a "positive average monthly return" It's the difference between an arithmetic average rate of return and geometric average rate of return: consider monthly returns of 1.000% and -0.995% alternating. The arithme...