Search results

The first question you should ask yourself when entering any trade or investment is not "How much do I want to make?" but "How much am I prepared to lose?" A sensible discussion cannot start until you clarify that point. If you are not prepared to lose anything at all, then no investment is...

Yes, I was about to say the same thing. The obvious strategy is to find the pair with the highest bid-ask spread in real terms, and then apply the maximum available leverage. The contest says a maximum of 4 orders per day (2 complete trades), so this is not a trivially easy way to blow an...

It's a worthwhile point Cesko, but one cannot ignore that 1. Japan was and still is a sort of military protectorate of the US and 2. China is an order of magnitude larger in population and resources than Japan. So yeah history rhymes, but it doesn't repeat ;) Who knows how this will all...

Interesting question - when I saw the title I assumed you might mean survivorship bias among *strategies* that you were backtesting. As for survivorship bias in the data you're using, I would have thought that the use of out of sample data at the end of any optimisation or selection procedure...

Thanks NoiseTrader. An interesting paradigm.

But Steve, surely your criticism is not to the point, since Raystonn is accusing the authors of optimisation. On that point the R2 statistic would tell us nothing other than how thoroughly the optimisation has been performed :)

Based on my own backtesting efforts, I would concur more or less 100% with Aaron's post above. Strategies of this type do indeed seem to profit over periods of 1 year or more, but their equity curves are not the kind of thing most people would be prepared to stomach. Sharpe ratios less than...

Beautiful idea :) I have some experience with nonlinear optimization, so it's easy for me to understand what you're talking about. Maybe I saw this least Pth idea many years ago, my memory fails me. I'd like to hear more about "equiripple polynomials" but I fear we strayed too far off topic :)

Thanks for the references and details. Interesting stuff. But I'm not sure I buy the argument as to stdev being more pessimistic and therefore better. If that were the reason to use sdev (sqrt(variance)), then why not use the 24th root of the mean of the 24th powers of the deviations...

Yes, I understand it's still not easy to imagine infinite variance. The problem is that the market is not solid like a metal rod in a science experiment (where we use variance just as a way of assessing our measurement inaccuracy), but it also seems that the market is not like the...

[in case it helps anyone on this: ] If you want to understand how infinite variance is possible, you first have to make sure you are clear about the meaning of variance. Variance can be expressed roughly as "the mean of the squares of the deviations of each data point from the mean of all...

Very good point, thank you for mentioning it. Sorry I didn't notice your post before. I'm going to go and update my backtesting code now :)

Yes, I understood this. My previous posts were a reply to pepper john, who said the opposite. But then back to my original question - why do autocorrelations give value to stops? If I see a clear autocorrelation in my trade returns, I would add a rule about position sizing dependent on...

I'm just saying that in my experience, setting stops to "cut out" the part of the distribution where a lot of losses are, often doesn't work at all. But I guess you have a lot more experience than me :) Tell me, have you often encountered clearly bimodal distributions of returns in your...

I'm sorry, I don't understand, please explain in more detail? Which peak is the second peak? And to be clear, are we looking at a histogram of *trade returns* or histogram of price movements in the market? Oh, OK, I thought we were talking about autocorrelation in the series of returns from...

I agree with this both empirically (have observed it often) and philosophically (imposing a target price on the market has no value *to the market* (only helpful to your risk management calculations), so just imposes transaction costs). But:- This is interesting to me; on what basis do you...

Just a thought, I'm no expert on these things - but how about Uranium?

As an answer to the original question in this thread, I would suggest looking into the Hurst exponent. Trendiness would be indicated by values significantly in excess of 0.5. You can measure it using the "rescaled range" calculation. This is very much a global, statistical measurement. Note...