Search results

Thanks! Do you have any thoughts on arithmetic vs. geometric means and standard deviations when computing Sharpe ratios and for position sizing? If a geometric standard deviation is preferred how is this used together with an exponentially weighted moving standard deviation for position sizing?

Would you consider doing this when computing the combined forecast i.e. making a long only rule and then including that in the portfolio of rules?

Thanks. That's much clearer now. So if I understand correctly more diversification means lower volatility, so to maintain the same level of volatility (e.g. to stay at half-Kelly) we will have to trade more contracts. This in turns means higher trading costs.

I think I understand where my confusion is coming from. I've been calculating the normalized trading cost (standardized cost * turnover) for each instrument, and then adding it up across the instruments in the portfolio. Now I'm thinking that since the instrument trading cost is normalized it...

From what you've written it seems like you're estimating trading costs using this approach, rather than just computing them directly. There are a few things I can't follow here: The trading costs are in terms of normalized turnover. I thought this turnover was volatility normalized, but from...

I've been reading and coding up the framework you describe in your book. One question: when computing costs you use the volatility normalized turnover. If this is calculated in backtesting do we simply compute the number of instrument blocks traded at each specific date, divide this by the...

With this in mind, if someone had all of their capital in a trading system, would it be worth including 'buy and hold' as one of the strategies to add diversity, in addition to other strategies like trend following and carry?

That makes a lot of sense. Thank you.

This thread is really interesting. Thank you for sharing your experience. Your book is a great read as well. One question, at what point will margin calls become an issue on your portfolio? Would this only happen if you have a 100% drawdown or could you be subject to this sooner? If so how do...

Thanks for the suggestions. I'm reading through @garachen's posts now. It's rapidly becoming apparent how much negativity there is on this forum. On the flip side it's amazing how much the signal to noise ratio improves when you just put every negative person on ignore.

I'm probably just arguing semantics but the way this is stated it seems the answer should be $0.75 for the option of rolling again. That is, you pay $3.50 to roll the dice, and an additional $0.75, prior to the first roll, for the option of rolling again.

Yeah. Agree completely. However many people are doing this without realizing by applying a moving average to compute the trend. Whether you apply filtering in the time domain with a moving average, or in the frequency domain, it's equivalent. The same assumptions of stationarity are being made...

I never made any statement on the effectiveness of TF. You are making statements about the effectiveness of signal processing. If you're using a moving average you're using signal processing, if you're using auto-regressive models or other time series analysis you're using signal processing...

One could say the same thing about trend following. It's very unlikely that there is one thing that is the 'key' to the market, if there was it would be discovered pretty quickly and the edge would be lost. These are useful tools to add to your bag and allow you a broader perspective on the...

If you haven't come across it yet I highly recommend Technical Analysis of Stocks and Commodities magazine. It has some good trading ideas.

Thanks again for the references. This is all really interesting stuff. It looks like he stopped recommending his earlier frequency discriminators in 2007 and is now suggesting using what he calls the 'autocorrelation periodogram', which is a misnomer. What he actually implements in code is just...

Thanks for the pointer. You're referring to the article in S&C November 2008 right? Looks like he's just using a spectrogram to determine the dominant market frequency. There's a few issues with this: if the cycles are not sinsusoids there will be harmonics and you may lock onto those instead...

First of all just to clear something up. Predicting and forecasting relates to events that occur in the future. You do not predict something that is occurring now or in the past, that is called an estimate. Specifically if you estimate the distribution of a random variable, and it's moments...

I'm just getting started with trading so figured now is a good time to start a journal. A bit about me: I have a PhD in signal processing and optimization and spent the last 10 years in industry as a software engineer developing signal processing and machine learning algorithms. Hopefully this...