Search results

Deleted my post as there seems to have been a lag at my end on seeing djames’ response (should have pressed refresh I guess)

:) - yes, of course. Thanks

In that case I am a bit stumped. The problem I am facing is that two instruments in particular (BRL, sugar) have such large -ve annualised forecast returns (anyone else see this?) that they overwhelm the forecast returns of every other instrument when pooled together. So if I pool, I end up with...

Thank you for this. Different, probably dumb, question. Again a yes or no would be fine as no doubt your academic duties are keeping you busy. I am currently filtering instruments with the help of the various tiebreakers in your book plus some shortcuts. For example, even before optimising...

Hi GAT, I was wondering if I might trouble you with a quick question on how I might use pooling to calculate the FDM for your system. When you pool the correlations are you a) simply getting the correlations of the forecasts for each instrument and averaging them out or b) are you stacking up...

Of course, that makes much more sense. This time I blame the Xmas booze :). There might be a few further attempts to drink and think in the upcoming year, so apologies in advance. In the meantime, I wish you a very successful 2018!

If you don't want to do your own stitching, you should have a look at quandl's db which offers a stitched database of the main futures contracts based on simple algos such as OI crossover.

Hi Rob, I have been trying to wrap my head around changing skew over different measurement frequencies (prior discussion of it in your journal on page 51). I was wondering if this has anything to do with returns volatility hammering any +ve drift in the short term but over longer measurement...

As GAT might have mentioned in his posts, the stitched price will vary subtly based on the roll algo (i.e. which day your algo stitches prices together as that determines the size of the adjustments) and which price contract you use. For that reason Quandl's own rolling algo is unlikely to match...

Agree it is weird.

Yes of course, I should have picked up on that. Thanks

The answer to your question is most likely on this page:

Hi sorry if I am butting in again, :), but interesting discussion. Reading between the lines, it seems you are saying one sensible approach is to allocate equally to carry and momentum and then apply the FDM to each style separately to alter the relative allocations? From what I recall from your...

Ok, thank you!

Sorry to butt in but, to be clear, GAT, are you saying there are multiple flavours of carry in your system (perhaps different smooths?) or do you simply downweight carry due to the lower number of carry variations?

Just to add my two cents: I believe the vix rolls are quite variable. You can try to match them by checking out the carry file which has the relevant ones listed for each day. Out of interest, what quandl code are you using to download the vix?

Hi GAT, minor thing. Just doing a comparison between your legacy stitched prices and mine and everything looks to be fairly consistent. However I noticed what looks like a rogue datapoint in your EUR file. On 11/06/2015 it shows a ~ 20 pts fall from previous day (1.329 -> 1.139). The carrydata...

Thanks and congrats on your latest performance!

Hi GAT, I am trying to work through and make sure my backtesting logic is sound. I note the industry practice, and your preference, is to use the 'current' day's signal on the next day's price for backtests, which I understand is linked to avoiding some sort of data snooping. However, if the...

Thank you