Welcome to NexusFi: the best trading community on the planet, with over 150,000 members Sign Up Now for Free
Genuine reviews from real traders, not fake reviews from stealth vendors
Quality education from leading professional traders
We are a friendly, helpful, and positive community
We do not tolerate rude behavior, trolling, or vendors advertising in posts
We are here to help, just let us know what you need
You'll need to register in order to view the content of the threads and start contributing to our community. It's free for basic access, or support us by becoming an Elite Member -- see if you qualify for a discount below.
-- Big Mike, Site Administrator
(If you already have an account, login at the top of the page)
Back to this homework, I got a few questions:
I assume you look at the "term structure" with the 5-year spread data, in this case in clear Contango.
1) Do you use normally linear regression instead of polynomial for spreads? I noticed you used polynomial for flies in a different post. Do you normally use polynomial regression for the flies?
2) You mention you shorted the fly. I am not savvy on statistics but what deviation made you go ahead with this decision? I guess the graph is clear on showing this but I was wondering if there is a numerical sweet spot?
3) Finally, would it be possible that the fly just stays on backwardation and changes the spread? That is, that the fly never reverses and changes the structure?
Trading: Primarily Energy but also a little Equities, Fixed Income, Metals, U308 and Crypto.
Frequency: Many times daily
Duration: Never
Posts: 5,059 since Dec 2013
Thanks Given: 4,410
Thanks Received: 10,226
If I was trading spreads, or just trying to identify spreads that look statistically cheap or expensive one way I would do this would be a polynomial regression. Spread curves tend to be most pronounced at the front, and flat at the back, and as such linear doesn't work well.
In theory the same applies for flies but in reality that's not always the case. For example ZMZ 6 month flies trade at a premium to MZM flies. Hence it's often difficult to fit a single model.
You've gone a long way back in time so I obviously can't remember exactly what I had on, or why.
What I actually seem to have said though was
Full Disclosure:- I am slightly short this Butterfly but do have hedges on against it
I suspect that what I was saying is that I was short this fly (the chart shows it's a full $1 above a simple linear prediction) but as protection I was long something similar, as protection against it. Given that this was the z678 fly I suspect I was long z567 and/or z789 against it.
Yes of course.
I know this is different than many/most people but I'm thinking in terms of relative value. It's not a question of backwardation or contango. Or even -$1 vs -50c. It's where is this (whatever 'this' is) relative to 'something else'.
First of all thank you for all your posts in this thread. I have learned a lot and I think I speak for many when I say this.
Sorry if I am being too inquisitive and if you dont wish to answer sth thats ok.
How sensitive to fundamentals would you say is your decision making (or your models)? ie. Inventory data, etc? I ask this because I guess your statistical approach to trading (from what Ive read) could be used with other instruments but you seem to trade CL mostly (only?)...
Trading: Primarily Energy but also a little Equities, Fixed Income, Metals, U308 and Crypto.
Frequency: Many times daily
Duration: Never
Posts: 5,059 since Dec 2013
Thanks Given: 4,410
Thanks Received: 10,226
One of the ways I try and protect myself from fundamentals is that I start scaling my positions down linearly once we reach 100 trading days to expiry (almost 5 months) so that I have no position at 50 days to expiry.
Unfortunately I seem to be unable to find any other markets that have a long term defined forward curve, where something like this may also work other than Eurodollars (not USD:EUR). I started experimenting with Eurodollars earlier in the year but so far the results have been insignificant/unimpressive.