I am Airliner.I want to protect my business from price volatility of jet fuel cost.Jet fuel is not traded in futures market but Crude oil is traded in futures market. I have daily spot prices of jet fuel and contract prices of crude oil. e.g. on 19th April,spot price(Jet fuel) is 100.April contract price (crude oil) = 103,May contract price = 110,June Contract price =118 and July contract price = 109 and August price = 125. Spot and contract prices change on daily basis as per demand-supply dynamics.

Should I find correlation between spot price on particular date and contract prices on that date for all contracts? How should I go about it? Please help me with approach.

  • $\begingroup$ This stupid app won't let me post a comment, so this will go in the answer section. Could you be more specific? This sounds like a question from a textbook. If so, probably would help to know the text, then I could pinpoint what they are looking for. My guess is if you're an airline, you're not actively trading futures: so time series analysis is out the window. The most simple approach would simply be to buy futures in the months you think oil would rise, at a ratio defined by the slope of the linear correlation between jet fuel and spot oil. $\endgroup$ – Dylan_Larkin Apr 19 '15 at 6:48
  • $\begingroup$ 1) No.It's not from any textbook. 2) We can assume that airlines trade Crude future contracts in the market. 3) I have daily data available for spot and future prices.Should I use,say,19th April's spot price and future prices of april,may,june,July and August contracts on that day? How should I establish correlation? $\endgroup$ – user2122922 Apr 19 '15 at 14:07

Well, because I'm new to this site, I am not allowed to comment. I will answer and have a moderator move it to the comments section (again).

Honestly, your question is way too broad. What do you mean by "daily data"? Tick data? Daily closing prices? Both? The literature on futures hedging is endless, so you need to be more specific in what context you need this answered, then I can be of more help.

Regressing futures prices against the underlying spot price is sort of circular. There are well known futures pricing models (based off spot, risk-free rates, etc... See Options, Futures and Other Derivatives by John C. Hull, for starters) that should theoretically GIVE you the futures price based off of spot.

Another approach is using spot prices and the yield curve to bootstrap an implied futures/spot relationship extending to the deferred months. This lets you see what the market is implying about futures prices of the deferred months, and where things are actually trading (due to liquidity issues, etc... This is common in products like soybeans, eg).

EDIT: Just to clarify, the reason you wouldn't want to regress the futures price against the underlying is that we already know there is a very direct correlation between the two assets. The spot asset is used in deriving the fair-value futures price. To use a concrete example, there are well known formulas to price out US Treasury futures based off of cash treasuries. What you're suggesting is to regress Treasury futures against treasury cash, and that is just silly. What you should be doing is regressing the Treasury BASIS (essentially buying the cash vs selling future and vice versa) against some other, external stimuli (like the Fed Funds rate, or the temperature outside - to use a silly example).

| cite | improve this answer | |
  • $\begingroup$ By daily data,I mean closing price.Thanks for response. I have collected data(historic prices).Let me tell you something about prices.April contract opens in 10th December previous year and expires on 20th April.So 20th April spot price can be put into equation using future prices of April,May,June,July and August contract on that day.But 21st April will have one variable because of April contract expiry.Again on 10th May,we will have additional variable September contract prices.When I tried to solve it using multiple regression in Excel,I got error since some of the fields were blank.conti.. $\endgroup$ – user2122922 Apr 20 '15 at 11:10
  • $\begingroup$ e.g. April Future contract price on 21st April.I don't know how to proceed further.Should I split my data in various intervals and then apply multiple regression?In that case,how should I collate the data in the end? Please let me know if my approach is wrong.Thanks for reading. $\endgroup$ – user2122922 Apr 20 '15 at 11:11
  • $\begingroup$ Well, one thing you want to do is take note of the spot month, or the month that exhibits the highest volume. Typically, that is the closest month to expirty. $\endgroup$ – Dylan_Larkin Apr 21 '15 at 3:18
  • $\begingroup$ HOWEVER, there is something called the "roll" where traders roll their futures from the expiring month into the next month closest month, or the next serial month, whichever has more volume. That contract then becomes the "top" contract, named so because the location pit traders used to stand in order to trade it (the top of the steps). Free information is available to see which contract exhibits the most volume and when there is a switch. Perhaps this is free too, but subscription software will actually produce a smoothed curve to account for these gaps that you undoubtedly are now aware of. $\endgroup$ – Dylan_Larkin Apr 21 '15 at 3:18

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.