![Page 1: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/1.jpg)
Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter.
Delft – 22-02-08www.ing.com
Adriaan Krul
![Page 2: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/2.jpg)
ING 2
Contents
Introduction
Convenience yield follows Ornstein-Uhlenbeck process
Analytical results
Convenience yield follows Cox-Ingersoll-Ross process
Analytical results
Numerical results
Conclusion
Further research
![Page 3: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/3.jpg)
ING 3
Introduction
A future contract is an agreement between two parties to buy or sell an asset at a certain time in the future for a certain price. Convenience yield is the premium associated with holding an underlying product or physical good, rather than the contract of derivative product.
Commodities – Gold, Silver, Copper, Oil
We use futures of light crude oil ranging for a period from 01-02-2002 until 25-01-2008 on each friday to prevent weekend effects.
![Page 4: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/4.jpg)
ING 4
Stochastic convenience yield; first approach
We assume that the spot price of the commodity follows an geometrical brownian motion and that the
convenience yield follows an Ornstein-Uhlenbeck process. I.e., we have the joint-stochastic process
![Page 5: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/5.jpg)
ING 5
In combination with the transformation x = ln S we have
![Page 6: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/6.jpg)
ING 6
Analytical results
Expectation of the convenience yield
Variance of the convenience yield
![Page 7: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/7.jpg)
ING 7
Analytical results
PDE of the future prices
Closed form solution of the future prices
![Page 8: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/8.jpg)
ING 8
Stochastic convenience yield; second approach
We assume that the spot price of the commodity follows an geometrical brownian motion and that the convenience yield follows a Cox-Ingersoll-Ross process. I.e., we have the joint-stochastic process
![Page 9: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/9.jpg)
ING 9
Together with the transformation x = ln S, we have
![Page 10: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/10.jpg)
ING 10
Analytical results
Expectation of the convenience yield
Variance of the convenience yield
![Page 11: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/11.jpg)
ING 11
Analytical results
PDE of the future prices
Closed form solution of the future prices
![Page 12: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/12.jpg)
ING 12
Kalman filter
Since the spot price and convenience yield of commodities are non-observable state-variables, the Kalman Filter is the appropriate method to model these variables.
The main idea of the Kalman Filter is to use observable variables to reconstitute the value of the non-observable variables. Since the future prices are widely observed and traded in the market, we consider these our observable variables.
The aim of this thesis is to implement the Kalman Filter and test both the approaches and compare them with the market data.
![Page 13: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/13.jpg)
ING 13
Kalman Filter for approach one.
Recall that the closed form solution of the future price was given by
From this the measurement equation immediately follows
![Page 14: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/14.jpg)
ING 14
From
we can write
![Page 15: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/15.jpg)
ING 15
Kalman filter for approach one
The difference between the closed form solution and themeasurement equation is the error term epsilon.This error term is included to account for possibleerrors. To get a feeling of the size of the error, suppose that the OU process generates the yields perfectly and that the state variables can be observedform the market directly. The error term could then bethought of as market data, bid-ask spreads etc.
![Page 16: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/16.jpg)
ING 16
Kalman filter for approach one
Recall the join-stochastic process
the transition equation follows immediately
![Page 17: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/17.jpg)
ING 17
For simplicity we write
![Page 18: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/18.jpg)
ING 18
Kalman filter for approach two
From
it follows
![Page 19: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/19.jpg)
ING 19
Kalman filter for approach two
Recall the join-stochastic process
the transition equation follows immediately
![Page 20: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/20.jpg)
ING 20
For simplicity we write
![Page 21: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/21.jpg)
ING 21
How does the Kalman Filter work?
We use weekly observations of the light crude oil marketfrom 01-02-2002 until 25-01-2008. At each observation weconsider 7 monthly contracts. The systems matrices consists of the unknown parameter set. Choosing an initial set we can calculate the transition and measurement equation and update them via the Kalman Filter. Then the log-likelihood function is maximized and the innovations (error between the market price and the numerical price) is minimized.
![Page 22: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/22.jpg)
ING 22
How to choose the initial state.
For the initial parameter set we randomly choose the value of the parameters within a respectable bound.For the initial spot price at time zero we retained it as the future price with the first maturity and the convenience yield is initially calculated via
![Page 23: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/23.jpg)
ING 23
Numerical results for approach one
![Page 24: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/24.jpg)
ING 24
Log future prices versus state variable x
![Page 25: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/25.jpg)
ING 25
Implied convenience yield versus state variable delta
![Page 26: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/26.jpg)
ING 26
Innovation for F1
![Page 27: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/27.jpg)
ING 27
Kalman forecasting applied on the log future prices
![Page 28: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/28.jpg)
ING 28
Kalman Forecasting applied on the state variables
![Page 29: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/29.jpg)
ING 29
Conclusion
We implemented the Kalman Filter for the OU process. Both the convenience yield as well as the state variable x (log of the spot price) seems to follow the implied yield and the market price (resp.) quite good. Also, different initial values for the parameter set will eventually converge to the optimized set with the same value of the log-likelihood. This is a good result and tests the robustness of the method.
The main difference between the systems matrices of both processes is the transition error covariance-variance matrix Vt. In the CIR model, this matrix forbids negativity of the CY. We simply replaced any negative element of the CY by zero, but since it is negative for a large number of observations, this will probably give rise to large standard errors in the optimized parameter set.
![Page 30: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/30.jpg)
ING 30
Conclusion
The Kalman Forecasting seems to work only if there is no sudden drop in the data. To improve the Kalman Forecasting we could update it every 10 observations.
![Page 31: Calibration of Stochastic Convenience Yield Models For Crude Oil Using the Kalman Filter](https://reader036.vdocument.in/reader036/viewer/2022062411/56814ca9550346895db9afd7/html5/thumbnails/31.jpg)
ING 31
Further research
• Implement the Kalman Filter for the CIR model• Inserting a jump constant in the convenience yield• Compare both stochastic models• Pricing of options on commodities, using the optimized
parameter set