An Examination of Stochastic Models for Crude Oil

Abstract

This thesis is going to compare different commodity spot price models, which have one, two or three stochastic factors. Specifically, it is going to compare how the different models are able to accurately model WTI Crude Oil spot prices. In order to do this, we will look at what makes each model different and then use Maximum Likelihood Estimation (MLE) and Kalman Filtering to estimate the parameters for each model. This will give us the tools to be able to compare the models based on the accuracy of their spot price predictions and parameter estimation. The analysis will show us how having more factors allows us to more accurately estimate spot prices and volatility.