Access Type

Open Access Dissertation

Date of Award

January 2016

Degree Type


Degree Name




First Advisor

Robert Rossana


In chapter 1, we provide an extensive and systematic evaluation of the relative

forecasting performance of several models for the volatility of daily spot

crude oil prices. Empirical research over the past decades has uncovered

significant gains in forecasting performance of Markov Switching GARCH

models over GARCH models for the volatility of financial assets and crude

oil futures. We find that, for spot oil price returns, non-switching models

perform better in the short run, whereas switching models tend to do better

at longer horizons.

In chapter 2, I investigate the impact of volatility on firms' irreversible investment decisions using real options theory. Cost incurred in oil drilling is considered sunk cost, thus irreversible. I collect detailed data on onshore, development oil well drilling on the North Slope of Alaska from 2003 to 2014. Volatility is modeled by constructing GARCH, EGARCH, and GJR-GARCH forecasts based on monthly real oil prices, and realized volatility from 5-minute intraday returns of oil futures prices. Using a duration model, I show that oil price volatility generally has a negative relationship with the hazard rate of drilling an oil well both when aggregating all the fields, and in individual fields.