Open Access Dissertation
Date of Award
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.
Pastor, Daniel Joseph, "Essays On Oil Price Volatility And Irreversible Investment" (2016). Wayne State University Dissertations. 1472.