Abstract
dc:description.abstract<p>In chapter 1, we provide an extensive and systematic evaluation of the relative</p> <p>forecasting performance of several models for the volatility of daily spot</p> <p>crude oil prices. Empirical research over the past decades has uncovered</p> <p>significant gains in forecasting performance of Markov Switching GARCH</p> <p>models over GARCH models for the volatility of financial assets and crude</p> <p>oil futures. We find that, for spot oil price returns, non-switching models</p> <p>perform better in the short run, whereas switching models tend to do better</p> <p>at longer horizons.</p> <p>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.</p>
Degree
thesis:*- Name thesis:degree_name
- Ph.D.
- Level thesis:degree_level
- Open Access Dissertation
- Discipline thesis:degree_discipline
- Economics
- Year dc:date.available
- 2016
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Pastor, Daniel Joseph
- Contributors dc:contributor
-
- Robert Rossana
Subjects
dc:subject × 7Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.wayne.edu/oa_dissertations/1472
- OAI identifier oai:identifier
- oai:digitalcommons.wayne.edu:oa_dissertations-2471