Hdadou, Houda (2013-08). The Value of Assessing Uncertainty in Oil and Gas Portfolio Optimization. Master's Thesis. Thesis uri icon

abstract

  • It has been shown in the literature that the oil and gas industry deals with a substantial number of biases that impact project evaluation and portfolio performance. Previous studies concluded that properly estimating uncertainties will significantly impact the success of risk takers and their profits. Although a considerable number of publications investigated the impact of cognitive biases, few of these publications tackled the problem from a quantitative point of view. The objective of this work is to demonstrate the value of quantifying uncertainty and evaluate its impact on the optimization of oil and gas portfolios, taking into consideration the risk of each project. A model has been developed to perform portfolio optimization using Markowitz theory. In this study, portfolio optimization has been performed in the presence of different levels of overconfidence and directional bias to determine the impact of these biases on portfolio performance. The results show that disappointment in performance occurs not only because the realized portfolio net present value (NPV) is lower than estimated, but also because the realized portfolio risk is higher than estimated. This disappointment is due to both incorrect estimation of value and risk (estimation error) and incorrect project selection (decision error). The results of the cases analyzed show that, in a high-risk-tolerance environment, moderate overconfidence and moderate optimism result in an expected decision error of about 19% and an expected disappointment of about 50% of the estimated portfolio. In a low-risk-tolerance environment, the same amounts of moderate overconfidence and optimism result in an expected decision error up to 103% and an expected disappointment up to 78% of the estimated portfolio. Reliably quantifying uncertainty has the value of reducing the expected disappointment and the expected decision error. This can be achieved by eliminating overconfidence in the process of project evaluation and portfolio optimization. Consequently, overall industry performance can be improved because accurate estimates enable identification of superior portfolios, with optimum reward and risk levels, and increase the probability of meeting expectations.
  • It has been shown in the literature that the oil and gas industry deals with a substantial number of biases that impact project evaluation and portfolio performance. Previous studies concluded that properly estimating uncertainties will significantly impact the success of risk takers and their profits. Although a considerable number of publications investigated the impact of cognitive biases, few of these publications tackled the problem from a quantitative point of view.

    The objective of this work is to demonstrate the value of quantifying uncertainty and evaluate its impact on the optimization of oil and gas portfolios, taking into consideration the risk of each project. A model has been developed to perform portfolio optimization using Markowitz theory. In this study, portfolio optimization has been performed in the presence of different levels of overconfidence and directional bias to determine the impact of these biases on portfolio performance.

    The results show that disappointment in performance occurs not only because the realized portfolio net present value (NPV) is lower than estimated, but also because the realized portfolio risk is higher than estimated. This disappointment is due to both incorrect estimation of value and risk (estimation error) and incorrect project selection (decision error). The results of the cases analyzed show that, in a high-risk-tolerance environment, moderate overconfidence and moderate optimism result in an expected decision error of about 19% and an expected disappointment of about 50% of the estimated portfolio. In a low-risk-tolerance environment, the same amounts of moderate overconfidence and optimism result in an expected decision error up to 103% and an expected disappointment up to 78% of the estimated portfolio. Reliably quantifying uncertainty has the value of reducing the expected disappointment and the expected decision error. This can be achieved by eliminating overconfidence in the process of project evaluation and portfolio optimization. Consequently, overall industry performance can be improved because accurate estimates enable identification of superior portfolios, with optimum reward and risk levels, and increase the probability of meeting expectations.

ETD Chair

publication date

  • August 2013