Risk and Decision Analysis
- Probability definitions, objective and subjective, calculation rules, expected value
- Simple exploration economics
- Decision trees
- Bayes formula and the Value of Information (VOI)
In Day 1 basic concepts of probability and economics will be recalled, and decision analysis tools presented. A case study will illustrate the value of perfect information and another will combine decision trees and Bayesian inversion to show how the probability of geologic success should be revised to incorporate new seismic information and how the quality of this information impacts its value.
Decision continued and Uncertainty
- Utility curves, risk attitudes, and cognitive biases
- Deterministic versus probabilistic: what is the difference?
- Histogram, pdf, cdf, percentiles, mean, mode, median, standard deviation
- Standard error of the mean
- Random and systematic errors and how to deal with them
- The flaw of averages, the winner’s curse
After completion of the VOI case study Day 2 will follow with psychological aspects of decision making. The rest of the day will be devoted to a review of the most common descriptive statistics and a discussion of estimation in general.
Monte Carlo and Applications
- A review of the most common distributions used in geosciences
- The Monte Carlo approach
- Presentation of @RISK™, a Monte Carlo add-in for Excel™
- Computing uncertainty on STOIIP
Day 3 will focus on Monte Carlo simulation and hands-on applications. A case study of estimation of the production increase expected from a workover program will demonstrate the importance of scale in assessing uncertainty. The issues of multi-prospect evaluation will close the day.
- Shared Risk Model
- Cluster development evaluations under geological dependencies
- Portfolio issues and Efficient Frontier
- Correlation, interpretation and effects
Half of Day 4 will be devoted to modeling the development of geologically dependent reservoirs drilled by a single well and of a cluster of dependent, geographically dispersed, fields drilled separately, and to providing scenarios for planning and economics. Portfolio issues will be briefly discussed and an exercise will illustrate the effects of diversification. The day will close with correlation and its significance.
Trend Lines and Review
- Least squares
- The predictive value of a trend line
- General wrap-up of the week
In Day 5 uncertainty on fluid densities computed from pressure data will take participants through the various steps involved in establishing and checking a regression model and deriving prediction uncertainty. The session will end with a wrap-up of the week, main technical messages, and answering questions from the audience.
Anyone interested in learning more about the approach and techniques of risk, uncertainty, and decisions in E&P projects.
Some basic statistics knowledge would be a plus but is not required.