AEB 6182

Agricultural Risk Analysis and Decision Making

This course reviews the conceptual framework and research methods for analysis of decision-making under risk by agricultural producers. The course covers expected utility theory, risk programming, stochastic dominance, and dynamic decision models. Prerequisites: AEB 6106

Instructor:  Charles B. Moss
             1121 McCarty Hall
             Phone: 392-1847
             Email: cbmoss@ifas.ufl.edu

Class meets for 2 hours on Tuesday and Thursday. Grades will be assigned based on biweekly homework, two examinations (a mid-term and a final), and a term project. I am willing to meet outside of class for consultations on the students' term projects.

Textbooks: There are three primary textbooks uses in this course:

Anderson, Jock R., John L. Dillon, and J. Brian Hardaker. Agricultural Decision Analysis (Ames, Iowa: Iowa State University Press, 1977).

Barry, Peter J. Risk Management in Agriculture (Ames, Iowa: Iowa State University Press, 1984).

Dillon, John L. The Analysis of Response in Crop and Livestock Production (New York: Pergamon Press, 1979).

Unfortunately, the first two references are out of print. Therefore, copies of the relevant sections of these books will be left in the secretarial office at 1120 McCarty Hall. In addition to these references, other readings from the literature will also be required. The most current copy of the reading list as well as lecture notes will be available on the internet at http://128.227.113.185/aeb6182.risk/syllbus.html.To facilitate classroom discussion I have a established a teaching bulletin board at http://ricardo.ifas.ufl.edu/cgi-bin/YaBB/YaBB.cgi

Computing: The software used in this course are available on either my DEC Alpha/OSF workstation or the department network. OSF is a variant of Unix and can be operated with Xwin, a Windows terminal emulator. GAMS is a standard program on the department network. Further, a student version of GAMS is available with the users guide at a reasonable price. A student version of Mathematica is also available through the Technology Hub.

Grading: The grade for this class will be assigned based on two examinations, a term project, class participation, and homework as follows:

Mid - Term Examination
25%
Final Examination
35%
Term Project
25%
Homework
10%
Class Participation
5%

Homework is due on two week increments. Each assignment will be handed out at the beginning of each increment and will involve topics covered over that time span. For example, the first assignment will involve the computation of expected utilities and certainty equivalents. Assignments are intended to diagnose the students understanding of material as it is covered in class and provide the basis for classroom discussion of the application of risk theory. The term project consists of two components (1) a written paper of a relevant application of risk theory less than 12 pages in length and (2) an oral presentation of the results for the class. The intent of this project is to prepare the students for the contributed paper process followed by most academic societies. The 5% assigned to class participation is intended to guarantee that the students are attending classes and keeping up with the required readings.

Course Outline
  1. Expected Utility
  2. Risk Aversion
  3. Expected Value-Variance
  4. Portfolio Analysis
  5. Risk Programming

Midterm October 14
  1. Stochastic Dominance
  2. Dynamic Decision Rules
  3. Market Models
  4. Option Models of Risk
  5. State Contigent Production Models"

Final Examination Thursday December 19, 12:30-2:30

Class notes will be offered in Adobe Acrobat PDF format. The Acrobat read is available at http://www.adobe.com/acrobat/readstep.html.
Expected Utility

The basic economic notions of decision making under risk are based on the concept that economic agents make decisions that maximize their expected utilities. This section of the course develops the basis for this theory and how this basic tenant is used to analyze decisions under risk.

Course Outline
Risk Aversion

Course Outline
Expected Value-Variance

Course Outline
Portfolio Analysis

Course Outline
Risk Programming

The historic difficulties in eliciting utility functions and direct maximization of expected utility originally lead to the development of the mean-variance or of risk programming models. Historically, agricultural economics has focused on mean-variance models to design a crop portfolio. More recent advances include the use of risk programming models to study optimal leverage and other sequential decision processes.

Course Outline
Stochastic Dominance

An alternative to either assuming a utility function or approximating the utility maximizing behavior with mean-variance rule is the use of efficiency criteria. One group of those efficiency criteria are known as stochastic dominance criteria. The most popular of these criteria are first and second degree stochastic dominance along with stochastic dominance with respect to a function. In the first case the only economic assumption required is that the decision maker prefers more to less. In the second two criteria we must assume something about the utility function.

Course Outline
Dynamic Decision Rules

Our discussion of dynamic decision rules will focus on the value of information and stochastic optimal control. As a starting point, we will discuss the value of information without risk aversion with some discussion of Bayesian decision making. Our discussion of the value of information will then provide an introduction to stochastic dynamic programming which will lead into a discussion of stochastic optimal control.

Course Outline
Market Models

Beyond the use of risk efficiency rules, another approach to incorporating risk into agricultural decision models is to use information implied by the financial markets. This approach is based on the theory of financial markets. However, because of the lack of publically traded equities in agriculture, we typically rely on aggregated data and worry about barriers to entry.

Option Models of Risk

Another link to the financial economics literature is the use of option models to quantify the value of an investment under risk. Most of this work originates with the work of Dixit and Pindyck.

Course Outline
State Contingent Production Models

Course Outline
My Guestbook

Statistics by Awstats