This article briefly reviews the theory of decision making under uncertainty and the programming methods used to consider uncertainty in farm planning. A multiperiod MOTAD model is developed to analyze the risk and return of a farm's investment financing, production, and marketing plans. The results of an empirical model of a beginning farmer in the Corn Belt are briefly presented to illustrate the potential applicability of the multiperiod MOTAD model and demonstrate the type of information generated. Most farm management decisions are made under conditions of uncertainty. This uncertainty in agriculture arises from market forces, weather, disease, insect damage, and other factors that cannot be controlled or accurately predicted. However, many agricultural economic models used to study farm management problems are specified under assumed certainty. For example, conventional linear programming used extensively in farm planning analyses does not accurately accommodate uncertainty. Of course, assumed yields and prices can be changed in these models to see how the farm organization is affected by changes in these variables. But there is no measurement of the risk associated with each farm organization. As a result, the conventional linear programming solutions for farm organization have often been rejected because, these solutions may specify actions that lead to a higher degree of risk than many farm managers are willing to accept [3, 5]. The objective of this article is to present a multiperiod linear programming model that can be used to evaluate farm management decisions under uncertainty. The discussion will begin with a review of the concepts of decision making under uncertainty. Then numerical analysis techniques will be discussed with emphasis on dynamic risk models. Finally, recent numerical results obtained from the use of a multiperiod MOTAD (Minimization of Total Absolute Deviations) model will be presented to illustrate its potential in dynamic risk analysis. DECISION MAKING UNDER UNCERTAINTY We assume that the objective of the rational individual is to maximize utility. Utility is derived from present and future consumption. Consumption, in turn, is a function of income. Utility can then be expressed as a function of income as:
[1]
A. M. M. McFARQUHAR.
RATIONAL DECISION MAKING AND RISK IN FARM PLANNING–AN APPLICATION OF QUADRATIC PROGRAMMING IN BRITISH ARABLE FARMING.
,
1961
.
[2]
John G. Stovall.
Income Variation and Selection of Enterprises
,
1966
.
[3]
John L. Dillon,et al.
An Expository Review of Bernoullian Decision Theory in Agriculture: Is Utility Futility?
,
1971
.
[4]
H. Markowitz.
Portfolio Selection: Efficient Diversification of Investments
,
1971
.
[5]
A. Stuart,et al.
Portfolio Selection: Efficient Diversification of Investments
,
1959
.
[6]
R. Freund.
THE INTRODUCTION OF RISK INTO A PROGRAMMING MODEL
,
1956
.
[7]
N. H. Hakansson..
ON OPTIMAL MYOPIC PORTFOLIO POLICIES, WITH AND WITHOUT SERIAL CORRELATION OF YIELDS
,
1971
.
[8]
Harold J. Larson,et al.
Introduction to Probability Theory and Statistical Inference
,
1974
.
[9]
J. Brake.
Firm Growth Models often Neglect Important Cash Withdrawals
,
1968
.
[10]
Michael J. Brennan,et al.
The Geometry of Separation and Myopia
,
1976,
Journal of Financial and Quantitative Analysis.
[11]
John T. Scott,et al.
A Practical Way to Select an Optimum Farm Plan Under Risk
,
1972
.
[12]
C. Richard Shumway,et al.
Farm Planning and Calf Marketing Strategies for Risk Management: An Application of Linear Programming and Statistical Decision Theory
,
1979
.
[13]
H. J. Larson.
Introduction to Probability Theory and Statistical Inference
,
1970
.
[14]
J. Tobin.
Liquidity Preference as Behavior towards Risk
,
1958
.
[15]
Peter B. R. Hazell,et al.
A Linear Alternative to Quadratic and Semivariance Programming for Farm Planning under Uncertainty
,
1971
.
[16]
E. Kaiser.
An economic evaluation of alternative financial strategies used by beginning farmers to enter agriculture
,
1979
.
[17]
Van Horne,et al.
Financial Management and Policy
,
1968
.