Remarkable advance in quantitative marketing research in the last two decades, incorporating applied microeconomic theories, operations research and management applications, has brought the field of marketing alongside with finance, accounting and productionto within an executive'sreach for a sophisticatedtoolbox for decision making in an increasingly competitive and complex business environment. A quick look at Marketing, a recently published book edited by Eliashberg and Lilien would indicate even to the casual reader the extent of such methodological progress made by marketing scholars. Even in such an impressive and nearly exhaustive collection oftopics, with the notable exception pointed out by the editors of applicationsofthe scanner data, and in spite of the reference to it, an important omission is related to the issues ofmarketing decisions under conditions ofuncertainty. It is fairly obvious to the marketing executive and academician alike to recognize the important role uncertaintyplays in marketingdecisions such as pricing, promotion, advertising, sales force management, and others. The major purpose of this study is to address certain major marketing decision variables within the general context of an uncertain environment. While there have been significant progresses in analyzing marketing behaviors in a stochastic environment,the sourcesscatteramong differentmanagementandmarketingjoumals; and to the extent that these issues are addressed at all, they have aimed mainly at each separate, specifictopic at a time. Thus, our effort to bring these studies together in the same framework should facilitate our in-depth analysis of these important phenomena.

1. Introduction. 1.1. Formulating the risk problem. 1.2. Decision criteria. 1.3. Decision making under risk : fact and fiction -- 2. Probability theory - a mathematical basis for making decisions under risk and uncertainty. 2.1. Set theory and probability. 2.2. Random variables. 2.3. Conditional probability and independence. 2.4. Some useful distribution functions. 2.5. Expected value, moments, and the moment generating function. 2.6. Estimating probability functions. 2.7. Martingales and random walks. 2.8. Summary -- 3. Expected utility - the economic basis of decision making under risk. 3.1. Consumption and utility. 3.2. Expected utility. 3.3. Expected value - variance and expected utility models. 3.4. Problems with expected utility. 3.5. Summary -- 4. Risk aversion in the large and small. 4.1. Arrow-Pratt risk aversion coefficient. 4.2. Eliciting risk aversion coefficients. 4.3 Summary -- 5. Portfolio theory and decision making under risk. 5.1. The expected value - variance frontier. 5.2. A simple portfolio. 5.3. A graphical depiction of the expected value-variance frontier. 5.4. Mean-variance versus direct utility maximization. 5.5. Derivation of the expected value-variance frontier. 5.6. Summary -- 6. Whole farm-planning models. 6.1. Farm portfolio models. 6.2. Minimize total absolute deviation. 6.3. Focus-loss. 6.4. Target MOTAD. 6.5. Direct utility maximization. 6.6. Discrete sequential stochastic programming. 6.7. Chance-constrained programming. 6.8. Interpreting shadow values from risk programming models. 6.9. Summary -- 7. Risk efficiency approaches - stochastic dominance. 7.1. Stochastic dominance. 7.2. Applications of stochastic dominance. 7.3. Summary -- 8. Dynamic decision rules and the value of information. 8.1. Decision making and Bayesian probabilities. 8.2. Concepts of information. 8.3. A model of information. 8.4. Summary -- 9. Market models of decision making under risk. 9.1. Risk equilibrium from the consumer's point of view. 9.2. The role of the riskless asset. 9.3. Risk equilibrium from the firm's perspective. 9.4. Arbitrage pricing theorem. 9.5. Empirical applications of capital market models. 9.6. Summary -- 10. Option pricing approaches to risk. 10.1. Introductions to options and futures. 10.2. Real option valuation. 10.3. Crop insurance. 10.4. Summary -- 11. State contingent production model : the stochastic production set. 11.1. Depicting risk and input decisions in the production function. 11.2. State Production set and input requirement set. 11.3. Distance functions and risk aversion. 11.4. Summary -- 12. Risk, uncertainty, and the agricultural firm - a summary and outlook

In the midst of a changing economy, most executives continue to use a strategy toolkit designed for yesterday's more stable marketplace. As a result, strategies emerge that neither manage the risks nor take advantage of the opportunities that arise in highly uncertain times. Now, McKinsey shows strategists how to tailor every aspect of the decision-making process-from formulation to implementation-to the level of uncertainty faced, describes the strategic-planning processes readers can use to monitor, update, and revise strategies as necessary in volatile markets, and includes a toolkit for identifying, developing, and testing new strategy options-complete with guidelines for applying the right tool to the right situation at the right time. A comprehensive approach to strategy development under all possible levels of uncertainty and across all kinds of industries, this is the essential guide for making tough strategic choices in a changing world. Hugh Courtney is an Associate Principal with the Global Strategy Practice at McKinsey Company in Washington D.C.

The theory of optimal decisions in a stochastic environment has seen many new developments in recent years. The implications of such theory for empirical and policy applications are several. This book attempts to analyze some of the impor tant applied aspects of this theory and its recent developments. The stochastic environment is considered here in specific form, e.g., (a) linear programs (LP) with parameters subject to a probabilistic mechanism, (b) decision models with risk aversion, (c) resource allocation in a team, and (d) national economic planning. The book attempts to provide new research insights into several areas, e.g., (a) mixed strategy solutions and econometric tests of hypotheses of LP models, (b) the dual problems of efficient estimation and optimal regulation, (c) input-output planning under imperfect competition, and (d) linear programs viewed as constrained statistical games. Methods of optimal decision rules developed here for quadratic and linear decision problems are applicable in three broad areas: (a) applied economic models in resource allocation, planning and team decision, (b) operations research models in management decisions involving portfolio analysis and stochastic programming, and (c) systems science models in stochastic control and adaptive behavior. Some results reported here have been published in professional journals be-. fore, and I would like to thank the following journals in particular: Inter national Journal of Systems Science, Journal of Optimization Theory and Applica tions and Journal of Mathematical Analysis and Applications.