Decision Theory

Decision making process

Identification of the various possible outcomes, called states of nature or events, Eis, for the decision problem. The events are beyond the control of the decision maker. Identification of all the courses of actions, Ajs, or the strategies that are available to the decision maker. The decision-maker has control over choice of these. Determination of the pay-off function which describes the consequences resulting from different combinations of the acts and events.the pay-off may be designated as Vijs the pay-off resulting fron the ith event and jth strategy. Choosing from among the various alternatives on the basis of some criterion, which may involve the information given in step(c) only or which may require and incorporate some additional information.

Decision making models

The econological model or economic man model The bounded rationality model or administrative man model The implicit favorite or games man model

ECONOLOGICAL MODEL
The ECONOLOGICAL MODEL rests on two assumptions It assumes that people are economically rational and that they will select the decision or course of action that has the greatest advantage or payoff from the many alternatives It also assumes that people attempt to maximize outcomes in an orderly and sequential process by going about the search for the best alternative in a planned, orderly and logical fashion.

1. 2.
3. 4. 5. 6. 7.

A basic econological decision model suggests the following orderly steps in the decision process: Discover the symptoms of the problem or difficulty Determine the goal to be achieved or define the problem to be solved Develop a criterion against which alternative solution can be evaluated Identify all alternative courses of actions Consider the consequences of each alternative as well as the likelihood of the occurrence of each. Choose the best alternative by comparing the consequences of each alternative (step 5) with the decision criterion (step 3) Act or implement the decision

Set goal or define problem

Discover symptoms

Select best alternativs

Act or implement the decision

Develop criterion

Develop all alternatives

Determine all outcomes

THE ECONOLOGICAL MODEL

Disadvantages
This model is unrealistic since it makes the following assumptions about human beings People can have complete information They can accurately recall any information any time they like People can manipulate all this information in a series of complex calculations to provide expected values People can rank the consequences in a consistent fashion for the purposes of identifying the preferred alternative.

BOUNDED RATIONALITY MODEL (BRM) Herbert Simon

As the name implies this model, does not assume individual rationality in the decision making process. It assumes that people while they may seek the best solutions usually settle for much less because the decisions they confront typically demand greater information processing capabilities than they possess They seek a kind of bounded (or limited) rationality in decisions

The concept of bounded rationality attempt to describe decision process in terms of three mechanisms: Sequential attention to alternative solutions: Instead of identifying all possible solutions and selecting the best, the various alternatives are identified and evaluated one at a time. Use of heuristics: Decision makers use heuristics to reduce large problems to manageable proportions so that decisions can be made rapidly. They look for obvious solutions or previous solutions that worked in similar situations. (A heuristic is a rule which guides the search for alternatives into areas that have a high probability for yielding satisfactory solutions). Satisfying : Whereas the econological model focuses on the decision maker as an optimizer, this model sees him or her as a satisficer.

An alternative is optimal if: There exists a set of criteria that permits an alternative to be compared; and The alternative in question is preferred, by these criteria, to all other alternatives.

An alternative is satisfactory if : There exists a set of criteria that describes minimally satisfactory alternatives; and The alternative in question meets or exceeds all these criteria

Steps in BRM
1. 2. Set the goal to be pursued or define the problem Establish an appropriate level of aspiration or criterion level (that is, when do you know that a solution is sufficiently positive to be acceptable even if it is not perfect) Employ heuristics to narrow problem space to a single promising alternative If no feasible alternative is identified (a) lower the aspiration level, and (b) begin the search for a new alternative solution (repeat steps 2 and 3) After identifying a feasible alternative (a) evaluate it to determine its acceptability If the identified alternative is unacceptable, initiate search for a new alternative solutions (repeat steps 3-5) If the identified alternative is acceptable implement the solution. Following implementation, evaluate the case with which the goal was (or was not) attained and raise or lower the level of aspiration accordingly on future decisions of this type

3. 4. 5. 6. 7. 8.

In contrast to the perspective econological model, it is claimed that the bounded rationality model is descriptive; that is, it describes his decision makers actually arrive at the identification of solutions to organizational problems.

DEFINE PROBLEM

REDUCE ASPIRAION LEVEL NO

IDENTIFY THE PROBLEM

SET ASPIRATION LEVEL

IDENTIFY ALTERNATIVES

CHECK IF DECISION SATISFACTORY

SET CRITERION

YES

IMPLEMENT DECISION

THE BOUNDED RATIONALITY MODEL

IMPLICIT FAVORITE OR GAMES MAN MODEL - Soelberg

In this process, an implicit favorite is identified very early in the choice process during the generation of alternatives The search for additional choices is continued and quickly the best alternative candidate is selected, known as the confirmation candidate. Next, decision rules are generated to demonstrate unequivocally that the implicit favorite superior to the alternative confirmation candidate This is done through perceptual distortion of information about the two alternatives and through weighing systems designed to highlight the positive features of the implicit favorite. The decision rules are designed to contain only those one or two dimensions in which the implicit favorite can be shown to be superior to the confirmation candidate.

The following are the steps in the process of this model 1. Set goal 2. Identify implicit favorite 3. Compare and rank implicitly rejected alternatives 4. Identify confirmation candidate 5. Establish decision rule or criterion 6. If decision rule does not justify implicit favorite repeat steps 4 and 5 7. Otherwise announce decision; and 8. Act

Decision rule does not justify implicit favorite

Set goal

Identify implicit favorite

Compare and rank implicitly rejected alternatives

Identify confirmation candidate

Establish decision rule or criterion

ACT

Announce decision

Decision rule justify implicit favorite

THE IMPLICIT FAVORITE MODEL

Single-stage Decision making Problems

Decision-making in case of single stage decision problems calls for (i) Identification of the course of action available to the decision-maker in the face of various possible events, (ii) Developing a pay-off matrix, and (iii) choosing a particular course of action in accordance with some principle.

Example
A book store sells a particular book of tax laws for Rs. 100. it purchases the book for Rs. 80/copy. Since some of the tax laws change every year, hthe copies unsold at the end of a year become outdated and can be dispose of for Rs. 30 each. According to past experience, the annual demand for this book is between 18 and 23 copies. Assuming that the order for this book can be placed only once during the year, the problem before the store's manager is to decide how many copies of the book should be purchased for the next year.

Pay-table: It represents the matrix of the conditional values(profit, loss or cost) associated with all the possible combinations of acts and events How to construct pay-off table for the example?

Pay-off table
Events Ei E1:18 E2:19 E3:20 E4:21 E5:22 E6:23 Acts, Aj A1:18 A2:19 A3:20 A4:21 A5:22 A6:23

For the given problem, Let D denote demand in units for the book Q denote the quantity to be purchased(the course of action) P denote profit When D Q, P =100D -80Q But D=Q, P= 100Q-80Q, P=20Q When D<Q, P = 100D-80Q+30(Q-D), P=70D-50Q

Pay-off table
Events Ei E1:18 E2:19 E3:20 E4:21 E5:22 E6:23 Acts, Aj A1:18 A2:19 A3:20 A4:21 A5:22 A6:23 360 360 360 360 360 360 310 380 380 380 380 380 260 330 400 400 400 400 210 280 350 420 420 420 160 230 300 370 440 440 110 180 250 320 390 460

Regret table
Events Ei E1:18 E2:19 E3:20 E4:21 E5:22 E6:23 Acts, Aj A1:18 A2:19 A3:20 A4:21 A5:22 A6:23 0 20 40 60 80 100 50 0 20 40 60 80 100 50 0 20 40 60 150 100 50 0 20 40 200 150 100 50 0 20 250 200 150 100 50 0

Decision Rules
There are several rules or criteria on the basis of which decision may be taken once the pay-off table is set-up. The selection of an appropriate criteria depends on factors like the nature of decision situation, attitude of decisionmaker, and so on.

Decisions under uncertainty

The decision situations where there is no way in which the decision-maker can assess the probabilities of the various states of nature are called decisions under uncertainty. The several principles which may be employed in such condition are given below:
1. 2. 3. 4. 5. Laplace Principle Maximin or Minimax principle Maximax or Minimin principle Hurwicz principle Savage principle

Laplace principle
It based on philosophy that if we are uncertain about the various events then we may treat them as equally probable. Under this assumption, the expected(mean) value of pay-off for each strategy is determined and strategy with highest mean value is adopted. If pay-off are in terms of costs, we choose the strategy with the lowest average cost.

Maximin or Minimax principle

This principle is adopted by pessimistic decision-makers. Using this approach, the minimum pay-offs resulting from adoption of various strategies are considered and among these values the maximum one is selected If dealing with the costs, the maximum cost associated with each alternative is considered and the alternative which minimizes this maximum cost is chosen.

Maximax or Minimin principle

The maximax principle is optimists principle of choice. It suggests that for each strategy, the maximum profit should be considered and the with which the highest of these values is associated should be chosen. If dealing with costs, the minimum cost for each alternative is considered and then the alternative which minimises the minimum cost is selected.

Hurwicz principle
Decision makers view fall somewhere between extreme pessimism and extreme optimism. An index of optimism is defined on scale ranging from 0 to1 = 0, extreme pessimism. = 1, extreme optimism. Assuming that the decision-maker is able to reflect a degree of optimism by assigning a particular value of , we multiply the maximum profit for each strategy Aj by and the minimum profit for it by 1- . The sum of these products, called the Hurwicz Criterion, is obtained for each strategy and we select the alternative which maximizes this quantity.

 In the case of costs, the minimum of the costs for each course of action is multiplied by (the indicator of degree of optimism of the decision-maker), and the maximum of the costs for each alternative is multiplied by 1- . The sum of the product for each action strategy is obtained. The alternative for which the sum is the least is selected.

Savage principle
It is based on the concept of regret and calls for selecting the course of action that minimizes the maximum regret. It is alternatively known as the principle of minimax regret.

Decision under risk

The decision situations wherein the decision-maker chooses to consider several possible outcomes and the probabilities of their occurrences can be stated are called decisions under risk. There are two criteria under the conditions of risk: 1. Maximum Likelihood principle 2. Expectation principle

Maximum Likelihood principle

Under this principle, the decision-maker first considers the event that is most likely to occur. Then decides for the course of action which has the maximum conditional pay-off, corresponding to this event(when the payoff matrix is in the terms of costs, then theaction with the least conditional pay-off would be chosen).

Expectation principle
With the events probabilities assigned the expected pay-off for each strategy is calculated by multiplying the pay-off values with their respective probabilities and then adding up these products. The strategy with the highest expected pay-off represents the optimal choice. Pay-off matrix in terms of costs, optimal strategy is the corresponding to which the expected value is the least.

 Expected opportunity loss or expected regret Expected pay-off of perfect information(EPPI)

Suppose the bookstore observes from the past sales data that the proportion of times the number of copies sold is 18, 19, 20, 21,22,23 are respectively 0.05, 0.10, 0.30, 0.40, 0.10, 0.05. Find he solution based on two of the criterions under risk condition.

Expected Pay-offs
Events Ei E1:18 E2:19 E3:20 E4:21 E5:22 E6:23 Probability Pi 0.05 0.10 0.30 0.40 0.10 0.05 Acts, Aj A1:18 A2:19 A3:20 A4:21 A5:22 A6:23

Expected Pay-off

Expected regret
Events Ei E1:18 E2:19 E3:20 E4:21 E5:22 E6:23 Probability Pi 0.05 0.10 0.30 0.40 0.10 0.05 Expected Regret Acts, Aj A1:18 A2:19 A3:20 A4:21 A5:22 A6:23

Multi-stage Decision-making problems: Decision tree

In single stage problems the decision amker has to select the best course of action on the basis of whatever information is achievable at a point in time. Now the decision situation that involves multiple stages is considered. It is also called sequential decision problems, they are characterized by a sequence of decisions in which following each decision, a chance event occurs which in turn influences the next decision. To evaluate the decision proceeding in a backward manner by evaluating the best course of action at the later stages to decide the best action at the earlier stages. Generally Expectation principle is used.

An oil company has recently acquired rights in a certain area to conduct surveys and test drillings to lead to lifting oil if it is found in commercially exploitable quantities. The area is considered to have good potential for finding oil in commercial quantities. At the outset, the company has the choice to conduct further geological tests or to carry out a drilling programme immediately. On the known conditions, the company estimates that there is a70:30 chance of further tests showing success. whether the tests show the possibility of ultimate success or not or even if no tests are undertaken at all, the company could still pursue its drilling programme or alternatively consider selling rights to drill in the area. Theraafter, however, if it carries out the drilling programme, the likelihood of final success or failure is considered dependent on he foregoing stages. Thus: If successful tests have been carried out, the expectation of success in drilling is given as 80:20 If the tests indicate failure, then the expectation of success in drilling is given as 20:80 If no tests have been carried out at all, the expectation of success in drilling is given as 55:45

Costs and revenues have been estimated for all possible ouycomes and the net present value of each is as follows.
outcome Success With prior tests Without prior tests Net present value(Rs millions) 100 120

Failure Sale of exploitaton rights

With prior tests Without prior tests Prior test show success Prior test show failure Without prior tests

-50 -40 65 15 45

1. Draw the decision tree diagram to represent the above information. 2. Evaluate the tree in order to advise the management of the company on its best course of action