Professional Documents
Culture Documents
Chapter 6: Decision Theory: Decision Theory Problems Are Categorized by The Following
Chapter 6: Decision Theory: Decision Theory Problems Are Categorized by The Following
Chapter 6: Decision Theory: Decision Theory Problems Are Categorized by The Following
Romero
BSA2205 – BSMA1E
Activity 6
Decision theory is a decision-making principle. In the mid-twentieth century, numerous academic fields
collaborated to produce contemporary decision theory. Researchers that identify as economists,
statisticians, psychologists, political and social scientists, or philosophers are usually drawn to decision
theory. Decision theory provides a systematic framework for making rational decisions in the face of
uncertainty. Decision theory provides conceptually simple processes for choosing given a collection of
options, a set of consequences, and a correspondence between those sets. The utility function of payoffs is
used in decision theory to draw its origins from economics. It suggests that decisions be made by
calculating utility and probability, as well as the ranges of possibilities, and it also sets out techniques for
making excellent decisions.
Decision theory is a collection of concepts, principles, tools, and strategies that assist choice makers in
coping with complex decision issues that are uncertain. Decision theory, in particular, is concerned with
methods for choosing the best course of action when a number of choices are accessible and their effects
cannot be predicted with certainty.
David Lewis (1974) states that "Decision theory (at least if we omit the frills) is not an esoteric science,
however unfamiliar it may seem to an outsider. Rather, it is a systematic exposition of the consequences
of a certain well-chosen platitudes about belief, desire, preference, and choice. It is the very core of our
common-sense theory of persons, dissected out and elegantly systematized.”
Decision theory is described in theoretical literature as a broad approach to decision making. It helps the
decision maker to assess a collection of complex situations with various alternatives and many distinct
possible outcomes, and to select a plan of action that is compatible with the decision maker's basic
economic and psychological desires.
1. A decision criterion
2. A list of alternatives
3. A list of possible future events (states of nature)
4. Payoffs associated with each combination of alternatives and events
5. The degree of certainty of possible future events
There are two categories of decision theories, including normative or prescriptive decision theories, for
identifying the best decision, provided that an ideal decision maker is fully informed, capable of
calculating with perfect precision, and completely rational. The practical application of this prescriptive
approach is known as decision analysis, and it aims to find tools, methods, and software that help people
make better decisions. The most systematic and comprehensive software tools developed in this way are
called decision support systems.
In contrast, positive or descriptive choice theory gives an explanation for determined behaviors below the
idea that the decision-making agents are behaving below a few constant rules. These rules may, for
instance, have a technical framework or an axiomatic framework, integration the Von Neumann-
Morgenstern axioms with behavioral desecrations of the predicted utility hypothesis, or they'll explicitly
supply a useful shape for time-inconsistent utility functions.
Decision Making faces 3 particular conditions they are; (1) uncertainty, (2) certainty, and (3) risk. These
conditions determine the probability of an error in decision making.
A decision-maker is in a condition of certainty when he or she knows with reasonable certainty what the
alternatives are, what circumstances are connected with each alternative, and what the consequence of
each alternative will be. Under certain conditions, accurate, quantifiable, and credible information on
which to make choices is accessible.
The cause-and-effect connections are well understood, and the future is highly foreseeable under certain
conditions. Such circumstances arise when normal and repetitive decisions about the day-to-day
operations of the firm are made.
Example:
What will you choose to build if the demand will be low, moderate, and high?
If the demand will be low, just choose the small facility with a payoff of $10 million.
If the demand is moderate, choose to build a medium facility with a payoff of $12 million.
If the demand is high, just build large facility with a $16 million.
The majority of significant decisions made in today's complex world are made in the state of uncertainty.
When the future environment is uncertain and everything is in motion, conditions of uncertainty exist.
The decision-maker is unaware of all possible alternatives, the risks connected with each, and the
outcomes or probability of each alternative.
The management lacks thorough knowledge on the alternatives, and whatever information that is
provided may not be totally accurate. Managers must establish some assumptions about the circumstance
in order to create an acceptable framework for decision-making in the face of such uncertainty. They must
rely on their own judgment and expertise to make decisions.
Maximin: Choose the alternative with the best of the worst possible payoff.
Laplace: Choose the alternative with the best average period of any of the alternatives.
Minimax Regret: Choose the alternative that has the least of worst regrets.
Example 1:
Hence, since $10 million is the best we choose to build a small facility.
Example 2:
The best overall payoff is the $16 million on the third row. Hence, the maximax criterion leads to building
a large facility.
Example 3:
Example 4:
The best of these worst regrets would be chosen using a minimax regret. The lowest regret is 4, which is
for medium facility. Hence,
DECISION MAKING UNDER RISK
Risk develops when a management lacks perfect information or when there is an information imbalance.
In a risky situation, the decision maker has incomplete information about possible alternatives but has a
good idea of the probability of outcomes for each.
Managers must determine the probability associated with each alternative based on the available
information and his experience while making risky decisions.
Decisions made under the condition that the probability of occurrence for each state of nature can be
estimated.
Determine the expected payoff of each alternative, and choose the alternative that has the best expected
payoff. This approach is most appropriate when the decision maker is neither risk averse nor risk seeking.
Example:
Using the EMV criterion, identify the best alternative for these probabilities:
low = .30; moderate = .50; high = .20
Hence, choose the medium facility because it has the highest expected value.
DECISION TREES
Decision trees are great tools for guiding you in deciding between multiple alternatives.
They give a highly effective structure for laying out alternatives and investigating the potential outcomes
of those options. They also assist you in developing a balanced picture of the risks and rewards connected
with each possible course of action.
You create a Decision Tree with a decision that has to be made. Draw a small square to the left of a large
sheet of paper to symbolize this.
Draw lines to the right from this box for each possible solution, then write that solution along the line.
Keep the lines as widely apart as possible to allow you to extend your thoughts.
Once you've evaluated the worth of the outcomes and assessed the probability of the outcomes of
uncertainty, it's time to begin calculating the values that will help you in making your decision.
Begin on the right side of the decision tree and work your way back to the left. All you have to do after
you finish a set of computations on a node (decision square or uncertainty circle) is record the result.
From then on, you may disregard all of the computations that resulted in that outcome.
When calculating the value of uncertain outcomes (circles on the figure), multiply the value by the
probability of the outcomes. The sum of these values is the total for that node of the tree.
In the example in figure 2, the value for "new product, thorough development" is:
0.4 (probability good outcome) x $1,000,000 (value) =
$400,000
TOTAL $420,400
When evaluating a decision node, keep track of the costs of each alternative along each decision line.
Then deduct the cost from the previously calculated outcome value. This will provide you with a
monetary value that indicates the advantage of that option.
It is important to note that sums already spent do not count for this analysis — they are "sunk costs" and
should not be included (despite emotional counter-arguments).
When you've computed the decision benefits, select the one with the largest benefit and make it your
decision. This is the decision node's value.
The net benefit of "new product, rapid development" was $31,400. On this branch, we, therefore, choose
the most valuable option, "new product, thorough development", and allocate this value to the decision
node.
Result
Using this method, we can see that developing a new product is the best option. It is far more valuable to
us to take our time and get the product perfect than to rush it to market. Even if it costs us less, it is
preferable to improve our present products than to launch a new product.
They provide for the visual representation of sequential decisions, i.e. they illustrate a series of
chronological decisions. Decision trees are universal; they improve the accuracy of the structure of the
decision process and promote communication among decision problem solvers. The decision tree forces
the decision maker to consider all of the consequences of his decisions. The use of computers in the
construction and analysis of decision trees allows for quick experimentation with decision trees and the
evaluation of the impact of changes in the tree's input parameters on the selection of the optimal policy.
The major outcome of a decision tree analysis is to select the best option in the initial stage of the decision
process. Following this step, certain changes in choice situations may occur, additional information may
be received, and it is typically necessary to realize the decision tree and select a new best strategy. This
procedure is required before proceeding to another stage.
The expected value of perfect information is the amount a healthcare decision maker is ready to pay to
have perfect information about all aspects that affect which treatment option is selected as a result of a
cost-effectiveness analysis. This is the monetary worth of eliminating all uncertainty from such an
analysis. EVPI is computed as the difference in the monetary value of health gain associated with a
decision between therapy alternatives when the decision is made using currently available information
(i.e. uncertainty in the factors of interest) and when the decision is made using perfect information (no
uncertainty in all factors). The expected value of perfect information is the amount a healthcare decision
maker is ready to pay to have perfect information about all aspects that affect which treatment option is
selected as a result of a cost-effectiveness analysis. This is the monetary worth of eliminating all
uncertainty from such an analysis. EVPI is computed as the difference in the monetary value of health
gain associated with a decision between therapy alternatives when the decision is made using currently
available information (i.e. uncertainty in the factors of interest) and when the decision is made using
perfect information (no uncertainty in all factors).
Or
SENSITIVITY ANALYSIS
Sensitivity Analysis is a financial modeling method that analyzes how multiple values of a set of
independent variables influence a certain dependent variable under specified conditions. Sensitivity
analysis is utilized in a variety of areas, from biology and geography to economics and engineering.
It is particularly valuable in the study and analysis of a "Black Box Process," in which the output is an
opaque function of multiple inputs. An opaque function or process is one that cannot be studied or
analyzed for any reason. Climate models, for example, are often quite complex in geography. As a result,
the precise connection between the inputs and outputs is unknown.
Example:
John is in charge of sales for HOLIDAY CO, a business that sells Christmas decorations at a shopping
mall. John knows that the holiday season is approaching and that the mall will be crowded. He wants to
find out whether an increase in customer traffic at the mall will raise the total sales revenue of HOLIDAY
CO and, if so, then by how much.
The average price of a packet of Christmas decorations is $20. During the previous year’s holiday season,
HOLIDAY CO sold 500 packs of Christmas decorations, resulting in total sales of $10,000.
After carrying out a Financial Sensitivity Analysis, John determines that a 10% increase in customer
traffic at the mall results in a 7% increase in the number of sales.
Using this information, John can predict how much money company XYZ will generate if customer
traffic increases by 20%, 40%, or 100%. Based on John’s Financial Sensitivity Analysis, such increases in
traffic will result in an increase in revenue of 14%, 28%, and 70%, respectively.
REFERENCES:
Decision-Making Under Certainty, Risk And Uncertainty. (2016, June 18). Essays, Research Papers and
Articles on Business Management. https://www.businessmanagementideas.com/decision-
making/decision-making-under-certainty-risk-and-uncertainty/3371.
Decision Theory, Decision Theory Lecture Notes, Decision Theory Definition. (n.d.). Decision Theory,
Decision Theory Lecture Notes, Decision Theory Definition.
https://www.civilserviceindia.com/subject/Management/notes/decision-theory.html.
Decision Tree Analysis: Choosing By Projecting "Expected Outcomes". (n.d.). Decision Tree Analysis -
Decision Skills from MindTools.com. https://www.mindtools.com/dectree.html.
Overview Of Sensitivity Analysis - What Is Sensitivity Analysis. (2020, April 8). Corporate Finance
Institute. https://corporatefinanceinstitute.com/resources/knowledge/modeling/what-is-sensitivity-
analysis/.
https://wiki.analytica.com/index.php?title=Expected_value_of_information_--_EVI,_EVPI,_and_ESVI