Scribd
Upload
54 views

Decision Analysis (DA)

This document discusses decision analysis and its importance in project management. It defines decision analysis as a systematic process for transforming opaque decisions into transparent ones. Decision analysis is important because it provides structure to decision-making and helps overcome biases. It then outlines the 10-step decision analysis process and describes the two main models used: decision trees and Monte Carlo simulation. Decision trees graphically represent decisions and uncertainties, while Monte Carlo simulation uses random values to model risk and uncertainty.

Uploaded by

K. Lee B.
Copyright
© Public Domain
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
54 views

Decision Analysis (DA)

This document discusses decision analysis and its importance in project management. It defines decision analysis as a systematic process for transforming opaque decisions into transparent ones. Decision analysis is important because it provides structure to decision-making and helps overcome biases. It then outlines the 10-step decision analysis process and describes the two main models used: decision trees and Monte Carlo simulation. Decision trees graphically represent decisions and uncertainties, while Monte Carlo simulation uses random values to model risk and uncertainty.

Uploaded by

K. Lee B.
Copyright
© Public Domain
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 18

D ecision A n alysis (D A )

Decision Making Under Uncertainty

Presented by1 Kirt Lee


D ecision A n alysis (D A ) or
R isk A n alysis (R A )
What is Decision Analysis? Why is it
important?
What is its importance in Project
Management?
Discuss the different methods used in
Decisions Analysis.

2
W h at is D ecision A n alysis

Decision Analysis as defined by (Howard,


1988), can be seen as a systematic
procedure for transforming opaque
decision problems into transparent
decisions problems by a sequence of
transparent steps.
Definition of Decision: A conclusion or resolution reached after consideration.
3
W h y is D ecision A n alysis
Im p ortan t?

Adds structure to the decision process


Structured thinking can help overcome biases
Formal structure permits decision traceability
Permits others to understand decision
Allows decision process improvement

Provides a better outcome than a random


choice
We cant control outcomes; but we can
influence the probability of certain outcomes
4
In R elation to P roject
M an ag em en t?
Is there anything more important to the success of a project
than making a good decisions? Good decisions make or break
a project.

This management skill is certainly near the top of the list, yet
so few Project Managers have had formal training in decision
making.

Decision analysis is a discipline that helps us choose wisely


under conditions of uncertainty.

Project management and, especially, project risk


management are receiving great attention these days.
5
D ecision A n alysis P rocess
Decision analysis is a process for solving problems. While most
decisions are unique, the general process can be the same.

Decision analysis provides a step-by-step procedure that has proved


practical in tackling even the most complex problems in an efficient and
orderly way.
6
10-S tep D ecision A n alysis P rocess

1. Proactively Identify Decision Opportunities


2. Define the Problem
3. Identify Alternatives
4. Develop the Decision Model
5. Quantify Judgments about Uncertainty

6. Develop the Valuation Model


7. Calculate Expected Value for Each Alternative
8. Rethink the Problem
N.B.: This process could also be iterative (i.e. a
9. Implement the Best Alternative
cycle).
10.Post-Analyze the Decision 7
M ain M od els u sed in D ecision A n alysis

Therere a wide variety of methods used in


Decision Analysis, however, the two main methods
used are:

1. Decision Trees
2. Monte Carlo Simulation

8
D ecision Trees
A decision tree is a graphical representation of expected value
calculations. The tree consists of decision, chances, and terminal
nodes, connected by branches.

Squares () represents decisions and are called decision nodes (these


are variables/actions that can be controlled by the decision maker).

Circles () represent Chance/Event nodes (these cant be controlled by


the decision maker).

Each possible choice is represented as a line ( ) called a Branch that


emanates from the decision node.

Terminal/End Nodes are un-connected branches, these endpoints9 are


10
D ecision Trees (con t.)
Decision Trees represent a systematic way of
organizing and representing the various
decisions and uncertainties that a decision-
maker faces.

Conceptually, any decision, no matter how


complex, can be analyzed with a decision tree
analysis.
11
M on te C arlo
S im u lation
Monte Carlo simulation is a computerized mathematical
technique that allows people to account for risk in quantitative
analysis and decision making.

The technique is used by professionals in varying fields, such


as, finance, project management, energy, manufacturing,
engineering, R & D, insurance, oil & gas, transportation, and
the environment.

The technique was first used by scientists working on the


atom bomb (code named the Manhattan Project); it was
named after Monte Carlo, the resort town in Monaco notorious
12
H ow d oes M on te C arlo S im u lation
W ork?
In a Monte Carlo simulation, a random value is selected for each of
the tasks, based on the range of estimates. The model is
calculated based on this random value. The result of the model is
recorded, and the process is repeated.

A typical Monte Carlo simulation calculates the model hundreds or


thousands of times, each time using different randomly-selected
values.

When the simulation is complete, we have a large number of


results from the model, each based on random input values.
These results are used to describe the likelihood, or probability, of
13
Th e B ell C u rve

x-axis is range (possible values) and y-axis is


probability 14
W h y u se M on te C arlo
S im u lation ?
Monte Carlo Simulation is used to understand and
control complex stochastic systems.

For instance a decision tree with hundreds/thousands


of terminal nodes, this would be to cumbersome and
impractical to calculate, thus, Monte Carlo
Simulation is option of said scenario.

Definition of Stochastic: Involving chance or


probability 15
S im p le exam p le of M on te C arlo
S im u lation

Question:
In a room of 30 people, what is the probability that 2
people share the same birthday?

Answer:
The overall probability no shared birthdays is equal to
.294. hence, there is 71% chance that at 2 people (in
a room of 30) share the same birthday. 16
C om p arison of B oth M od els (Trees & M on te
C arlo)
Method Strengths Weaknesses
Decision Tree Analysis Graphical layout of expected Must convert continuous into
value calculation. discrete distributions
Evaluating alternatives with Requires decision policy
sequential decisions (e.g., value function
values of information)
Must limit number of decision
alternatives and chance
event outcomes
Monte Carlo Simulation Can accommodate Time versus accuracy
complexity easily, such as, tradeoff; solution can be
dynamic behavior under computationally time-
contingencies consuming
Very generally applicable Solution is approximate and
changes with random
number seeds
17
Poor precision with low-
R eferen ces

18

You might also like