Uncertainty and Decision Making

Content for Today

 Risk and uncertainty

 Decision tree – expected value

 Multi-Criteria Decision Making (MCDM) methods

– one example - Analytic Hierarchy Process
(AHP)

 Conclusions
 Uncertainty in Decision Making

• In decision theory lack of knowledge is divided

into two categories

– Risk and
• In decision-making under risk, it is known what the possible
outcomes are and what there probabilities of occurrences are

– Uncertainty
• In decision-making under uncertainty, probabilities are either
not known at all or are only known with insufficient precision
 Risk
• In non-technical contexts, ‘risk’ refers to situation in which it is
possible, but not certain, that some undesirable event will occur

• In technical uses, ‘risks’ refers to something quantifiable

• In risk analysis, ‘risk’ often denotes a numerical representation of

severity that is obtained by multiplying the probability of an
unwanted event with a measure of its value

• In decision theory, ‘decision under risk’ means decision with known

probabilities
 Project Life Cycle Processes in AEC
Industry

Client
Brief/requirements

Design

Installation/
Construction/
Commission
Operation &
Maintenance

Disposal/
Reuse/or
Recycle
 Decision from uncertainty

• It is the characteristic of many decisions in

management that they have to be made
before all the relevant facts are known

• In other words decision making under

conditions of uncertainty

• That is there is a chance factor that the issue

may or may not arise – or simply put the
probability or the real likelihood of its
occurrence
 Outcome or pay-off
• When a situation arises in which a decision has to be made and a
particular outcome may result, it is usual to give a particular value to
that outcome

• This is sometimes also referred to as pay-off

• For example, if a contractor was successful in obtaining a contract

at a tender price of £100k and incurred a cost of £90k in the
execution of that contract, the pay-off from that contract will give him
a gross profit of £10k.

• If however, he was able to complete the work at £85k, his net profit
will be £15k

• However if he did the contract for 95k, his profit will be £5k.
 Expected value
• Expected value is a concept that gives a measure
of the expectation of pay-off (i.e. Outcome) that
will arise from a particular situation

• This is obtained by multiplying the pay-off of each

possible outcome by the probability that, that
outcome will arise, and then summing up all the
products

• Assigning probabilities to the three different costs

of the simple example given before, will produce
expected outcomes as shown overleaf.
 Expected value

Tender Sum Contractor Profit Probability of Outcome

Expected cost (T-C) the cost (T-C) x p
T C £ arising
£ £ p
100,000 85,000 15,000 0.1 1500
100,000 90,000 10,000 0.6 6000
100,000 95,000 5,000 0.3 1500
Expected 9000
value
 Other examples of decision under
uncertainty

• Design of water tower

• Competitive tendering for a project
• Taking out insurance for job
• Temporary works – coffer dam
 Choosing Between Options by
Projecting Likely Outcomes
• Help you to choose between several courses of action

• Effective structure within which you can lay out options

and investigate the possible outcomes of choosing those
options

• Help you to form a balanced picture of the risks and

rewards associated with each possible course of action
 Decision Tree

Decision point

1
A

Chance event
 Constructing a Decision Tree

• Start a Decision Tree with a decision that you need to make

• Draw a small square to represent this
• From this box draw out lines towards the right for each possible
solution, and write that solution along the line
• At the end of each line, consider the results
– If the result of taking that decision is uncertain, draw a small circle
– If the result is another decision that you need to make, draw another
square
• Squares represent decisions, and circles represent uncertain
outcomes
• Write the decision or factor above the square or circle. If you have
completed the solution at the end of the line, just leave it blank
 Decision Tree

B
 Conti…
• Starting from the new decision squares on your diagram,
draw out lines representing the options that you could
select

• From the circles draw lines representing possible

outcomes. Again make a brief note on the line saying
what it means

• Keep on doing this until you have drawn out as many of

the possible outcomes and decisions as you can see
leading on from the original decisions
 Conti…
• Once you have done this, review your tree diagram

• Challenge each square and circle to see if there are any

solutions or outcomes you have not considered
– If there are any, draw them in
– If necessary, redraft your tree if parts of it are too congested or
untidy

• You should now have a good understanding of the range

of possible outcomes of your decisions
 Evaluating the Decision Tree

• Determine which option has the greatest worth…

– Start by assigning a cash value or score to each possible
outcome - how much you think it would be worth to you if that
outcome came about

• Next look at each circle (i.e. representing an uncertainty

point) and estimate the probability of each outcome
– If you use percentages, the total must come to 100% at each
circle
– If you use fractions, these must add up to 1
– If you have data on past events you may be able to make
rigorous estimates of the probabilities
– Otherwise write down your best guess
 Calculating Tree Values

• Once you have worked out the value of the outcomes, and have
assessed the probability of the outcomes of uncertainty, it is time to
start calculating the values that will help you make your decision

• Start on the right hand side of the decision tree, and work back
towards the left

• As you complete a set of calculations on a node (decision square or

uncertainty circle), all you need to do is to record the result

• You can ignore all the calculations that lead to that result from then
on - if you are sure or definite that no mistakes have been made
Calculating the Value of Uncertain
Outcome Nodes

• Where you are calculating the value of uncertain

outcomes (circles on the diagram), do this by multiplying
the value of the outcomes by their probability

• The total for that node of the tree is the total of these
values
0.4 (probability good outcome) x £500,000 (value) = £200,000

0.4 (probability moderate outcome) x £25,000 (value) = £10,000

0.2 (probability poor outcome) x £1,000 (value) = £200

+ £210,200
 Calculating the Value of Decision
Nodes
• When you are evaluating a decision node, write down the cost of
each option along each decision line
• Then subtract the cost from the outcome value that you have
already calculated
• This will give you a value that represents the benefit of that decision
• Note that amounts already spent do not count for this analysis -
these are 'sunk costs' and (despite emotional counter-arguments)
should not be factored into the decision
• When you have calculated these decision benefits, choose the
option that has the largest benefit, and take that as the decision
made
• This is the value of that decision node
In this example, the benefit
we previously calculated for
'new product, thorough
development' was £210,000.
We estimate the future cost
of this approach as £75,000.
This gives a net benefit of
£135,000.

The net benefit of 'new

product, rapid development'
was £15,700. On this branch
we therefore choose the
most valuable option, 'new
product, thorough
development', and allocate
this value to the decision
node.
 Result
• By applying this technique we can see that the
best option is to improve our new product
• It is worth much more if we take our time and get
the product right, than to rush the product to
market
• It is better just to improve our existing products
than to rush a new product, even though it costs
less
• Overall it is best to come up with the new
product with thorough development
 Key Points
• Decision trees provide an effective method of decision-
making because they…
– clearly lay out the problem so that all options can be challenged
– allow us to analyse fully the possible consequences of a decision
– provide a framework to quantify the values of outcomes and the
probabilities of achieving them
– help us to make the best decisions on the basis of existing
information and best guesses
• As with all decision-making methods, decision tree
analysis should be used in conjunction with common
sense - decision trees are just one important part of your
decision-making tool kit
 Supplier selection using unweighted
attributes (Attribute Analysis)
Attributes A B C D E
Knowledge and experience 6 7 7 9 8

Reputation 6 6 7 9 10

Prone to strikes/bankruptcy 4 6 9 9 9

Significance of their support 4 8 7 9 9

Design appreciation & conformance 7 7 8 8 9

QA system 5 6 8 9 9

Defects and warranty claims to date 7 6 8 9 10

Reliability of delivery times 6 6 6 9 10

Cost control 7 6 7 6 6

Service control 8 7 8 8 10

Total 60 65 75 85 90
Multi-Criteria Decision Making
Methods (MCDM)

•AHP - Analytical Hierarchy Process

•ANP – Analytic Network Process

•The Bayesian View of decision making

The Analytic Hierarchy Process
(AHP)
• Developed by Saaty in the 1970s
• General theory of measurement that derived ratio
scales from pair wise comparison
• These comparison are provided in multilevel
hierarchy structures
• The comparison can either be based upon actual
measurement or a fundamental scale of relative
strengths of preferences
The Analytic Hierarchy Process
(AHP)
•The fundamental scale range from 1 (equal
importance) to 9 (extremely more important)
•The scale also uses reciprocal (e.g. 1/9) to
represent where dominance is in reverse.
•A fairly basic decision problem would involve a
three level hierarchy of Goals, Criteria, and
Alternatives
•The comparison can either be based upon actual
measurement or a fundamental scale of relative
strengths of preferences
Fundamental Assumptions of AHP

•Elements with the same level of decision hierarchy,

cannot impact upon each other, and thus are
independent of each other.

•For example, the relationship between social risk

and political risk cannot be modelled by the AHP
 Example

Choice between Project A and Project B

 Example – Choice between Two
Projects
GOAL
Selection of Best Project

CRITERIA
Social Political Technological Environmental
Financing

Project A Project B
ALTERNATIVE
 Pairwise Comparison Matrix for
Level 1 – Criteria wrt Goal
Finance Social Political Technological Environmental Priority vector

Finance 1 5 3 7 6 0.502

Social 1/5 1 1/3 5 3 0.140

Political 1/3 3 1 6 3 0.243

Technological 1/7 1/5 1/6 1 1/3 0.039

Environmental 1/6 1/3 1/3 3 1 0.076

Level 2 Comparison wrt criteria

Preference of project Project A

B over project A
Finance 6 0.39

Social 7

Political 1/8 Project B

Technological 1 0.61

Environmental 1/5
Bayes’ Formula or Bayes’ Theorem
– Probability as Belief

• Bayes proved a theorem about conditional

probability. It states that, given fairly broad
conditions

p(AB) = p(A\B)p(B) = p(B\A)p(A)

Whence p(A\B) = p(B\A)p(A) / p(B)

Here, p(AB) means the probability of both A & B, and p(A\B) means the
probability of A given B
 Bayes’ Formula or Bayes’
Theorem – Updating

• A central pillar of Bayesianism is the

interpretation of Bayes’ Formula, which
states that

p (H\D) α p (D\H) p (H)

Where H is a proposition called the hypothesis, and D is the data. On the

right hand side, the term p (H) is called the PRIOR: ones prior belief in
the possible truth of the hypothesis (before looking at the data)
Bayes’ Formula or Bayes’ Theorem
– Updating

• Essentially, one has some beliefs, some

new information arrives, and one takes
cognisance of this and updates one beliefs
accordingly.

p (H\D) α p (D\H) p (H)

 Key Points
• Bayes belief approach helps in the
development of the knowledge that is
required in making pair wise comparison

• Multi-Criteria Decision making involves

the selection of the best actions from a set
of alternatives, each of which is evaluated
against multiple, and often conflicting
criteria.
 Reading matter

• Thomas L. Saaty. How to make a decision: The Analytic Hierarchy

Process, International Journal of Project Management 18 (2000) pp.
173 – 177.

• W Watthayu and Y Peng (2004). A Bayesian Network Based

Framework for Multi-Criteria Decision Making, MCDM 2004,
Whistler, B. B. Canada, August 6 -11, 2004.

• Webb A (2005) Project Manager’s Guide to Handling Risk