AP / ADMS 3300

DECISION ANALYSIS

1
Week 6
Chapter 7

Probability Basics

2
In Last lecture we covered
 Subjective Probability. What is it? Why do we need it?
 Assessing Subjective Probabilities
 Assessing Discrete Probabilities
 Direct Method
 Betting Strategies
 Reference Lotteries
 Assessing Continuous Probabilities
 Reference Lottery
 Fractile Method
 Using Continuous CDF􀁠s in Decision Trees
 Pitfalls: Heuristics and Biases
 Experts and Probability Assessment: Putting It All Together

3
 Overview of Chapter 7
In this lecture, we will review the basics of probability
theory. Since uncertainty is a typical aspect of problems,
rigorous and accurate problem solving requires using
probability theory (i.e., math and logic).
Specifically, we want you to:
Understand probability concepts
Use probability to model simple situations
Interpret probability statements
Manipulate and analyze models.

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 A Little Probability Theory
Probability theory uses math and logic to deal with
chance events, events that we are uncertain as to their
outcome.
Chance events have more than one possible outcome
and we use probability theory to rigorously deal with
the chances associated with the different outcomes.

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 A Little Probability Theory
 

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 A Little Probability Theory
3. Total Probability Must Equal 1
If we have a set of outcomes such that one (and only
one) of them has to occur, then the probability of the set
must sum to 100% and there is a 100% chance that one
(and only one) of the outcomes will occur.
Thus, the set of outcomes is called collectively
exhaustive and mutually exclusive.

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 Venn diagrams graphically represent probability.

Venn Diagrams
The entire Venn diagram is
the set of all possible
outcomes (A1, A2, and C),
and the entire area of the
diagram is 1 or 100%. There
is a 100% chance one the
outcomes in the diagram will
occur. The area of A1, e.g.,
is the probability of A1
occurring, say, 10%. That is,
just as A1 is 10% of the A1 and A2 do not overlap since they are mutually
diagram’s area, so it has a exclusive. They cannot both happen. Thus, their
10% chance of happening. probabilities are additive, just as A1, A2 and C
must add up to 100%.
© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas
4. Conditional Probability
 The probability of A happening when B has also
occurred
 Stated as “the probability of A given B”

 “The probability of A given B is the joint probability of

A and B divided by the probability of B.”
P(A|B) P(B|A) Are they same???

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas
Conditional Probability
as a Venn Diagram—the
probability of a certain
stock price going up given
that the Dow Jones went
up (the diagonally shaded
area)

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas
5. Independence
The probability of outcome A occurring stays the same
no matter which outcome of B has occurred.

where

Note that independence is a special instance of

conditional probability.
© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 Some Additional Probability Rules
Symmetry in independence: independence in one
direction implies independence in the other
direction
If P(Ai Bj) = P(Ai), then P(Bj Ai) = P(Bj)
This is also a special case of conditional probability.
Independent chance events are not the same as
mutually exclusive outcomes.
Two chance events being probabilistically dependent
does not imply a causal relationship.

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas
Conditional Independence: If A and B are
conditionally independent given C, then learning the
outcome of B adds no new information regarding A if
the outcome of C already is known.
For example, drownings are correlated with ice cream
consumption. It is unlikely that these two are causally
related. The explanation lies in a common cause; both
tend to happen during summer. Therefore, drownings
and ice cream consumption can be said to be
conditionally independent given the season.

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas

In these influence diagrams, A and B are conditionally

independent given C. The conditioning event can be either (a) a
chance event or (b) a decision.
© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability
6. Complements
Formulas
One event is said to be the complement of another if the
two together are the case of all that is.
 “Every object in the universe is either a butterfly (B) or not a
butterfly (B). Thus, the probability of not being a butterfly
(p=0.9999999) is the complement of the probability of being a
butterfly (p=0.0000001).”

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas
7. Total Probability of an Event
A convenient way to calculate the probability of A: P(A)

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas
Total Probability of Outcome A

The probability
of outcome A is
made up of the
probability of
outcome “A and
B” and the
probability of
outcome “A and
B.”

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
 More Probability Formulas
8. Bayes’ Theorem
Lets you simultaneously relate P(A|B), the chance that
an event A happened given B, and P(B|A), the chance B
happened given that event A occurred
 Via the symmetry principle of conditional probability
Lets you factor in false positives (concluding things don’t
exist when in fact they do) and false negatives
(concluding things do exist when they don’t)
 Type I error—incorrectly rejecting a true null hypothesis
 Type II error—incorrectly not rejecting a false null
hypothesis 

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
False Positive/Negative
Test +ve
Correct

Laboratory
You know this
person has COVID Test -ve False Negative
Error

Test +ve False Positive

Error
Laboratory
You know this
person has NO Test -ve
COVID Correct

19
 More Probability Formulas
Deriving Bayes’ theorem

Starting with the

symmetry formula
Rearranging it
algebraically
And replacing P(A) with the formula for total
probability

© 2014 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part, except for use as permitted in a license distributed with a certain product or service or otherwise on a password-protected website for classroom use.
Bayesian Statistics

21
Bayes’ Theorem

22
Bayes’ Theorem

23
Drug Testing

24
Drug Testing

25
Drug Testing
26
Drug Testing

27
Drug Testing

28
Drug Testing
0.05 x 0.93
0.93 0.0465

0.05
0.05 x 0.07
0.07 0.0035

0.95 x 0.03
0.03 0.0285

0.95

0.95 x 97
0.97 0.9215

29
Drug Testing

30
 Drug Testing
0.05 x 0.93
0.93 0.0465

0.05
0.05 x 0.07
0.07 0.0035

0.95 x 0.03
0.03 0.0285

0.95

0.95 x 97

P(T+) = 0.0465 + 0.0285 = 0.0750 0.97 0.9215

31
 Drug Testing
0.05 x 0.93
0.93 0.0465

0.05
0.05 x 0.07
0.07 0.0035

0.95 x 0.03
0.03 0.0285

0.95

0.95 x 97

P(T-) = 0.0035 + 0.9215 = 0.9250 0.97 0.9215

32
Drug Testing
P(T+|D) P(D|T+)

P(T-|D) P(D|T-)
P (T  | D ) 
P(T+|F) P(F|T+)

P(T-|F) P(F|T-)

P (T  and D )
P( D | T  ) 
P (T  )

33
 Drug Testing
0.05 x 0.93
P (T  and D ) 0.93 0.0465
P( D | T  ) 
P(T  )

0.05
0.05 x 0.07
0.07 0.0035

0.95 x 0.03
0.03 0.0285

0.95
0.0465
P( D | T  )   0.62 0.95 x 97
0.075
P(T+) = 0.0465 + 0.0285 = 0.0750 0.97 0.9215

34
Drug Testing

35
Drug Testing

36
Week 6
Chapter 12

Value of Information
(Part-I)
37
Introduction -Value of Information

38
Introduction

39
Introduction

40
Value of Information

41
Probability and Perfect
Information

42
Probability and Perfect
Information

43
Probability and Perfect
Information

44
Probability and Perfect
Information

45
Probability and Perfect Information

46
Stock Market Example:

47
Stock Market Example:

48
Stock Market Example:

49
Stock Market Example:

50
Stock Market Example:

51
Stock Market Example:
The above tree can be re-drawn as follows.

52
EVPI is expected value of perfect information is the maximum
amount of money you would be willing to pay for the services of
clairvoyant expert. If he charges more than $420 you would not
consult the expert.
53
Chapter 12
to be Continued …..

54
Practice Questions
12.4
12.5
12.6
12.7 (a, b and c only)

55