Subjective Probability

1
Chapter 8

• Subjective Probability

2
Chapter 8, Subjective Probability

• Learning Objectives
• Uncertainty and public policy
• Subjective probability-assessment technique
• Heuristics and Biases
• Experts and Probability Assessment

3
Chapter 8,Subjective Probability

• Subjective assessments of uncertainty are an
  important element of decision analysis.
• In modern decision analysis subjective judgments
  of uncertainty can be made in terms of
  probability.
• Need to develop a approach to measure the
  uncertainty that we feel

4
Uncertainty and Public Policy

• Fruit Frost, Farmers occasionally must decide
  whether to protect a crop from potentially
  damaging frost.
• Decision must be made in terms of probability
• Earthquake Prediction, Geologists are beginning
  to develop ways to assess the probability of
  major earthquakes.

5
Uncertainty and Public Policy

• Environment Impact Statements
• Require assessments of the risks assessments of
  the risks associated with proposed projects.
• Projects involving pesticides and herbicides, the
  chances of cancer and other health risks are
  assessed.

6
Uncertainty and Public Policy

• Public Policy and Scientific Research
• Scientists learn of the possible presence of
  conditions that may require action by the
  government.
• Medical Diagnosis
• Many physicians in hospital intensive-care units
  (ICUs) have access to a complex computer system
  known as APACHE III.

7
Uncertainty and Public Policy

• APACHE III (Acute Physiology, Age, and Chronic
  Health Evaluation).
• APACHE III evaluates the patients risk as a
  probability of dying either in the ICU or later
  in the hospital.

8
Assessing Discrete Probabilities

• There are three basic methods for assessing
  discrete probabilities
• The first is to have decision maker assess the
  probability directly
• What is your belief regarding the probability
  that event such and such will occur?

9
Assessing Discrete Probabilities

• The second method is to ask about the bets that
  the decision maker would be willing to place
• The third approach adopts a thought-experiment
  strategy
• Decision maker compares two lotterylike games,
  each of which can result in a prize.

10
Assessing Discrete Probabilities

• Third method approach
• We would ask the decision maker to compare the
  lottery
  Win prize A if the Lakers win
  Win prize B if the Lakers lose
  With the lottery
  Win prize A with known probability
  p. Win prize B with probability 1-p.
  

11
Assessing Continuous Probabilities

• Apply the technique of assess individual
  probabilities and then use these to plot a rough
  CDF.
• The easiest way to use a continuous distribution
  in a decision tree or influence diagram is to
  approximate it with a discrete distribution.

12
Pitfalls Heuristics and Biases

• Heuristics can be thought of as rules of thumb
  for accomplishing tasks.
• They are easy and intuitive ways to deal with
  uncertain situations
• It takes considerable practice before one is
  comfortable making probability assessments.

13
Heuristics and Biases

• Representatives judge the probability that
  someone or something belongs to a particular
  category.
• Availability judge the probability that an event
  will occur according to the ease with similar
  events from memory.
• Traffic accident and fire

14
Heuristics and Biases

• Motivational Bias Incentives often exist that
  lead people to report probabilities that do not
  entirely reflect their true beliefs.
• Awareness of the heuristics and biases may help
  individuals make better probability assessments.

15
Experts and Probability Assessment

• In complex problems, expert risk assessment plays
  a major role in the decision-making process.
• The procedures for acquiring expert probability
  assessment has been established.
• Every assessment protocol should include the
  following steps
• Background

16
Experts and Probability

• Background The first important step
• Identification and recruitment of experts
• Motivating Experts
• Structuring and Decomposition, this step
  identifies specific variables for which judgments
  are needed.
• Probability-Assessment training

17
Experts and Probability

• Probability Elicitation and Verification, in this
  step the experts make the required probability
  assessment.
• As part of this process, an expert may provide
  detailed chains of reasoning for the assessments.
• Aggregation of Experts Probability Distribution

18
Subjective probability

• Constructing Distribution using RISKview
• Step 1 through 8

19
Chapter 8, Subjective Probability

• Summary
• Build model using subjective probability-assessmen
  t
• Continuous and discrete probability assessing
• Pitfalls and Heuristics
• Expert probability assessment