A Decision Analytic Perspective on Crisis Response and Management

1
A Decision Analytic Perspective on Crisis
Response and Management

• Simon FrenchManchester Business School
• simon.french_at_mbs.ac.uk

2
Plan of todays session

• Decision Analysis and Knowledge Management
• Technologies for decision support systems
• Problem formulation and modelling
• Exercise

3
Decision Analysis and Knowledge Management
4
Types of Decisions
5
Strategy Pyramid (1)

• Strategic
• Tactical
• Operational

6
Strategy Pyramid (2)
7
Planned, Orderly Activities
8
Responsive Activities
Immediate response regain of control
Strategic, unstructured decision making
Instinctive, (rehearsed?) decision making
9
Players
Decision Makers
10
Data, Information, Knowledge

• Data are, to a large extent, context-free
• Information is the result of organising, i.e.
  processing, data for a specific context, usually
  a decision.
• Knowledge is generic information which may be
  applied in a variety of contexts
• skills, understanding, experience and expertise
• explicit vs tacit

11
Data, Information, Knowledge
12
Knowledge Management

• data processing ? information management?
  knowledge management
• How does an organisation keep and deploy
  knowledge, expertise, skills, ?
• How do it know where to find them?
• Explicit Knowledge vs Tacit Knowledge

ICT can help
can ICT help?
13
Subjective Expected Utility Theory

• subjective probabilities representing beliefs
  P(s) gt P(s')
• utilities representing preferences u(x) gt u(x')
• SEU ranking based on

14
Bayesian analysis modelling, inference, and
decision
15
Framing Issues

• Imagine that you are a public health official and
  that an influenza epidemic is expected. Without
  any action it is expected to lead to 600 deaths.
  However, there are two vaccination programmes
  that you may implement

• Programme A would use an established vaccine
  which would save 200 of the population.
• Programme B would use a new vaccine which might
  be effective. There is a 1/3rd chance of saving
  600 and 2/3rds chance of saving none.

16
Framing Issues

• Imagine that you are a public health official and
  that an influenza epidemic is expected. Without
  any action it is expected to lead to 600 deaths.
  However, there are two vaccination programmes
  that you may implement

• Programme A would use an established vaccine
  which would lead to 400 of the population dying.
• Programme B would use a new vaccine which might
  be effective. There is a 1/3rd chance of no
  deaths and 2/3rds chance of 600 deaths.

17
Example

• Who is more likely to be mugged in an inner city
  area
• You
• An old age pensioner?

18
Availability
An event seems more likely if you can remember
ones like it so memorable events seem more likely
19
Value focused thinking(1)

• Values are what we care about. As such, values
  should be the driving force for our decision
  making. They should be the basis for the time
  and effort we spend thinking about decisions.
  But this is not the way it is. It is not even
  close to the way it is.
• Keeney (1992)

20
Value focused thinking(2)

• More creative
• alternative focused thinking closes down the mind
• value focus thinking opens it up
• Focuses attention on what matters
• Teams share common goals

21
Prescriptive Decision Analysis
22
The process of decision analysis
Formulate
Evaluate
Review
No
Requisite?
Yes
Decide
23
Technologies for decision support systems
24
Levels of Decision Support

• Level 0 Acquisition, checking and presentation
  of data, directly or with minimal analysis, to
  DMs
• Level 1 Analysis and forecasting of the current
  and future environment.
• Level 2 Simulation and analysis of the
  consequences of potential strategies
  determination of their feasibility and
  quantification of their benefits and
  disadvantages.
• Level 3 Evaluation and ranking of alternative
  strategies in the face of uncertainty by
  balancing their respective benefits and
  disadvantages.

25
Computer versus Human Ability
26
DSS by levels and domains
DecisionAnalysis
Level 3
ExpertSystems
ORmodels
Level of Support
Level 2
Softmodelling
Forecasting
Level 1
DatabasesData Mining
EIS
Level 0
Instinctive
Operational
Tactical
Strategic
27
DSS architecture
Database and database management system
User interface
Knowledge base and knowledge-based management
system
Models and model base management system
User
28
Janis and Mann

• Three phases of good decision making
• Unconflicted adherence
• Unconflicted change
• Vigilance

• Two types of bad decision making
• Defensive avoidance
• Hypervigilance

29
UnconflictedAdherence?UnconflictedChange?Vig
ilantDecisionMaking
No
Yes
Yes
No
30
Knowledge Management Systems

• very flexible data/information management systems
  to allow storage and access to material stored in
  a variety of formats and databases distributed
  across the computing systems together with very
  flexible querying tools to access such data,
  ideally using natural language or at least
  graphical interfaces
• collaborative working tools to share and work
  synchronously and asynchronously on materials
  together with full project, workflow, financial
  and diary management

31
Cynefin model of decision contexts
Knowable Cause and effect can be determined with
sufficient data The realm of scientific inquiry
Chaotic Cause and effect not discernable
Known Cause and effect understood and
predictable The realm of scientific knowledge
32
Types of decision making
Tactical
Strategic
Operational
Instinctive
33
Cynefin model of decision contexts
34
The context expected by current emergency
management DSS
35
and then as data accumulates
36
What can we learn from the past?
37
Chernobyl
38
TMI
39
Non nuclear events/issues

• Outside the Nuclear domain
• BSE
• GMOs
• MMR
• Challenger and Columbia Shuttle Disasters
• All indicate
• Change of role of science and public trust of
  science
• Difficulty of communication between scientists,
  managers and the public

40
An accident is an event in a human society
Long term
Late Phase
Early Phase
41
Decisions are not independent

• What we do in the early phase sets the context
  for the later phase and the long term
• in fact,
• what we say in the early phase sets the context
  for the later phase and the long term
• and
• the early phases responses can constrain the
  flexibility we may need in the long term

42
The domains of scientific models
Value based thinking important
QuantitativeScientific Models are usedto encode
Knowledge
43
Decision Support and Models

• Scientific Models encode our understanding of the
  past.
• Models for decision support need to provide
  requisite predictions of the future.

44
Key issues in using Scientific models

• Models poorly calibrated for emergency management
• too few datasets (thankfully!)
• Experts are overconfident in their models
• DMs do not understand the models
• DMs do not like uncertainty and conflicting views
• Different models

45
But perhaps the key issue is

• Models poorly calibrated for emergency management
• too few datasets (thankfully!)
• Experts are overconfident in their models
• DMs do not understand the models
• DMs do not like uncertainty and conflicting views
• Different models
• Scientific models focus attention on the known
  and knowable domains

46
In summary

• The context will almost certainly become
• complex
• Thus we need a socio-technical decision support
  process
• which anticipates this complexity
• multi-disciplinary
• integrated
• Is it sometimes too partitioned into different
  groups of experts?

47
Problem formulation and modelling
48
Brainstorming

• Simply get a group to list ideas that seem
  relevant without evaluation
• Built on the notions
• on idea triggers another
• all ideas have equal value a priori
• Write up on whiteboard or Post-its

49
Value focused thinking

• Early on brainstorm values and objectives
• Values are what we care about. As such, values
  should be the driving force for our decision
  making. They should be the basis for the time
  and effort we spend thinking about decisions.
  But this is not the way it is. It is not even
  close to the way it is.
• Keeney (1992)
• More creative
• alternative focused thinking closes down the mind
• value focus thinking opens it up

50
Check-lists

• Simply an aide-memoire
• Used to prime brainstorming
• Used to structure reports

51
PEST and 7 Ss

• External environment
• Political
• Economic
• Social
• Technical

• Internal Environment
• Strategy
• Structure
• Systems
• Style
• Shared values
• Skills
• Staff

52
SWOT
53
Simple two dimensional plots

• Easy to draw on paper or flip charts
• Even better use post-its

54
Stakeholder Identification
55
Stakeholders involved in Asthma Drug Scare
56
Uncertainty identification
57
Networks

• Can show inter-relations

58
Cognitive Mapping
59
Preference ModellingAttribute Hierarchies
Hierarchy used in Chernobyl Study
60
Rich Picture Diagrams

• A picture speaks a 1000 words ...

61
Rich picture diagram of hole in the ozone layer
issues as perceived in 1988
From Daellenbach (1994)
62
(No Transcript)
63
(No Transcript)