ArticlePDF Available

Decisions with Multiple Objectives: Preferences and Value Trade-Offs

Authors:
Ralph L. Keeney at Duke University
Ralph L. Keeney
Howard Raiffa
Howard Raiffa
Howard Raiffa
  • This person is not on ResearchGate, or hasn't claimed this research yet.
David W. Rajala
David W. Rajala
David W. Rajala
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Download full-text PDF
Read full-text
Download citation

Abstract

Not Available
Content uploaded by Ralph L. Keeney
Author content
All content in this area was uploaded by Ralph L. Keeney on Nov 20, 2014
Content may be subject to copyright.
IEEE
TRANSACTIONS
ON
SYSTEMS,
MAN,
AND
CYBERNETICS,
VOL.
SMC-9,
No.
7,
JULY
1979
FM
feedback
loops
and
phase-locked
loops,
respectively.
The
linear
models
are
presented
with
design
graphs
and
the
effects
of
nonlinearities
and
noise
are
discussed.
Chapter
6
is
devoted
to
the
design
of
phase-locked
loops
for
FM
demo-
dulation
and
includes
the
necessary
design
curves.
The
chapter
is
well
illustrated
by
a
number
of
numerical
design
problems.
Chapter
7
covers
the
design
of
frequency-feedback
loops
for
FM
demodulation
and
again
gives
a
step-by-step
design
procedure
with
a
number
of
illustrative
examples.
Chapter
8
explains
the
need
for
designing
and
methods
for
the
design
of
compound
and
multiple
loops
for
low-threshold
demodulation.
The
ninth
chapter
contains
a
very
short
review
of
digital
FM
and
considers
very
briefly
a
number
of
other
phase-locked
loop
applications
(including
a
passing
reference
to
frequency
synthesis,
which
has
become
a
major
topic
in
its
own
right
since
the
book
was
published).
The
final
chapter
contains
a
review
of
system
test
procedures-a
useful
but
unusual
item
in
a
textbook.
There
are
a
number
of
useful
analytical
appendices,
including
one
on
varactor
VCO
distortion.
The
bibliography
is
extensive
and
is
laid
out
both
chronologically
and
according
to
topic.
Workers
in
the
communications
field
will
find
this
work
a
valuable
reference
book.
A
major
criticism
is
that
the
work
on
phase-locked
loops
is
confined
to
the
analog
variety;
digital
phase-locked
loops,
nowadays
extensively
used
in
frequency
synthesis,
are
neglected.
Decisions
with
Multiple
Objectives:
Preferences
and
Value
Trade-Offs-R.
L.
Keeney
and
H.
Raiffa
(New
York:
Wiley,
1976,
569
pp.).
Reviewed
by
David
W.
Rajala,
Department
of
Engineering
Science
and
Systems,
Univer-
sity
of
Virginia,
Charlottesville,
VA
22903.
This
book
is
a
welcome
and
unquestionably
significant
contribution
to
the
practice
of
decision
analysis
as
well
as
to
the
research
and
teaching
of
its
theory
and
application.
Its
primary
contributions
are
a
development
of
a
prescriptive
framework,
based
on
some
behavioral
assumptions,
for
quantifying
decisionmaker
preferences
under
uncertainty
through
the
unification
of
extensive
theoretical
results
previously
appearing
predo-
minantly
in
the
journal
literature
and
a
concurrent
lucid
exposition
of
the
operational
aspects
of
that
framework.
This
book
is
important
to
those
practicing
systems
engineering,
as
well
as
to
economists,
managers,
policy
advisors,
and
others
because
of
the
ubiquitous
nature
of
decision
problems
and
the
book's
treatment
of
a
variety
of
real
applications.
The
authors
have
stressed
the
need
for
the
decisionmaker
to
think
hard
and
systema-
tically
about
his/her
decision
problem
and,
for
the
preference
assessment
process,
have
emphasized
a
decomposition
approach
by
which
to
examine
value
trade-offs
and
risk
attitudes.
The
material
in
this
book
may
be
organized
into
four
categories.
The
subject
of
the
first
category
is
the
defining
and
structuring
of
problems
for
a
multiattribute
decision
analysis.
In
the
second
category
the
theory
of
quantifying
preferences
over
multiple
objectives
is
presented.
Applications
of
the
theory
are
presented
in
the
third
category.
The
last
category
intro-
duces
two
important
special
topics:
preferences
over
time
and
the
aggrega-
tion
of
individual
preferences.
The
reader
should
have
little
difficulty
comprehending
the
theory's
basic
concepts
because
of
the
book's
organi-
zation
and
clarity
of
presentation.
For
example,
standard
concepts
such
as
independence,
risk
attitude,
and
value
and
utility
functions,
which
have
come
out
of
economics,
the
management
sciences,
mathematics,
opera-
tions
research,
and
psychology,
are
unambiguously
defined,
and
the
use
of
notation
is
consistent
throughout.
Although
the
first
chapter
introduces
the
subject
of
decision
analysis,
it
might
be
helpful
if
the
reader
were
familiar
with
its
fundamentals
as
presented
in
[1],
[3],
[4],
for
example.
A
more
extensive
treatment
of
the
encoding
of
uncertainty
in
decision
analysis
problems,
not
the
subject
of
this
text,
may
be
found
in
[1]-[5].
The
material
related
to
problem
definition
and
structuring
is
composed
of
two
chapters
that
respectively
introduce
the
decision
analysis
paradigm
and
the
preference
structuring
process.
The
development
of
decision
analysis
is
motivated
by
sketches
of
a
variety
of
complex
real
decision
problems
from
business,
medicine,
and
the
public
sector,
and
later
by
methodological
problems.
The
sections
pertaining
to
the
authors'
com-
ments
on
the
decision
analysis
paradigm
and
on
complex
value
problems
offer
valuable
insight
into
decision
analysis
use.
The
authors'
concern
with
the
preference
structuring
process
has
ranged
from
suggesting
useful
guidelines-for
obtaining
quality
inputs
to
suggesting
criteria
for
judging
the
quality
of
its
output.
Topics
discussed include
the
generation
of
objec-
tives
and
identification
of
attributes
(objectives
measures),
the
hierarchical
manner
in
which
objectives
are
often
structured,
and
attribute
selection
criteria.
The
theory
of
quantifying
preferences
over
multiple
objectives
is
covered
in
four
chapters.
In
Chapter
3
systematic
procedures
for
ranking
a
set
of
consequences
whose
value
is
described
in
terms
of
multiple
attrib-
utes
are
considered
in
order
to
compare
alternatives
under
conditions
of
certainty.
It
includes
presentations
on
choice
precedures
not
requiring
a
formalized
preference
structure,
trade-offs,
preferential
independence
and
its
implications,
and
willingness
to
pay.
In
Chapter
4
a
generalization
to
the
uncertain
case
occurs
for
the
special
situation
of
a
single
attribute.
It
lucidly
presents
the
utility
concept
and
develops
procedures
for
analyzing
and
assessing
a
decisionmaker's
preferences
under
uncertainty.
The
struc-
ture
and
assessment
of
multiattribute
utility
functions
are
examined
in
Chapters
5
and
6.
The
former
addresses
the
two-attribute
case,
and
the
latter
is
concerned
with
the
more
complicated
situation
of
more
than
two
attributes.
Utility
and
additive
independence
concepts
and
their
implica-
tions
are
presented
together
with
an
operational
procedure
for
assessing
a
multiattribute
utility
function.
Throughout
the
chapters
in
this
category,
the
authors
provide
valuable
insight,
based
on
their
experience,
to
facili-
tate
implementation
of the
theory.
There
are
two
chapters
presenting
noncontrived
cases
to
demonstrate
the
theory's
application.
Chapter
7
is
exclusively
devoted
to
examining
assessments
of
preferences
for
a
variety
of
interesting
topics,
including
an
air
pollution
problem,
a
resource
allocation
problem
for
an
educational
program,
the
problem
of
structuring
corporate
preferences,
nuclear
power
plant
siting
and
liscensing,
and
many
others.
A
complete
case
is
carefully
presented
in
Chapter
8
for
the
siting
of
a
Mexico
City
airport.
It
includes
a
definition
of
the
problem,
a
specification
of
the
client's
value
system
through
the
definition
and
structuring
of
objectives
and
their
measures,
development
of
a
decision
model
and
the
requisite
probability
and
multi-
attribute
preference
assessments,
an
analysis
of
alternatives,
and
a
follow-
up
appraisal
of
the
study's
impact.
The
special
topics
material
is
contained
in
two
chapters.
Chapter
9,
contributed
to
by
Richard
F.
Meyer,
presents
a
multiattribute
framework
for
examining
preferences
over
time.
Its
emphasis
is
on
the
discrete-time
problem,
and
it
introduces
many
of
the
usual
concepts
such
as
discounting
and
an
uncertain
horizon.
Chapter
10
contains
an
introduction
to
the
complex
problem
of
aggregating
individual
preferences.
It
considers
Arrow's
impossibility
theorem
and
interprets
many
of
the
results
of
Chap-
ter
3
in
the
context
of
the
group
problem.
Short
appendices,
totaling
four
in
number,
appear
at
the
end
of
certain
chapters
and
present
material
supplementary
to
the
main
development.
There
is
also
a
valuable
and
extensive
bibliography
that
should
be
of
considerable
use
to
a
diverse
audience.
The
lack
of
any
home
problems
should
not
hinder
the
reasonably
capable
reader
from
understanding
or
applying
this
material.
In
summary,
this
well-written
book
is
an
outstanding
addition
to
the
decision
analysis
literature.
Most
of
the
theoretical
results,
having
previously
appeared
in
professional
journals,
are
new
in
textbook
form.
Additionally,
the
synthesis
of
the
theoretical
results
with
some
original
contributions
to
the
operational
aspects
of
the
theory
makes
this
book
currently
quite
unique.
REFERENCES
[1]
R.
V.
Brown,
A.
S.
Kahr,
and
C.
Peterson,
Decision
Analysis
for
the
Manager.
New
York:
Holt,
Rinehart,
and
Winston,
1974.
[2]
J.
M.
Hampton,
P.
G.
Moore,
and
H.
Thomas,
"Subjective
probability
and
its
measurement,"
J.
Of
the
Roy.
Statistical
Society,
Series
A,
vol.
136,
pp.
21-42,
1973.
[3]
R.
A.
Howard,
"The
foundations
of
decision
analysis,"
IEEE
Trans.
Syst.
Sci.
Cybern.,
vol.
SSC-4,
pp.
211
-219,
1968.
[4]
H.
Raiffa,
Decision
Analysis.
Reading,
MA:
Addison-Wesley,
1968.
[5]
C.
S.
Spetzler
and
C-A.
S.
Stael
von
Holstein,
"Probability
encoding
in
decision
analysis,"
Management
Science,
vol.
22,
pp,
340-358,
1975.
403
... Production management models developed and used by C. Clark, and G. Munro are widely known and discussed [1,2].They have been applied to modeling and optimal management in the Canadian fishing industry and in the mining and, to a lesser extent, the forestry industry. In this study, to 2 renewable forest industry we add consideration of social, economic and other factors in supplement [13]. This is achieved with the multiattribute utility theory, in fact with a multiattribute utility function as a mathematical description of the main objective and appropriate subobjectives. ...
... The new element is the consideration of the social effect for the population such as the labor force (financial means for salaries), the ecological effect such as biodiversity and their combination with the economic efficiency of logging (harvested wood) [2,9]. A multiattribute utility function was constructed, which in different control models was used as an objective function [13,15,16]. The utility function is built on the basis of the preferences of a specialist biologist (in this case, a teaching unuversity professor) as an expert on the considered forestry. ...
... In previous studies, a multi-attribute utility function was built taking into account three factors related to the considered forestry and logging [13,16]. For this we will briefly describe the result. ...
RENEWABLE PRODUCTION, STOCHASTIC MODELING AND VALUE DRIVEN CONTROL: A FOREST MANAGEMENT CASE
Presentation
Full-text available
  • Jun 2024
Managing forest ecosystems with uncertain threshold responses and multiple factors poses nontrivial analytical challenges. The paper investigate the question of multifactor management of stochastically renewable resources of a forest systems. Timber harvesting closely concerns local population from economic and ecological position. The production is relevant only as means to achieve human values. Because of this values are the focus of the decision making and the strategic management needs to defining and structuring the fundamental values. In the paper are discussed a value oriented stochastic model, based on a multiattribute utility function which analytically represents human preferences. Such value based modeling permits mathematical description of complex stochastic multifactor processes and even optimal control. The mathematical solutions define a well-founded ecologically, socially and economically oriented strategy of forest resource management.
View
... Decision-makers (DMs) seeking a method and software for their MCDM problems face a dilemma between ease of use and the quality of the decision recommendation. In general, the MAUT methodology [13] is considered demanding and difficult due to the trade-offs between objectives that need to be assessed. To reduce the application hurdles and avoid overwhelming the DM, certain methodologies, such as AHP [14] and outranking methods [15], are based on clear and simple queries. ...
... MAUT has clear advantages over most other methods in this respect. The reason for this can be explained by the comparatively simple and strictly decomposition mathematics combined with a theoretically clean foundation [13]. Although the trade-offs between objectives required by MAUT are-as mentioned above-difficult to determine, they can be clearly interpreted in terms of content without further fuzziness. ...
... In his recent book, Keeney [27] also refers to the ENTSCHEIDUNGSNAVI as the only tool comprehensively supporting VFT. In the decision back-end, the concept of MAUT [13] is used to find the best alternative under uncertainty. In addition, the ENTSCHEIDUNGSNAVI offers many different evaluation methods that allow the DM to reflect on and analyze their results. ...
Integrating Uncertainties in a Multi-Criteria Decision Analysis with the Entscheidungsnavi
Article
Full-text available
  • Jun 2024
The Entscheidungsnavi is an open-source decision support system based on multi-attribute utility theory, that offers various methods for dealing with uncertainties. To model decisions with uncertainties, decision-makers can use two categories: Forecast and Parameter Uncertainties. Forecast Uncertainty is modeled with (combined) influence factors using discrete, user-defined probability distributions or predefined ‘worst-median-best’ distributions. Parameter Uncertainty allows imprecision for utilities, objective weights, and probability distributions. To analyze these uncertainties, the Entscheidungsnavi offers several methods and tools, like a robustness check, based on (Monte Carlo) simulations and a sensitivity analysis. The objective weight analysis provides insights into the effects of different objective weight combinations. Indicator impacts, tornado diagrams, and risk profiles visualize the impact of uncertainties in a decision under risk. Risk profiles also enable a check for stochastic and simulation dominance. This article presents the complete range of methods for dealing with uncertainties in the Entscheidungsnavi using a hypothetical case study.
View
... We validate our coding scheme in two studies (Study 2 and 3) and then use the covariance structure of this dataset to derive a hierarchical taxonomy of the diverse considerations at play in naturalistic decision making, which gives us new insights into the prominence of different decision attributes, their co-occurrence relationships and tradeoffs, and their distribution across different demographic groups and social contexts. Finally, we use this taxonomy, in combination with existing decision models [52][53][54][55] , to predict people's choices across diverse naturalistic dilemmas (Study 4 and 5). Our LLM pipeline is illustrated in Figure 1, Figure S1 shows an example of a post as well GPT outputs and our attribute analysis, and Table 1 presents a summary of the 207 theory-driven attributes, outcomes, and goals, analyzed in our paper. ...
... This implies that formal decision theories developed by researchers-theories that describe how people resolve attribute tradeoffs-can be applied alongside our pipeline to predict naturalistic choices between common dilemmas. One such theory is the weighted additive rule, which proposes that people's preferences take the form of attribute weights, and that an option's utility is simply the weighted sum of its attributes [52][53][54][55] . If our computational pipeline accurately codes the attributes in the dilemmas then, based on the weighted additive rule, we would expect participants who have a higher preference for one attribute over another to consistently pick choice options with the first attribute over choice options with the second attribute. ...
The Structure of Everyday Choice: Insights from 100K Real-life Decision Problems
Preprint
Full-text available
  • Feb 2024
The diversity and complexity of everyday choices make them difficult to formally study. We address this challenge by constructing a dataset of over 100K real-life decision problems based on a combination of social media and large-scale survey data. Using large language models (LLMs), we are able to extract hundreds of choice attributes at play in these problems and map them onto a common representational space. This representation allows us to quantify both the content (e.g. broader themes) and the structure (e.g. specific tradeoffs) inherent in everyday choices. We also present subsets of these decision problems to human participants, and find consistency in choice patterns, allowing us to predict naturalistic decisions with established decision models. Overall, our research provides new insights into the attributes, outcomes, and goals that underpin important life choices. In doing so, our work shows how LLM-based large-scale structure extraction can be used to study real-world human behavior.
View
... Organizations, in general, need to deal with multiple objectives constantly, and the decision-making process needs to include them in decision guiding. However, this is not a simple procedure due to situations in which the objectives of a decision may be conflicting [9,10]. Thus, the decision-support methodologies aim to assist in this process, which involves the study and development of models that can help the decision-maker to make a decision considering the performance of other actors, such as analysts, stakeholders, experts, among others. ...
... Unlike classical optimization problems, multiple-criteria decision-making problems deal with more than one objective simultaneously. In addition, these objectives often conflict with each other, which brings the study closer to reality and allows for broad applications in practical problems [9,[30][31][32]. ...
Multicriteria Decision-Making in Public Security: A Systematic Review
Article
Full-text available
  • Jun 2024
The Multiple Criteria Decision-Making/Analysis (MCDM/A) methods have been widely used in several management contexts. In public security, their use enhances managerial decision-making by considering the decision-maker’s preference structure and providing a multidimensional view of problems. However, methodological support for their applications in this field lacks clarity, including selecting appropriate methods, addressing pertinent problematics, and identifying alternatives and criteria. To address this gap, this article conducts a Systematic Literature Review (SLR) to diagnose the state of the art and identify the main directions of the research in multicriteria models applied to public security management. The research methodology involves five main research questions, and the extraction and analysis of data from 51 articles selected through a structured filtering process. The analysis includes identifying the number of publications and citations, as well as listing the MCDM/A approaches and issues employed. Furthermore, the criteria used and the number of criteria considered are discussed, as well as the method employed. Finally, the identification of the main research directions in MCDM/A models applied to public security is presented. The findings suggest that prioritization and classification are common problematics, social criteria are frequently considered, and the AHP method is widely used, often employing fuzzy sets and hybrid models.
View
... Emerging from the operations research community, the field of multi-criteria decision analysis (MCDA) focuses on decision-making under multiple conflicting criteria (Keeney & Raiffa, 1993;Pomerol & Barba-Romero, 2000). Although our work is related to this field, it diverges from the traditional MCDA approaches, which often involve aggregating preferences across criteria into a single performance measure (Young, 1974;Dyer & Sarin, 1979;Baskin & Krishnamurthi, 2009;Baumeister & Rothe, 2016;Bhatia et al., 2020). ...
Preferential Multi-Objective Bayesian Optimization
Preprint
Full-text available
  • Jun 2024
Preferential Bayesian optimization (PBO) is a framework for optimizing a decision-maker's latent preferences over available design choices. While preferences often involve multiple conflicting objectives, existing work in PBO assumes that preferences can be encoded by a single objective function. For example, in robotic assistive devices, technicians often attempt to maximize user comfort while simultaneously minimizing mechanical energy consumption for longer battery life. Similarly, in autonomous driving policy design, decision-makers wish to understand the trade-offs between multiple safety and performance attributes before committing to a policy. To address this gap, we propose the first framework for PBO with multiple objectives. Within this framework, we present dueling scalarized Thompson sampling (DSTS), a multi-objective generalization of the popular dueling Thompson algorithm, which may be of interest beyond the PBO setting. We evaluate DSTS across four synthetic test functions and two simulated exoskeleton personalization and driving policy design tasks, showing that it outperforms several benchmarks. Finally, we prove that DSTS is asymptotically consistent. As a direct consequence, this result provides, to our knowledge, the first convergence guarantee for dueling Thompson sampling in the PBO setting.
View
... The Ottawa Decision Support Framework is well-cited (36) and speci cally includes the context of the persons facing the decision as well as other people who in uence the decision. The framework is theoretically grounded in expectancy value, social support, cognitive and psychological theories (37)(38)(39)(40)(41)(42)(43)(44). Within the framework, a person makes a decision based on knowledge of alternatives, expectations, values, beliefs about the alternatives, and knowledge of decisional con icts, and is given support and resources to make and implement the decision (36). ...
Decisional needs for older adults, home health care nurses and dental hygienists during team-based oral health assessments in ordinary home settings – a qualitative study
Preprint
Full-text available
  • May 2024
Background Participation by all actors involved in health planning is a prerequisite for person-centred care and healthy ageing. Understanding the multiple knowledge needs and the values that shape oral health assessments in home settings is important both to enable participation in oral health planning and to contribute to healthy ageing. Objective The aim of this study was to investigate decisional needs during oral health assessments in ordinary home settings from the perspectives of older adults, home health care nurses and dental hygienists. Methods Data was collected in ordinary home settings through 24 team-based oral assessments and 39 brief, semi-structured interviews including older adults (n = 24), home health care nurses (n = 8) and dental hygienists (n = 7). Data was analysed using content analysis with a deductive approach. The analysis was guided by the Ottawa Decision Support Guide. Results The analysis revealed that all participants considered participation in decision-making important but until now, older adults might not have participated in making decisions regarding oral health issues. The older adults considered participation important because the decisions had a strong impact on their lives, affecting their health. The professionals considered decision-making important for knowing what step to take next and to be able to follow up and evaluate previous goals and treatments. Organizational and personal barriers for shared decision-making among home health care nurses and dental hygienists were identified. Of the 24 older adults, 20 had different oral health conditions that objectively indicated the need for treatment. An initial important decision concerned whether the older adult wanted to make an appointment for dental care, and if so, how. Another decisional conflict concerned whether and how assisted oral care should be carried out. Conclusion It is important for key participants in ordinary home settings to participate in interprofessional teams in home health care. To further anchor this in theory, conceptual models for professionals from different care organizations (municipal care, dental care) need to be developed that also involve older adults as participants. Future research could bridge theory and practice by including theories of learning while exploring interorganizational oral health planning in home settings.
View
WHO Bacterial Priority Pathogens List, 2024
Technical Report
Full-text available
  • Jun 2024
Overview The 2024 WHO Bacterial Priority Pathogens List (WHO BPPL) is an important tool in the global fight against antimicrobial resistance. Building on the 2017 edition, the 2024 WHO BPPL updates and refines the prioritization of antibiotic-resistant bacterial pathogens to address the evolving challenges of antibiotic resistance. The list categorizes these pathogens into critical, high, and medium priority groups to inform research and development (R&D) and public health interventions. The 2024 WHO BPPL covers 24 pathogens, spanning 15 families of antibiotic-resistant bacterial pathogens. Notable among these are Gram-negative bacteria resistant to last-resort antibiotics, drug-resistant mycobacterium tuberculosis, and other high-burden resistant pathogens such as Salmonella, Shigella, Neisseria gonorrhoeae, Pseudomonas aeruginosa, and Staphylococcus aureus. The inclusion of these pathogens in the list underscores their global impact in terms of burden, as well as issues related to transmissibility, treatability, and prevention options. It also reflects the R&D pipeline of new treatments and emerging resistance trends. The WHO BPPL acts as a guide for prioritizing R&D and investments in AMR, emphasizing the need for regionally tailored strategies to effectively combat resistance. It targets developers of antibacterial medicines, academic and public research institutions, research funders, and public–private partnerships investing in AMR R&D, as well as policy-makers responsible for developing and implementing AMR policies and programs. Further details on the rationale behind the list, the methodologies used to develop the list and the key findings, can be found in the accompanying report.
View
View
When Are We Willing to Wait? Prescriptive Challenges in Evaluating Intertemporal Outcomes
Chapter
  • May 2024
The classic normative model for intertemporal preferences uses a constant discount rate, but behavioral experiments have shown that people do not tend to make choices consistent with a constant discount rate. We first present normative models for time preferences, then discuss descriptive results for choices between single outcomes occurring at different times. People often have different implicit discount rates for different types of scenarios, and several anomalies arise consistently. We contrast those results with findings for preferences for sequences of multiple outcomes over time. People tend to prefer increasing or constant sequences of outcomes over time, especially when the outcomes are non-monetary in nature. This suggests a willingness to wait for improvement, but not in the way that classical discounting would prescribe. We end with prescriptive nudges to improve dynamic consistency and pose questions still to be resolved about how decisions involving outcomes over time can be improved prescriptively.
View
Consequences of Missing Objectives in Applications of Multiattribute Utility Analysis
Chapter
  • May 2024
Multiattribute decision analysis allows decision makers to identify their objectives as a critical part of constructing a prescriptive model for decision making. Failure to consider all relevant objectives is one of the leading causes of poor decision outcomes (Keeney & Raiffa, Decisions with multiple objectives: Preferences and value trade-offs. Cambridge University Press, 1976). However, studies have shown that decision makers are often ill-equipped to identify objectives and may generate less than half of the objectives they later recognize as important (Bond et al., Management Science, 54(1), 56–70, 2008; Bond et al., Decision Analysis, 7(3), 238–255, 2010). The present study examines the consequences of incomplete objective sets in a broad range of multiattribute utility analysis applications from various fields such as energy planning, conservation, and disaster management. We compare agreement between models that use the originally identified objectives with models constructed from only a subset of objectives using performance metrics related to the top choice, value loss, and rank ordering of alternatives. Analyses of the MAU applications considered suggest that the consequences of missing objectives depend primarily on three factors: (1) the direction and magnitude of the relationships (correlations) between attributes defining the objectives, (2) the decision space of the alternatives considered, i.e., the competitiveness and spread of the alternatives, and (3) the steepness of the assessed scaling parameters (weights). Our analysis demonstrates in actual MAU applications that the magnitude of negative consequences associated with missing objectives is highly variable.
View
Subjective Probability and Its Measurement
Article
  • Jan 1973
  • J R STAT SOC B
Subjective probability is defined and its place in decision analysis, with special reference to business problems, is identified. The literature on its measurement is critically analysed both for the single decision-maker and group. The use of direct fractile assessment and the Delphi Technique are felt to be some of the more tenable of the methods reviewed. An account of some of the behavioural aspects of decision-making with a résumé of the "risky" shift theories is included and their implications are discussed. Some practical guidelines and suggestions for further research are indicated.
View
View
Exceptional Paper--Probability Encoding in Decision Analysis
Article
  • Nov 1975
This paper presents the present philosophy and practice used in probability encoding by the Decision Analysis Group at Stanford Research Institute. Probability encoding, the process of extracting and quantifying individual judgment about uncertain quantities, is one of the major functions required in the performance of decision analysis. The paper discusses the setting of the encoding process, including the use of sensitivity analyses to identify crucial state variables for which extensive encoding procedures are appropriate. The importance of balancing modeling and encoding techniques is emphasized and examples of biases and unconscious modes of judgment are reviewed. A variety of encoding methods are presented and their applicability is discussed. The authors recommend and describe a structured interview process that utilizes a trained interviewer and a number of techniques designed to reduce biases and aid in the quantification of judgment.
View
The Foundations of Decision Analysis
Article
  • Oct 1968
Decision analysis has emerged from theory to practice to form a discipline for balancing the many factors that bear upon a decision. Unusual features of the discipline are the treatment of uncertainty through subjective probability and of attitude toward risk through utility theory. Capturing the structure of problem relationships occupies a central position; the process can be visualized in a graphical problem space. These features are combined with other preference measures to produce a useful conceptual model for analyzing decisions, the decision analysis cycle. In its three phases¿deterministic, probabilistic, and informational¿the cycle progressively determines the importance of variables in deterministic, probabilistic, and economic environments. The ability to assign an economic value to the complete or partial elimination of uncertainty through experimentation is a particularly important characteristic. Recent applications in business and government indicate that the increased logical scope afforded by decision analysis offers new opportunities for rationality to those who wish it.
View
Decision Analysis for the Manager
  • Jan 1974
  • R V Brown
  • A S Kahr
  • C Peterson
R.V. Brown, A.S.Kahr, and C.Peterson, Decision Analysis for the Manager.New York: Holt, Rinehart, and Winston, 1974.