Decision Analysis for Management
Judgement
Chapter 2 How people make decisions involving multiple objectives
Introduction
Simon used the term bounded rationality to refer to the fact that the limitations of the human mind
mean that people have to use ‘approximate methods’ to deal with most decision problems and,
as a result, they seek to identify satisfactory, rather than optimal, courses of action. These
approximate methods, or rules of thumb, are often referred to as ‘heuristics’. Heuristics are often
well adapted to the structure of their knowledge about the environment. ‘fast and frugal heuristics’
are quick ways of decision making when time is limited.
Heuristics used for decisions involving multiple objectives
When a decision maker has multiple objectives the heuristic used will either be compensatory or
non-compensatory. In a compensatory strategy an option’s poor performance on one attribute is
compensated by good performance on others. Compensatory strategies involve more cognitive
effort because the decision maker has the difficult task of making trade-offs between improved
performance on some attributes and reduced performance on others.
The recognition heuristic
The recognition heuristic is used where people have to choose between two options. If one is
recognized and the other is not, the recognized option is chosen. This simple heuristic is likely to
work well in environments where quality is associated with ease of recognition. It may be that a
more easily recognized manufacturer is likely to have been trading for longer and be larger. Its
long-term survival and size may be evidence of its ability to produce quality products and to
maintain its reputation.
The minimalist strategy
In this heuristic the decision maker first applies the recognition heuristic, but if neither option is
recognized the person will simply guess which is the best option. In the event of both options
being recognized then the person will pick at random one of the attributes of the two options. If
this attribute enables the person to discriminate between the two options they will make the
decision at this point. If not, then they will pick a second attribute at random, and so on.
Take the last
This is the same as the minimalist heuristic except that people recall the attribute that enabled
them to reach a decision last time when they had a similar choice to make. If this attribute does
not allow them to discriminate between the options this time then they will choose the attribute
that worked the time before, and so on. If none of the previously used attributes works, then a
random attribute will be tried.
The lexicographic strategy
In some circumstances the decision maker may be able to rank the attributes in order of
importance. In this case the decision maker can employ the lexicographic heuristic. This simply
involves identifying the most important attribute and selecting the alternative which is considered
to be best on that attribute. In the event of a ‘tie’ on the most important attribute, the decision
maker will choose the option which performs best on the second most important attribute (size),
and so on. In addition, the strategy is non-compensatory. With deeper reflection, a decision
,maker might have preferred an option that performed less well on the most important attribute
because of its good performance on other attributes.
The semi-lexicographic strategy
This differs slightly from the lexicographic strategy in that, if the performance of alternatives on an
attribute is similar, the decision maker considers them to be tied and moves on to the next
attribute.
Transitivity: if you prefer a to b and b to c, then you should also prefer a to c.
Elimination by aspects (EBA)
In this heuristic the most important attribute is identified and a cutoff point is then established. Any
alternative falling below this point is eliminated. The process continues with the second most
important attribute and so on. The major flaw in EBA is its failure to ensure that the alternatives
retained are, in fact, superior to those which are eliminated. This arises because the strategy is
non-compensatory. For example, when selecting a car, one of the cars might have been rejected
because it was slightly below the 1600cc cutoff value. Yet its price, service history and mileage
were all preferable to the car you purchased. These strengths would have more than
compensated for this one weakness
Sequential decision making: satisficing
In some situations, however, alternatives become available sequentially. For example, if you are
looking for a new house you might, over a period of weeks, successively view houses as they
become available on the market. Herbert Simon, 7 has argued that, in these circumstances,
decision makers use an approach called satisficing. The key aspect of satisficing is the aspiration
level of the decision maker which characterizes whether a choice alternative is acceptable or not.
Simon argues that you will search for jobs until you find one that meets your aspiration levels on
all attributes. Once you have found such a job you will take it and, at least for the time being,
conclude your job search. In a satisficing model, search terminates when the best offer exceeds
an aspiration level that itself adjusts gradually to the value of the offers so far received. It could be
that an unsuccessful search may lower your aspiration level such that you fall bac on what is now
seen as an acceptable alternative. Note also that satisficing is yet another example of a non-
compensatory strategy.
Reason-based choice
According to Shafir et al. ‘when faced with the need to choose, decision makers often seek and
construct reasons in order to resolve the conflict and justify their choice to themselves and to
others’. Reason-based choice can lead to some unexpected violations of the principles of rational
decision making. Positive features are weighted more highly when selecting and negative
features more highly when rejecting. This violates a basic principle of rational decision making
that choice should be invariant to the way the decision is framed. Another principle of rational
decision making is that of ‘ independence of irrelevant alternatives ’. If you prefer a holiday in
Mexico to a holiday in France you should still prefer the Mexican to the French holiday, even if a
third holiday in Canada becomes available. Reason-based decision making can lead to a
violation of this principle.
Factors affecting which strategies people employ
Factors that affect our choices include:
The time available to make the decision;
Th effort that a given strategy will involve;
The decision maker’s knowledge about the environment;
The importance of making an accurate decision;
, Whether or not the decision maker has to justify his or her choice to others;
A desire to minimize conflict.
Payne et al. argue that decision makers choose their strategies to balance the effort involved in
making the decision against the accuracy that they wish to achieve (the effort-accuracy
framework)
Other characteristics of decision making involving multiple objectives
Decoy effects
By creating a situation where one option (car with the insurance) is clearly better than another
other (the staid car without the insurance), the decision maker is presented with an easy
comparison. As a result, the attraction of the first option is enhanced. In fact, it now looks so
attractive that it is perceived to be better than its original competitor. When the choice situation is
said to exhibit asymmetric dominance, it means that one of the deals clearly dominates the
decoy, but the other does not. It is the offer that clearly dominates the decoy which becomes
substantially more attractive in these situations.
A similar phenomenon results from what are referred to as phantom decoys.26 Unlike the decoys
we have just discussed, these are options which asymmetrically dominate a particular option but
then turn out to be unavailable. For example, suppose you have difficulty choosing between two
makes of laptop computer: a cheap brand that will be heavy to carry around and a more
expensive but much lighter model. You then see that a retailer is advertising a 20% price discount
on the cheap, heavy model to the first 50 purchasers who arrive at its store. Unfortunately, when
you get to the store all of the deals have gone. Despite this, the phantom decoy has been found
to enhance the attraction of the original option relative to other options in many situations. As a
result you still choose the cheap model, despite the absence of the discount, because the
phantom decoy has made it appear to be much better than the other laptop.
Choosing by unique attributes
Research has shown that the degree to which attributes are shared across alternatives influences
which alternatives are preferred. Decision makers tend to place more importance on attributes
which possess unique rather than shared information. Unique favorable attributes help to make a
choice. This effect is called ‘attribute salience’.
Chapter 3. Decisions involving multiple objectives: SMART
Introduction
When faced with a large and complex problem, there may be too much information to handle
simultaneously so the decision maker is forced to use simplified mental strategies, or heuristics,
in order to arrive at a choice. By splitting the problem into small parts and focusing on each part
separately, the decision maker is likely to acquire a better understanding of the problem than that
which would be achieved by taking a holistic view.
Axioms: a set of generally accepted propositions or a formalization of common view. If the
decision maker accepts. Accepts the axioms then it follows that the results of the analysis will
indicate how he or she should behave if the decision is to be made in a rational way. The analysis
is therefore normative or prescriptive; it shows which alternative should be chosen if the decision
maker acts consistently with his or her stated preferences. The method explained here is
normally applied in situations where a particular course of action is regarded as certain (or
virtually certain) to lead to a given outcome so that uncertainty is not a major concern of the
analysis.
Basic terminology
Objectives and attributes
, Objective: an indication of the preferred direction of movement (maximize/ minimize)
Attribute: to measure performance in relation to an objective
Proxy attribute: an attribute which is not directly relate to the objective
Value and utility
Value: if the decision involves no element of risk and uncertainty
Utility: where the decision involves risk and uncertainty
An overview of the analysis
SMART: Simple Multi-attribute Rating Techique.
The analysis involved is transparent, so the method is likely to yield an enhanced understanding
of the problem and be acceptable to the decision maker who is distrustful of a mathematical
‘black-box’ approach. This, coupled with the relative speed by which the method can be applied,
means that SMART has been found to be a useful vehicle. The cost of this simplicity is that the
method may not capture all the detail and complexities of the real problem. The main stages in
the analysis are shown below:
Stage 1: Identify the decision maker (or decision makers) . In our problem we will assume that
this is just the business owner, but in Chapter 13 we will look at the application of SMART to
problems involving groups of decision makers.
Stage 2: Identify the alternative courses of action . In our problem these are, of course,
represented by the different offices the owner can choose.
Stage 3: Identify the attributes which are relevant to the decision problem . The attributes which
distinguish the different offices will be factors such as rent, size and quality of working conditions.
In the next section we will show how a value tree can be of use when identifying relevant
attributes.
Stage 4: For each attribute, assign values to measure the performance of the alternatives on that
attribute . For example, how well do the offices compare when considering the quality of the
working conditions they offer?
Stage 5: Determine a weight for each attribute . This may reflect how important the attribute is to
the decision maker (though we will discuss the problem of using importance weights later).
Stage 6: For each alternative, take a weighted average of the values assigned to that alternative .
This will give us a measure of how well an office performs over all the attributes.
Stage 7: Make a provisional decision.
Stage 8: Perform sensitivity analysis to see how robust the decision is to changes in the figures
supplied by the decision maker.
Constructing a value tree
Stages 1 and 2 of our analysis have already been completed: we know who the decision maker is
and we have identified the courses of action open to him. The next step is to identify the
attributes which the decision maker considers to be relevant to his problem. we need to arrive at
a set of attributes which can be assessed on a numeric scale.
