DECISION MAKING THEORY

1
DECISION MAKING THEORY

• Implications for Academic Advising
• Tina Brazil (TAB291_at_gmail.com)
• Jim Levin (JL7_at_psu.edu)

2
Importance Curriculum of Academic Advising

• Academic Advising .. This curriculum includes
  .. decision-making .. (NACADA, 2006).
• use complex information . reach decisions
  (NACADA, 2006).

3
Definition

• Rational decisions are ones that advances the
  welfare of the decision maker effectively and
  logically based on everything the decision maker
  knows and feels (Brown, 2005, p. 54)
• Criteria for rational decisions (Hastie Dawes,
  2001, p.18)
• It is based on the decision makers current
  assets. Assets include not only money, but
  physiological state, psychological capacities,
  social relationships, and feelings.
• It is based on the possible consequences of the
  choice.
• When these consequences are uncertain, their
  likelihood is evaluated according to the basic
  rules of probability theory.
• It is a choice that is adaptive within the
  constraints of those probabilities and the values
  or satisfactions associated with each of the
  possible consequences of choice.

4
Problems with Qualitative Decision Making Methods

• Heuristics speculative formulation serving as a
  guide in the investigation or solution of a
  problem (Keren and Teigen, 2004)
• Representation bias decision making by
  recalling a memory or experience that is similar
  to the present decision making experience
• Availability bias decision making by the primacy
  and/or by predicting easily conceivable
  outcomes
• Anchor adjustment bias decision making by what
  is familiar and conceivable

5
Models

• Goals, Options and Outcomes (GOO)
• The Personalist Approach
• Lens Model
• Simple Utility Equation
• Additive Linear Multi-Attribute Utility Theory
  (MAUT)

6
Definition of Utility

• The consumption utility of an option is broadly
  defined here as the benefit the option delivers.
  (Hsee, 1999, p. 555)
• Furthermore, it is assumed that the decision
  maker should choose the option that delivers the
  greatest utility or benefit. (Hsee, 1999)
• When making decisions, we think about what option
  will derive the highest utility. (Hastie and
  Dawes, 2001, p. 200)

7
Goals, Options, and Outcomes

• What do I want? (goals)
• What can I do? (options)
• What might happen? (outcomes) (Brown, 2005, p. 9)
• In Practice
• Goals options can be listed
• Difficult to predict outcomes
• Quantitative methods can be used (simple
  probability theory)
• Research indicates that quantitative methods
  predict outcomes better than qualitative methods
  (Hastie Dawes, 2001)

8
The Personalist Approach(first approximation of
quantifiable decision making
Fig 1. The pluses and minuses are assigned on an
arbitrary scale decided by the decision maker.
(Brown, 2005)
9
Lens Model Concept

• The decision maker is trying to see a distal
  true state of something through a proximal lens
  of cues. These cues represent information or
  characteristics that the decision maker uses to
  make a decision (Hastie and Dawes, 2001)
• An algebraic model of probability that measures
  and assigns a scaled weight to the importance of
  each piece of information (cue) available to the
  decision maker (Hastie and Dawes, 2001)
• Research experts correctly select variables
  that are important in making predictions, but
  that a probability model combines these variables
  in a way that is superior to the global
  judgments of these very same experts. (Hastie
  and Dawes, 2004, p. 58)
• Probability models have been derived from the
  Lens Model Concept.

10
Simple Utility Equation

• Decision tree in which each option represents a
  major branch, and from each branch stems the
  possible outcomes. Each of these outcomes is
  assigned a specific quantitative probability so
  that the sum of the outcomes stemming from one
  choice adds up to 1, or 100. The probability
  for each outcome is multiplied by an assigned
  number that represents how the decision maker
  would feel about that outcome (Hastie and Dawes,
  2001)
• Utility S (probabilityoutcome x valueoutcome)

11
Simple Utility Equation
Value prob x value utility -100
-.3
.4 100 .7 -100 -.8
-.6 100
.2
study
fail .3
pass .7
fail .8
pass .2
play
Figure 2. Here, the two options are study and
play. In this case, the utility of option
study has a much higher utility value to the
decision maker than does play. Utility S
(probabilityoutcome x valueoutcome)
12
Additive Linear Multi-Attribute Utility Theory
(MAUT)

• MAUT weighs all of the attributes and scales the
  attributes by importance to the decision maker.
  Each option is considered by assigning a scaled
  value to that option-attribute, according to its
  importance, and then adding up all of the scaled
  option-attributes to obtain the utility value for
  that option (Hastie and Dawes, 2001)

13
Example of MAUT

• To predict the probability of a student
  graduating from ENGR, Dr. James Levin constructed
  a probability model (logic regressions) that used
  several quantitative and qualitative (which were
  quantified) student criteria as inputs, assigned
  a scaled value to each criterion, and produced an
  output that gave the probability of that student
  graduating from ENGR. (Levin Wyckoff, 1998)
• Similar models are in progress for SC (Levin,
  2007)

14
Additive Linear Multi-Attribute Utility Theory
(MAUT) ENGINEERING

• Grad Engr/Not Grad Engr -3.8 -.02 x 10 (nspts)
  -.01 x 520(satv) .69 x 3.00(hsgpa) .08 x
  25(alg) .07 x 12(chem-s) .28 x 1(reas-g) .20
  x 1(gen) .236
• Odds of Grad Engr/Not Grad Engr e.236
  2.72.236 1.27/1
• Probability 1.27/2.27 56

15
MAUT Example SC
16
MAUT Example cont SC
17
References

• Brown, Rex, Rational Choice and Judgment
  Decision Analysis for the Decider, John Wiley
  Sons, Inc., Hoboken, New Jersey, 2005.
• Hastie, Reid and Robyn M. Dawes, Rational Choice
  in an Uncertain World The Psychology of Judgment
  and Decision Making, Sage Publications, Thousand
  Oaks, California, 2001.
• Hsee, Christopher K. (1999). Value Seeking and
  Prediction-Decision Inconsistency Why Dont
  People Take What They Predict Theyll Like the
  Most? Psychonomic Bulletin Review, 6 (4),
  555-561.
• Keren, Gideon and Karl H. Teigen, Yet Another
  Look at the Heuristics and Biases Approach.
  Blackwell Handbook of Judgment and Decision
  Making, Blackwell Publishing Ltd., Malden, MA,
  2004.
• Levin, James and Wykoff, Jack,(1998). Effective
  Advising Identifying Students Most Likely to
  Persist and Succeed in Engineering. Engineering
  Education, 75(11), 178-182.
• Levin, James, (2007). Effective Advising
  Identifying Students Most Likely to Persist and
  Succeed in Science in progress.
• NACADA National Academic Advising Association.
  (2006). NACADA concept of academic advising.
  Retrieved 5/2/07 from http//www.nacada.ksu.edu/Cl
  earinghouse/AdvisingIssues/Concept-Advising.htm