MGMT Science Notes 01 Introduction
MGMT Science Notes 01 Introduction
AE 232: MANAGEMENT SCIENCE: Summary Notes and Exercises: Quantitative Analysis Process
A. Midterms The quantitative analysis process includes the steps of model development,
data preparation, model solution and report generation. However, other
UNIT 1: Introduction to and Overview of Management Science steps that are included on a case‐to‐case basis are the model testing and
Management Science as a Body of Knowledge validation, and implementation and follow‐up. Including these additional
Management science steps, the quantitative analysis process steps are summarized as follows: (1)
• an approach to decision making based on the scientific model development, (2) data preparation, (3) model solution, (4) model
method testing and validation, (5) report generation, and (6) implementation and
• makes extensive use of quantitative analysis follow‐up.
• also referred to as Operations research and Decision science 1. Model Development
• It had its early roots in World War II and is flourishing in Models are representations of real objects or situations.
business and industry with the aid of computers. Generally, experimenting with models (compared to
Problem Solving and Decision Making experimenting with the real situation):
7 Steps of Problem Solving a. requires less time
1. Define the problem. b. is less expensive
2. Identify the set of alternative solutions. c. involves less risk
3. Determine the criteria for evaluating alternatives. The three forms of models are:
4. Evaluate the alternatives. a. Iconic models ‐ physical replicas (scalar
5. Choose an alternative (make a decision). representations) of real objects
6. Implement the chosen alternative. b. Analog models ‐ physical in form, but do not
7. Evaluate the results. physically resemble the object being modeled
• The first five steps in problems solving are actually the c. Mathematical models ‐ represent real world
process of decision making. Decision making is a large part problems through a system of mathematical
of problem solving. formulas and expressions based on key
Quantitative Analysis and Decision Making assumptions, estimates, or statistical analyses
Potential Reasons for a Quantitative Analysis Approach to More on Mathematical Models (MM):
Decision Making Cost/benefit considerations must be made in selecting an
The problem is complex. appropriate mathematical model.
The problem is very important. MMs must relate decision variables (controllable inputs) with fixed
The problem is new. or variable parameters (uncontrollable inputs).
The problem is repetitive. MMs frequently seek to maximize or minimize some objective
function subject to constraints.
1
AE 232: Management Science Short‐term 2019‐2020
MMs are said to be stochastic (or probabilistic) if any of the 3. Model Solution
uncontrollable inputs is subject to variation, otherwise are said to The analyst attempts to identify the alternative (the set of decision
be deterministic. variable values) that provides the “best” output for the model.
o Generally, stochastic models are more difficult to analyze. The “best” output is the optimal solution.
The values of the decision variables that provide the If the alternative does not satisfy all of the model constraints, it is
mathematically‐best output is referred to as the optimal solution for rejected as being infeasible, regardless of the objective function
the model. value.
Frequently a less complicated (and perhaps less precise) model is If the alternative satisfies all of the model constraints, it is feasible
more appropriate than a more complex and accurate one due to and a candidate for the “best” solution.
cost and ease of solution considerations. One solution approach is trial‐and‐error.
o Might not provide the best solution
o Inefficient (numerous calculations required)
Special solution procedures have been developed for specific
mathematical models.
o Some small models/problems can be solved by hand
calculations
o Most practical applications require using a computer
4. Model Testing and Validation
Often, goodness/accuracy of a model cannot be assessed until
solutions are generated.
Small test problems having known, or at least expected, solutions
can be used for model testing and validation.
Figure 1. Illustration of how mathematical models transform inputs to outputs. Source: If the model generates expected solutions, use the model on the
Anderson et al (2003).
full‐scale problem.
If inaccuracies or potential shortcomings inherent in the model are
2. Data Preparation
identified, take corrective action such as:
Data preparation is not a trivial step, due to the time required and
o Collection of more‐accurate input data
the possibility of data collection errors.
o Modification of the model
Often, a fairly large data base is needed.
Information systems specialists might be needed.
2
AE 232: Management Science Short‐term 2019‐2020
5. Report Generation
A managerial report, based on the results of the model, should be
prepared.
The report should be easily understood by the decision maker.
The report should include:
o the recommended decision
o other pertinent information about the results (for example,
how sensitive the model solution is to the assumptions and
data used in the model)
6. Implementation and Follow‐up
Successful implementation of model results is of critical importance.
Secure as much user involvement as possible throughout the
modeling process.
Continue to monitor the contribution of the model.
It might be necessary to refine or expand the model.
3