CSM 101:

Quantitative Methods
(including Modeling and
Simulation)

MARLON JUHN M. TIMOGAN, MIT

Instructor
 Objectives

1. Explain how modeling and simulation

affects an organization in response to the
development of an organization.

2. Describe the relation of modeling to

simulation in an organization.

2
 Contents

1. Introduction to modelling and

simulation.
2. System analysis, classification of
systems.
3. System theory basics

3
 1 Introduction to
Modeling and
Simulation

4
 Quantitative Methods

▪ People have been using mathematical tools to help

solve problems for thousands of ye ars
▪ The techniques have been applied successfully to an
increasingly wide variety of complex problems in
business, government, health care, education, and
many other areas.

5
 Quantitative Analysis

▪ It isn’t enough, though, just to know the mathematics of how a

particular quantitative technique works.
▪ Other things to consider:
▫ Limitations
▫ Assumptions
▫ specific applicability of the technique

6
 Quantitative Analysis

If the quantitative method is successful, it produces a solution that

is
▫ Timely
▫ Accurate
▫ Flexible
▫ Economical
▫ Reliable
▫ easy to understand and use.
7
 Sample Applications:

▪ Taco Bell has reported saving over $150 million with better
forecasting of demand and better scheduling of employees.
▪ NBC television increased advertising revenue by over $200
million between 1996 and 2000 by using a model to help develop
sales plans for advertisers.
▪ Continental Airlines s a v e s over $40 million per year by using
mathematical models to quickly recover from disruptions
caused by weather delays and other factors.

8
 What is Quantitative
Analysis/Methods?

▪ Quantitative analysis is the scientific approach to managerial

decision making.
▪ The approach starts with data.
▪ The processing and manipulating of raw data into meaningful
information is the heart of quantitative analysis.
▪ Computers have been instrumental in the increasing use of
quantitative analysis.

9
 What is Quantitative
Analysis/Methods?

10
 What is Quantitative
Analysis/Methods?

▪ In addition to quantitative analysis, qualitative factors should

also be considered. The weather, state and federal legislation,
new technological breakthroughs, the outcome of an election,
and so on may all be factors that are difficult to quantify.

11
 What is Quantitative
Analysis/Methods?

▪ In addition to quantitative analysis, qualitative factors should

also be considered. The weather, state and federal legislation,
new technological breakthroughs, the outcome of an election,
and so on may all be factors that are difficult to quantify.

12
 What is Quantitative
Analysis/Methods?

▪ Because of the importance of qualitative factors, the role of

quantitative analysis in the decision-making process can vary.
▪ When there is a lack of qualitative factors and when the
problem, model, and input data remain the same, the results of
quantitative analysis can automate the decision-making
process.

13
 What is Quantitative
Analysis/Methods?

▪ For example, some companies use quantitative inventory

models to determine automatically when to order additional new
materials. In most cases, however, quantitative analysis will be
an aid to the decision-making process. The results of
quantitative analysis will be combined with other (qualitative)
information in making decisions.

14
 Defining a
Problem

Developing a
Model

Acquiring
Input Data

Developing a
Solution

Testing the
Solution

Analyzing the
Results

Implementing
15 the Results
 Quantitative Method
Approach

▪ One step does not have to be finished completely

before the next is started
▪ In most cases one or more of these steps will be
modified to some extent before the final results
are implemented.
▪ This would cause all of the subsequent steps to be
changed.

16
 Quantitative Method
Approach

▪ In some cases, testing the solution might reveal

that the model or the input data are not correct.
▪ This would mean that all steps that follow
defining the problem would need to be modified.

17
 1. Defining a Problem

▪ The first step in the quantitative approach is

to develop a clear, concise statement of the
problem.
▪ This statement will give direction and
meaning to the following steps.
▪ In many cases, defining the problem is the
most important and the most difficult step.

18
 1. Defining a Problem

▪ It is essential to go beyond the symptoms of

the problem and identify the true causes.
▪ It is important to analyze how the solution to
one problem affects other problems or the
situation in general.

19
 1. Defining a Problem

▪ It is likely that an organization will have

several problems. However, a quantitative
analysis group usually cannot deal with all of
an organization’s problems at one time.
▪ Thus, it is usually necessary to concentrate
on only a fe w problems.

20
 1. Defining a Problem

▪ For most companies, this means selecting those

problems whose solutions will result in the
greatest increase in profits or reduction in costs
to the company. The importance of selecting the
right problems to solve cannot be
overemphasized. Experience has shown that bad
problem definition is a major reason for failure
of management science or operations research
21
groups to se rve their organizations well.
 1. Defining a Problem

▪ When the problem is difficult to quantify, it may

be necessary to develop specific, measurable
objectives.
▪ When objectives are used, however, the real
problem should be kept in mind. It is important
to avoid obtaining specific and measurable
objectives that may not solve the real problem.

22
 1. Defining a Problem

▪ A problem might be inadequate health care

delivery in a hospital. The objectives might be to
increase the number of beds, reduce the average
number of days a patient spends in the hospital,
increase the physician-to-patient ratio, and so
on.

23
 2. Developing a Model

▪ Once w e select the problem to be analyzed, the

next step is to develop a model.
▪ Simply stated, a model is a representation
(usually mathematical) of a situation.
▪ Architects sometimes make a physical model of
a building that they will construct. Engineers
develop scale models of chemical plants.

24
 2. Developing a Model

▪ Schematic model - a picture, drawing, or chart

of reality.
▪ Mathematical model - a set of mathematical
relationships. In most cases, these relationships
are expressed in equations and inequalities, as
they are in a spreadsheet model that computes
sums, averages, or standard deviations.

25
 2. Developing a Model

▪ Variable - is a measurable quantity that may

v a r y or is subject to change.
▪ Parameter - a measurable quantity that is
inherent in the problem. The cost of placing an
order for more inventory items is an example of
a parameter.
▫ In most cases, variables are unknown
quantities, while parameters are known
26
quantities..
 2. Developing a Model

▪ All models should be developed carefully. They

should be solvable, realistic, and easy to
understand and modify, and the required input
data should be obtainable.
▪ The model developer has to be careful to include
the appropriate amount of detail to be solvable
yet realistic

27
 3. Acquiring Input Data

▪ Once w e have developed a model, w e must

obtain the data that are used in the model (input
data).
▪ Obtaining accurate data for the model is
essential; even if the model is a perfect
representation of reality, improper data will
result in misleading results. This situation is
called garbage in, garbage out.
28
 3. Acquiring Input Data

▪ For a larger problem, collecting accurate data

can be one of the most difficult steps in
performing quantitative analysis.

29
 3. Acquiring Input Data

▪ company reports and documents

▪ interviews with employees or other persons
related to the firm
▪ Sampling and direct measurement provide other
sources of data for the model

30
 4. Developing a Solution

▪ Developing a solution involves manipulating the

model to arrive at the best (optimal) solution to
the problem. In some cases, this requires that an
equation be solved for the best decision.
▪ In other cases, you can use a trial and error
method, trying various approaches and picking
the one that results in the best decision.

31
 4. Developing a Solution

▪ For some problems, you may wish to try all

possible values for the variables in the model to
arrive at the best decision. This is called
complete enumeration

32
 4. Developing a Solution

▪ The accuracy of a solution depends on the

accuracy of the input data and the model.
▪ If the input data are accurate to only two
significant digits, then the results can be
accurate to only two significant digits.

33
 5. Testing the Solution

▪ Before a solution can be analyzed and

implemented, it needs to be tested completely.
Because the solution depends on the input data
and the model, both require testing.
▪ Testing the input data and the model includes
determining the accuracy and completeness of
the data used by the model.

34
 5. Testing the Solution

▪ One method of testing the data is to collect additional data

from a different source. If the original data were collected
using interviews, perhaps some additional data can be
collected by direct measurement or sampling.
▪ These additional data can then be compared with the
original data, and statistical tests can be employed to
determine whether there are differences between the
original data and the additional data. If there are
significant differences, more effort is required to obtain
accurate input data.
35
 5. Testing the Solution

▪ To help detect both logical and computational mistakes,

you should check the results to make sure that they are
consistent with the structure of the problem.
▪ For example, (1.96)(301.7) is close to (2)(300), which is equal
to 600. If your computations are significantly different
from 600, you know you have made a mistake.

36
 6. Analyzing the Results
and Sensitivity Analysis

▪ Analyzing the results starts with determining the

implications of the solution. In most cases, a solution to a
problem will result in some kind of action or change in the
w a y an organization is operating.
▪ The implications of these actions or changes must be
determined and analyzed before the results are
implemented

37
 6. Analyzing the Results
and Sensitivity Analysis

▪ Sensitivity analysis or Postoptimality analysis - the

sensitivity of the solution to changes in the model and
input data is a v e r y important part of analyzing the
results.
▫ It determines how much the solution will change if
there were changes in the model or the input data.
▫ When the solution is sensitive to changes in the input
data and the model specification, additional testing
should be performed to make sure that the model and
input data are accurate and valid
38
 7. Implementing the
Results

▪ The final step is to implement the results. This is the

process of incorporating the solution into the company.
▪ After the solution has been implemented, it should be
closely monitored. Over time, there may be numerous
changes that call for modifications of the original solution.
▪ A changing economy, fluctuating demand, and model
enhancements requested by managers and decision
makers are only a few examples of changes that might
require the analysis to be modified.

39
 MODELING IN THE
REAL WORLD

40
 1. Defining the Problem

▪ CSX Transportation, Inc., has 35,000 employees and

annual revenue of $11 billion. It provides rail freight
services to 23 states east of the Mississippi River, as well
as parts of Canada. CSX receives orders for rail delivery
service and must send empty railcars to customer
locations. Moving these empty railcars results in
hundreds of thousands of empty-car miles e v e ry day. If
allocations of railcars to customers is not done properly,
problems arise from excess costs, wear and tear on the
system, and congestion on the tracks and at rail yards.
41
 2. Developing a Model

▪ In order to provide a more efficient scheduling system,

CSX spent 2 ye ars and $5 million developing its Dynamic
Car-Planning (DCP) system. This model will minimize
costs, including car travel distance, car handling costs at
the rail yards, car travel time, and costs for being early or
late. It does this while at the same time filling all orders,
making sure the right type of car is assigned to the job,
and getting the car to the destination in the allowable time.

42
 3. Acquiring Input Data

▪ In developing the model, the company used historical data

for testing. In running the model, the DCP uses three
external sources to obtain information on the customer
car orders, the available cars of the type needed, and the
transit-time standards. In addition to these, two internal
input sources provide information on customer priorities
and preferences and on cost parameters.

43
 4. Developing a Solution

▪ This model takes about 1 minute to load but only 10

seconds to solve. Because supply and demand are
constantly changing, the model is run about e v e ry 15
minutes. This allows final decisions to be delayed until
absolutely necessary

44
 5. Testing the Solution

▪ The model w as validated and verified using existing data.

The solutions found using the DCP we re found to be v e ry
good compared to assignments made without DCP.

45
 6. Analyzing the Results

▪ Since the implementation of DCP in 1997, more than $51

million has been saved annually. Due to the improved
efficiency, it is estimated that CSX avoided spending
another $1.4 billion to purchase an additional 18,000
railcars that would have been needed without DCP. Other
benefits include reduced congestion in the rail yards and
reduced congestion on the tracks, which are major
concerns.

46
 6. Analyzing the Results

▪ This greater efficiency means that more freight can ship

by rail rather than by truck, resulting in significant public
benefits. These benefits include reduced pollution and
greenhouse gases, improved highway safety, and reduced
road maintenance costs.

47
 7. Implementing the
Results

▪ Both senior-level management who championed DCP as

well as key car-distribution experts who supported the
new approach were instrumental in gaining acceptance of
the new system and overcoming problems during the
implementation. The job description of the car distributors
w a s changed from car allocators to cost technicians.

48
 7. Implementing the
Results

▪ They are responsible for seeing that accurate cost

information is entered into DCP, and they also manage any
exceptions that must be made. They were given extensive
training on how DCP works so they could understand and
better accept the new system. Due to the su c c e s s of DCP,
other railroads have implemented similar s y s t e ms and
achieved similar benefits. CSX continues to enhance DCP
to make DCP even more customer friendly and to improve
car-order forecasts.

49
 How to Develop a
Quantitative Analysis Model

50
 Quantitative Analysis
Model

▪ Developing a model is an important part of the

quantitative analysis approach
▪ Look at a simple mathematical model of profit

Profit = Revenue – Expenses

51
 Quantitative Analysis
Model

▪ Expenses can be represented as the sum of fixed and

variable costs and variable costs are the product of unit
costs times the number of units
Profit = Revenue – (Fixed cost + Variable cost)
Profit = (Selling price per unit)(number of units 1 – 22 sold) –
[Fixed cost +(Variable costs per unit)(Number of units sold)]
Profit = sX – [f + vX]
Profit = sX – f – vX
where s = selling price per unit v = variable cost per unit f =
52
fixed cost X = number of units sold
 Quantitative Analysis
Model

▪ The parameters of this model are f, v, and s as these are

the inputs inherent in the model
▪ Profit and X are variables
▪ The decision variable of interest is X

53
 Example

▪ PRITCHETT’S PRECIOUS TIME PIECES

We will use the Bill Pritchett clock repair shop example to
demonstrate the use of mathematical models. Bill’s
company, Pritchett’s Precious Time Pieces, buys, sells,
and repairs old clocks and clock parts. Bill sells rebuilt
springs for a price per unit of $10. The fixed cost of the
equipment to build the springs is $1,000. The variable
cost per unit is $5 for spring material. In this example,

54
 Example

▪ s =5 ; f = 1,000; v =5
▪ Let X = number of springs sold

Profit = $10X - $1,000 - $5X

If sales are zero, Bill will have $ loss

If sales are 1,000 units, the profit is $

55
 BEP

▪ In addition to the profit models shown here, decision

makers are often interested in the break-even point
(BEP). The BEP is the number of units sold that will
result in $0 profits. We set profits equal to $0 and
solve for X, the number of units at the break-even
point:
0 = sX - f - vX

56
 BEP

▪ This quantity (X) that results in a profit of zero is the

BEP, and w e now have this model for the BEP: (1-2) For
the Pritchett’s Precious Time Pieces example, the BEP
can be computed as follows:
Fixed cost
BEP = Selling price per unit – Variable cost unit
f
BEP = s - v

57
 ▪ Ray Bond sells handcrafted yard decorations at
county fairs. The variable cost to make these is $20
each, and he sells them for $50. The cost to rent a
booth at the fair is $150. How many of these must Ray
sell to break even?

58
 ▪ Katherine D’Ann is planning to finance her college
education by selling programs at the football games
for State University. There is a fixed cost of $400 for
printing these programs, and the variable cost is $3.
There is also a $1,000 fee that is paid to the university
for the right to sell these programs. If Katherine w a s
able to sell programs for $5 each, how many would
she have to sell in order to break even?

59
 Mathematical Models
Categorized by Risk

▪ Some mathematical models, like the profit and break-

even models previously discussed, do not involve risk
or chance. We assume that w e know all values used in
the model with complete certainty. These are called
deterministic models.
▪ A company, for example, might want to minimize
manufacturing costs while maintaining a certain
quality level. If w e know all these values with
certainty, the model is deterministic.

60
 Mathematical Models
Categorized by Risk

▪ Other models involve risk or chance. For example, the

market for a new product might be “good” with a
chance of 60% (a probability of 0.6) or “not good” with
a chance of 40% (a probability of 0.4).
▪ Models that involve chance or risk, often measured as
a probability value, are called probabilistic models.

61
 Advantages of Mathematical
Modeling

62
 Advantages of
Mathematical Modeling

1. Models can accurately represent reality. If properly

formulated, a model can be extremely accurate. A valid
model is one that is accurate and correctly represents
the problem or system under investigation. The profit
model in the example is accurate and valid for many
business problems.

63
 Advantages of
Mathematical Modeling

2. Models can help a decision maker formulate problems.

In the profit model, for example, a decision maker can
determine the important factors or contributors to
revenues and expenses, such as sales, returns, selling
expenses, production costs, transportation costs, and so
on.

64
 Advantages of
Mathematical Modeling

3. Models can give us insight and information. For

example, using the profit model from the preceding
section, w e can see what impact changes in revenues
and expenses will have on profits. As discussed in the
previous section, studying the impact of changes in a
model, such as a profit model, is called sensitivity
analysis

65
 Advantages of
Mathematical Modeling

4. Models can save time and money in decision making

and problem solving. It usually takes less time, effort,
and expense to analyze a model. We can use a profit
model to analyze the impact of a new marketing
campaign on profits, revenues, and expenses. In most
cases, using models is faster and less expensive than
actually trying a new marketing campaign in a real
business setting and observing the results

66
 Advantages of
Mathematical Modeling

5. A model may be the only w a y to solve some large or

complex problems in a timely fashion. A large company,
for example, may produce literally thousands of sizes of
nuts, bolts, and fasteners. The company may want to
make the highest profits possible given its
manufacturing constraints. A mathematical model may
be the only way to determine the highest profits the
company can achieve under these circumstances.

67
 Advantages of
Mathematical Modeling

6. A model can be used to communicate problems and

solutions to others. A decision analyst can share his or
her work with other decision analysts. Solutions to a
mathematical model can be given to managers and
executives to help them make final decisions.

68
 Possible Problems in
Quantitative Methods
Approach

69
 Defining the Problem

CONFLICTING VIEWPOINTS
For example, there are at least two views that
managers take when dealing with inventory problems.
Financial managers usually feel that inventory is too
high, as inventory represents cash not available for
other investments. Sales managers, on the other hand,
often feel that inventory is too low, as high levels of
inventory may be needed to fill an unexpected order.

70
 Defining the Problem

IMPACT ON OTHER DEPARTMENTS

A change in ordering policy can seriously hurt
cash flows and upset production schedules to the point
that savings on inventory are more than offset by
increased costs for finance and production.
The problem statement should thus be as broad as
possible and include input from all departments that
have a stake in the solution.

71
 Defining the Problem

BEGINNING ASSUMPTIONS
The third difficulty is that people have a tendency
to state problems in terms of solutions. The statement
that inventory is too low implies a solution that inventory
levels should be raised

72
 Defining the Problem

SOLUTION OUTDATED
The problem can change as the model is being
developed. The analyst who presents a solution to a
problem that no longer exists can’t expect credit for
providing timely help.

73
 Developing a problem

UNDERSTANDING THE MODEL

A second major concern involves the trade-off
between the complexity of the model and ease of
understanding. Managers simply will not use the results
of a model they do not understand. Complex problems,
though, require complex models.

74
 Acquiring Input Data

USING ACCOUNTING DATA

One problem is that most data generated in a firm
come from basic accounting reports. The accounting
department collects its inventory data, for example, in
terms of cash flows and turnover

75
 Acquiring Input Data

VALIDITY OF DATA
A lack of “good, clean data” means that whatever
data are available must often be distilled and
manipulated (we call it “fudging”) before being used in a
model. Unfortunately, the validity of the results of a
model is no better than the validity of the data that go
into the model.

76
 Developing a Solution

VALIDITY OF DATA
A lack of “good, clean data” means that whatever
data are available must often be distilled and
manipulated (we call it “fudging”) before being used in a
model. Unfortunately, the validity of the results of a
model is no better than the validity of the data that go
into the model.

77
 Developing a Solution

HARD-TO-UNDERSTAND MATHEMATICS
The first concern in developing solutions is that
although the mathematical models w e use may be
complex and powerful, they may not be completely
understood.

78
 Developing a Solution

ONLY ONE ANSWER IS LIMITING

The second problem is that quantitative models
usually give just one answer to a problem. Most
managers would like to have a range of options and not
be put in a take-it-or-leave-it position.
This gives managers a choice as well as
information on how much it will cost to deviate from the
optimal solution. It also allows problems to be viewed
from a broader perspective, since nonquantitative
factors can be considered.
79
 Testing the Solution

The problem is that complex models tend to give

solutions that are not intuitively obvious. Such solutions
tend to be rejected by managers. The quantitative analyst
now has the chance to work through the model and the
assumptions with the manager in an effort to convince
the manager of the validity of the results.

80
 Analyzing the Results

Once a solution has been tested, the results must be

analyzed in terms of how they will affect the total
organization. You should be aware that even small
changes in organizations are often difficult to bring
about. If the results indicate large changes in
organization policy, the quantitative analyst can expect
resistance.

81
 Implementation

Lack of Commitment and Resistance to Change

▪ Some managers fear that the use of a formal analysis
process will reduce their decision-making power.
▪ Others fear that it may expose some previous
intuitive decisions as inadequate.
▪ Still others just feel uncomfortable about having to
reverse their thinking patterns with formal decision
making.

82
 Implementation

Lack of Commitment by Quantitative Analysts

▪ Just as managers’ attitudes are to blame for some
implementation problems, analysts’ attitudes are to
blame for others.
▪ That is, the analyst accepts the problem as stated by
the manager and builds a model to solve only that
problem.
▪ When the results are computed, he or she hands
them back to the manager and considers the job done.
83
 Implementation

Lack of Commitment by Quantitative Analysts

▪ The analyst who does not care whether these results
help make the final decision is not concerned with
implementation

84
 One half sheet of paper

85
 Answer the following in
your own words

1. What is the difference between quantitative and

qualitative analysis? Give several examples for
each
2. Define quantitative methods.
3. What is a mathematical model?
4. List some sources of input data.

86