Week 1 - Chapter 1

Quantitative analysis is the scientific approach to managerial decision making. Subjective not objective analysis. The approach starts with data which is processed into a meaningful form.

Quantitative vs. Qualitative factors.

Quantitative: interest rates, real estate market, stocks, current trends, etc.

Qualitative: weather, next election results, future legislation, new tech. breakthroughs, competition, etc.

Scope of OM is across an organization. We can use an airline company to illustrate a service organization’s operations system. The system consists of the airplanes, airport facilities, and maintenance facilities, sometimes spread out over a wide territory. Most of the activities performed by management and employees fall into the realm of operations management:

  • Forecasting such things as weather and landing conditions, seat demand for flights, and the growth in air travel.
  • Capacity planning, essential for the airline to maintain cash flow and make a reasonable profit. (Too few or too many planes, or even the right number of planes but in the wrong places, will hurt profits.)
  • Scheduling of planes for flights and for routing maintenance; scheduling of pilots and flight attendants; and scheduling of ground crews, counter staff, and baggage handlers.
  • Managing inventories of foods and beverages, first-aid equipment, in-flight magazines, life preservers.
  • Assuring quality – safety, customers at ticket counters, check-in, electronic reservations, curb service
  • Locating facilities according to managers’ decisions on which cities to provide service for, where to locate maintenance facilities, and where to locate major and minor hubs.

The Quantitative Analysis Approach:

  1. Define problem
  2. Some problems are difficult to quantify in which case break down to smaller goals
  3. Develop model
  4. Acquire input data
  5. To use in model
  6. GIGO – improper data produces useless results
  7. Collecting accurate data is difficult!
  8. Develop a solution
  9. Algorithm – sequence of steps to accomplish a goal
  10. Accuracy depends on input data and model used
  11. Mathematical models may not be understood; do not present a range of options.
  12. Test the solution
  13. Review assumptions
  14. Analyze the results
  15. Inertia – people resist change
  16. Implement the results
  17. There may be changes over time that require modification of the model or solution
  18. User involvement (and support) is critical
  19. May need to let users feel like they are still in control as processes are automated.

Goods – tangible outputThese two kinds of businesses are very similar in design and

Services – perform act decision processes.

Purpose of analysis is to transform business’s input into more valuable output. Most decisions involve many alternatives that can have quite different impacts on costs or profits. Consequently, it is important to make informed decisions.

Gathering accurate data:

convenience samples and voluntary response samples (polls) are often biased so need random samples – can pick numbers out of a hat or use a pseudo-random number generator (results can be predicted since computer program) i.e., people at risk of losing their jobs might keep calling, top of each crate of oranges might have the best juice.

Wording questions - a few words make a big difference!

Cartoon depicting unusual results “A national survey, commissioned especially for the tobacco industry, found that a majority of Americans do NOT support more restrictive anti-smoking measures!”… “Do you favor Gestapo-style police tactics to prevent smoking in public?”

Non-response should not be excluded!

Knowing whom to believe:

A study of deaths in bar fights showed that in 90% of the cases, the person who died started the fight. Should you believe this? If you killed someone in a fight, what would you say when the police ask you who started the fight? After all, dead men tell no tales. How’s that for non-response?!

Some questions to ask before paying much attention to poll results:

  • Who carried out the survey?
  • What was the population?
  • How was the sample selected?
  • How large was the sample?
  • What was the response rate?
  • How were the subjects contacted?
  • When was the survey conducted?
  • What were the exact questions asked?

Report that students do better online than in traditional classroom? Should colleges believe the results? After all it will save them a lot of money? Perhaps only students who will thrive in the online environment chose to take online sections?

People tend to behave differently when observed, i.e., observe class during test to find cheating

Managerial decision makers decide for the organization:

What: What resources will be needed and in what amounts?

When: When will each resource be needed? When should the work be scheduled? When should materials and other supplies be ordered? When is corrective action needed?

Where: Where will the work be done?

How: How will the product or service be designed? How will the work be done (organization, methods, equipment)? How will resources be allocated?

Who: Who will do the work?

Historical Perspective

Industrial Revolution – 1800’s

  • factory system
  • mass production
  • machines replace manual labor.

Scientific Management era - early 1900’s; brought widespread changes to the management of factories.

  • Frederick W. Taylorreferred to as the father of scientific management
  • Wrote book called “The Principles of Scientific Management”.
  • Analysis by observationtowards improvement of work methods, efficiency
  • separation between management and work activities
  • emphasized maximizing output. His ideas were not always popular with workers, who sometimes thought the methods were used to unfairly increase output without a corresponding increase in compensation. Certainly some companies did abuse workers in their quest for efficiency.
  • Frank Gilbreth
  • Cheaper By The Dozen
  • industrial engineer who is often referred to as the father of motion study
  • analyzed incredibly (comically so) small portions of a task to reduce motions expended.
  • Henry Ford
  • scientific management of his factories
  • moving assembly line
  • interchangeable parts
  • division of labor (implemented Adam Smith’s idea in “The Wealth of Nations”) - many small tasks requiring no skill replace skilled workers.

The factory movement was accompanied by the development of several quantitative techniques.

  • F.W. Harris developed one of the first quantitative models in 1915: a mathematical model for inventory management.
  • In the 1930’s, three coworkers at Bell Telephone Labs developed statistical procedures for sampling and quality control.
  • In 1935, Tippett conducted studies that provided the groundwork for statistical sampling control.

Until WWII, these quantitative models were not widely used in industry. The war generated tremendous pressures on manufacturing output, and specialists from many disciplines combined efforts to develop and refine quantitative tools for decision making continued, resulting in decision models for forecasting, inventory management, project management, and other areas of operations management.

During the 1960’s and 1970’s, management science techniques were highly regarded. The widespread use of PC’s and user-friendly software in the workplace contributed to a resurgence in the popularity of these techniques. Japanese products became competitive in US since the manufacturers developed or refined management practices that increased the productivity of their operations and the quality of their products.

Acceptance of quantitative approaches to decision making can be attributed to the proliferation of calculators and high-speed computers capable of handling the required calculations.

Models

A model is an abstraction of reality. Models are all decision-making tools and simplifications of more complex real-life phenomena. Real life involves an overwhelming amount of detail, much of which is irrelevant for any particular problem. Models omit unimportant details so that attention can be concentrated on the most important aspects of a situation.

For example, a child’s toy car is a model of a real automobile. It has many of the same visual features (shape, relative proportions, wheels) that make it suitable for the child’s learning and playing. But the toy does not have a real engine, it cannot transport people, and it does not weigh 2,000 pounds. We learn geography with the visual aid of a globe. The MTA route map shows routes we can travel without taking us anywhere.

Other examples of models include automobile test tracks and crash tests; simulated aircraft flights; formulas, graphs and charts; balance sheets and income statements; and financial ratios.

Models are sometimes classified as physical, schematic, or mathematical:

Physical models look like their real life counterparts. Examples include miniature cars, toy animals, and scale-model buildings. The advantage of these models is their correspondence with reality.

Schmatic models are more abstract. Examples include graphs and charts, blueprints, pictures and drawings. The advantage of schematic models is that they are often relatively simple to construct and change. Moreover, they have some degree of visual correspondence.

Mathematical models are the most abstract: they do not look at all like their real-life counterparts. Generally a set of mathematical relationships. These models are usually the easiest to manipulate, and they are important forms of input for computers (i.e., spreadsheets) and calculators. Common statistical models include descriptive statistics such as the mean, median, mode, range, and standard deviation.

Most mathematical models contain variables – measurable quantities that decision maker can change (unknown). Controlled/decision variables vs. uncontrolled variables.

There are also parameters – measurable quantities that are inherent to the problem (known)

For each model we need to distinguish:

Its purpose

Proper use

Interpretation of results

Assumptions and limitations

Examples of constraints: there needs to exist an air flight between 2 cities; a gift needs to arrive before Christmas

Models are beneficial because they

  1. Are generally easy to use and less expensive than dealing directly with the actual situation.
  2. Require users to organize and sometimes quantify information and, in the process, often indicate areas where addition information is needed.
  3. Increase understanding of a problem.
  4. Enable managers to analyze “What if” questions.
  5. Serve as a consistent tool for evaluation and provide a standardized format for analyzing a problem.
  6. Enable users to bring the power of mathematics to bear on a problem.

Limitations of models:

  1. Quantitative info. may be emphasized at the expense of qualitative info.
  2. May be incorrectly applied and be misinterpreted. The widespread use of computerized models adds to this risk because highly sophisticated models may be placed in the hands of users who are not sufficiently knowledgeable to appreciate the subtleties of a particular model; thus, they are unable to fully comprehend the circumstances under which the model can be successfully employed. That is why our lectures will focus on the theory of how these models should be used.
  3. The use of models does not guarantee good decisions.

Mathematical models can be split into two categories (we will see some of each during the semester):

Deterministic models – we are certain of values used.

Probabilistic/stochastic models – involve chance or risk

Analysis of trade-offs: merits of extra features relative to their cost (i.e., as scheduling of overtime to increase output vs. the higher costs of overtime) Decision makers sometimes deal with these decisions by listing the advantages and disadvantages of a course of action to better understand the consequences of the decisions they must make. In some instances, weights are added to reflect the relative importance of various factors.

A business organization can be thought of as a system composed of subsystems. The systems approach emphasizes interrelationships among subsystems, but its main theme is that the whole is greater than the sum of its individual parts. So the output and objectives of the organization as a whole take precedence over those of any one subsystem. An alternative approach is to concentrate on efficiency within subsystems and thereby achieve overall efficiency. But that approach overlooks the fact that organizations must operate in an environment of scarce resources and that subsystems are often in direct competition for those scarce resources, so that an orderly approach to the allocation of resources is called for.

Developing a QA Model

Productivity = output/ input

a)Machine produced 68 usable pieces in 2 hours => productivity=34 usable pieces/hour

b)72 square feet of carpet installed by 4 people in 3 hours in 8 hours => productivity= 6 sq. ft./ man hour

Profits = Revenue – Expenses

= Revnue – (fixed cost + variable cost)

= (selling price per unit)(number of units sold) – [fixed cost + (variable cost per unit)(number of units sold)]

Profits = sX – (f +vX)

Profits = sX – f –vX

Parameters:

s = selling price per unit

f = fixed cost

v = variable cost per unit

Variables:

X = number of units sold

Break-even point (BEP) is the number of units sold that result in $0 profits.

Solve the equation:

0 = sX – f – vX

0 = (s-v)X – f

BEP = X = f/(s-v)

Example: Mark’s dry cleaners purchases equipment for a fixed cost of $1200. The variable cost of cleaning a sports jacket is $2. Mark charges $5 to clean a jacket. In this example, s = 5, f = 1250, v = 2

Profits = 5X – 1200 – 2X

= 3X – 1200

If sales are 0 units, there is a $1200 loss; if sales are 500 units, there is $300 in profits

BEP = 1200 / (5-2) = 400 units

Example from book 1-14:

Gina Fox has started her own company, Foxy Shirts, which manufactures imprinted shirts for special occasions. Since she has just begun this operation, she rents the equipment from a local printing shop when necessary. The cost of using the equipment is $350. The material used in one shirt is $8, and Gina can sell these for $15 each.

a)If Gina sells 20 shirts, what will her total revenue be? What will her total variable cost be?

b)How many shirts must Gina sell to break even? What is the total revenue for this?

1-14. f = 350 s = 15 v = 8

a) Total revenue = 20(15) = $300

Total variable cost = 20(8) = $160

b) BEP = f/(s - v) = 350/(15 - 8) = 50 units

Total revenue = 50(15) = $750

Homework

Chapter 1

1-17, 1-18, 1-19, 1-20, 1-21

Hand in a printout of the spreadsheet results using QM for Windows.

1-17. f = 400 + 1,000 = 1,400 s = 5 v = 3

BEP =f/(s -v) = 1400/(5 - 3) = 700 units

1-18. BEP =f/(s -v)

500 = 1400/(s - 3)

500(s - 3) = 1400

s - 3 = 1400/500

s = 2.8 + 3

s = $5.80

1-19. f = 2400 s = 40 v = 25

BEP =f/(s -v) = 2400/(40 - 25) = 160 per week

Total revenue _ 40(160) _ 6400

1-20. f = 2400 s = 50 v = 25

BEP =f/(s -v) = 2400/(50 - 25) = 96 per week

Total revenue = 40(96) = 4800

1-21. f = 2400 s = ? v = 25

BEP =f/(s -v)

120 = 2400/(s - 25)

120(s - 25) = 2400

s = 45