This document provides an overview of statistics and their applications in business decision making. It discusses why statistics are important for managers to make informed decisions using all relevant data. Statistical methods allow companies to collect, analyze, and interpret market data to aid decision making. The document also covers key statistical concepts like descriptive and inferential statistics, data types and measurements, sources of data, and common statistical terms. It provides examples of how companies like American Express have benefited from applying statistical analysis to customer feedback data.
3. Introduction
Managers make sound decisions when they use allManagers make sound decisions when they use all
relevant information in an effective and meaningfulrelevant information in an effective and meaningful
manner. The principal purpose of statistics is tomanner. The principal purpose of statistics is to
provide decisionprovide decision--makers with a set of techniquesmakers with a set of techniques
for collecting, analyzing, and interpreting data intofor collecting, analyzing, and interpreting data into
actionable recommendations. Statistical methodsactionable recommendations. Statistical methods
are widely used to aid decisionare widely used to aid decision--makers in allmakers in all
functional areas of management. This chapterfunctional areas of management. This chapter
provides the basic ideas and concepts at a generalprovides the basic ideas and concepts at a general
level.level.
4. 1) Why Should I Study
Statistics?
Situation 1Situation 1
A company has to decide whether to introduce a new productA company has to decide whether to introduce a new product
into the market or not. The company will introduce the productinto the market or not. The company will introduce the product
into the market if 30% of the target audience in the relevantinto the market if 30% of the target audience in the relevant
population will accept the product so that the risk of productpopulation will accept the product so that the risk of product
failure is minimized. Obviously consumer acceptance isfailure is minimized. Obviously consumer acceptance is
paramount in making this decision. To know about theparamount in making this decision. To know about the
consumer acceptance in a reasonable manner, the company hasconsumer acceptance in a reasonable manner, the company has
done a "test marketing" exercise. In the test market, 30% ofdone a "test marketing" exercise. In the test market, 30% of
the sample target audience (based on a sample of 150the sample target audience (based on a sample of 150
consumers) indicate their acceptance of the product. Does theconsumers) indicate their acceptance of the product. Does the
sample result at 95% confidence level suggest that 30% of thesample result at 95% confidence level suggest that 30% of the
target audience in the population (entire market) will accept thtarget audience in the population (entire market) will accept thee
product?product?
5. 1) Why Should I Study
Statistics? Continues
Situation 2Situation 2
A bank which has been steadily losing customers in the lightA bank which has been steadily losing customers in the light
of intense competition wants to investigate the reasons forof intense competition wants to investigate the reasons for
the loss of customers on account of perceived service qualitythe loss of customers on account of perceived service quality
in critical dimensions like response time, reliability, courtesyin critical dimensions like response time, reliability, courtesy
of the service staff, and credibility. The bank would like toof the service staff, and credibility. The bank would like to
conduct a comprehensive survey to measure the perceivedconduct a comprehensive survey to measure the perceived
service quality from the customers' angle on theseservice quality from the customers' angle on these
dimensions with that of competition. This would help thedimensions with that of competition. This would help the
bank develop and implement effective strategies to woo itsbank develop and implement effective strategies to woo its
present customers back as well as to attract new customers.present customers back as well as to attract new customers.
6. 1) Why Should I Study
Statistics? Continues
Can you make the right decision in situation 1 andCan you make the right decision in situation 1 and
situation 2 with minimum risk without the help ofsituation 2 with minimum risk without the help of
statistics? The answer is clearly a "No". Informationstatistics? The answer is clearly a "No". Information
based decision making using statistical analysis isbased decision making using statistical analysis is
absolutely essential in the present environmentabsolutely essential in the present environment
characterized by intense competition, onslaught of newcharacterized by intense competition, onslaught of new
products and services, globalization, and revolution ofproducts and services, globalization, and revolution of
information technology.information technology.
7. 2 ) What is Statistics?
By "Statistics"By "Statistics" we mean methods speciallywe mean methods specially
adapted to theadapted to the collectioncollection,, classificationclassification,,
analysisanalysis,, andand interpretationinterpretation of data forof data for
making effective decisions in all functionalmaking effective decisions in all functional
areas of management.areas of management.
8. AMEX Gained by Statistical Analysis
American Express Company (AMEX), the pioneer in personalAmerican Express Company (AMEX), the pioneer in personal
charge cards during the eighties used to systematically collectcharge cards during the eighties used to systematically collect
customer feedback data from the marketplace on a continuouscustomer feedback data from the marketplace on a continuous
basis. AMEX is well known for its caring attitude towardsbasis. AMEX is well known for its caring attitude towards
customers.customers.
The Analysis and Interpretation of the customer data revealedThe Analysis and Interpretation of the customer data revealed
that the customers wanted the new card to be processed withinthat the customers wanted the new card to be processed within
three weeks where as AMEX was taking around 5 weeks.three weeks where as AMEX was taking around 5 weeks.
AMEX decided to issue new cards within two weeks.AMEX decided to issue new cards within two weeks.
Similarly another analysis revealed that the customers wantedSimilarly another analysis revealed that the customers wanted
the stolen/lost cards to be replaced within two days where asthe stolen/lost cards to be replaced within two days where as
AMEX was taking two or more weeks to issue replacementAMEX was taking two or more weeks to issue replacement
cards. AMEX decided to replace the lost cards within twocards. AMEX decided to replace the lost cards within two
days. As a result of these two decisions, AMEX could generatedays. As a result of these two decisions, AMEX could generate
$1.4million additional profit per year.$1.4million additional profit per year.
9. 3) Typical Application Areas
MarketingMarketing
Marketing ResearchMarketing Research
Demand ProjectionsDemand Projections
FinanceFinance
Financial Ratio AnalysisFinancial Ratio Analysis
Cash ForecastingCash Forecasting
Materials ManagementMaterials Management
Inventory ControlInventory Control
Incoming Quality AssessmentIncoming Quality Assessment
Quality ManagementQuality Management
SQC TechniquesSQC Techniques
Process CapabilityProcess Capability
10. 4) Types of Statistics
Descriptive StatisticsDescriptive Statistics isis
concerned with Dataconcerned with Data
Summarization,Summarization,
Graphs/Charts, andGraphs/Charts, and
TablesTables
Inferential StatisticsInferential Statistics is ais a
method used to talk aboutmethod used to talk about
a Population Parametera Population Parameter
from a Sample. It involvesfrom a Sample. It involves
Point Estimation, IntervalPoint Estimation, Interval
Estimation, andEstimation, and
Hypothesis TestingHypothesis Testing
11. Descriptive Statistics
Example
0
5
10
15
20
25
30
35
40
45
50
1st
Qtr
3rd
Qtr
Machine 1
Machine 2
Machine 3
Machine 4
The Quality Control Department of aThe Quality Control Department of a
large manufacturing company wouldlarge manufacturing company would
like to compute summary measureslike to compute summary measures
such as the mean production per shiftsuch as the mean production per shift
for a particular item. The departmentfor a particular item. The department
would also like to get a comparativewould also like to get a comparative
picture of performance of the meanpicture of performance of the mean
production across the four machines inproduction across the four machines in
the plant by tabulation. Further thethe plant by tabulation. Further the
company might like to graph thecompany might like to graph the
comparative performance of the fourcomparative performance of the four
machines by a bar chart depicting themachines by a bar chart depicting the
mean production per shift.mean production per shift.
12. Inferential Statistics -Example
Suppose you, as a marketing manager would like to identify aSuppose you, as a marketing manager would like to identify a
niche market for your product. You know from your experienceniche market for your product. You know from your experience
that an accurate assessment of the income of a typical family isthat an accurate assessment of the income of a typical family is
crucial. The average income of this type of families in thecrucial. The average income of this type of families in the
population is estimated by you to be Rs. 320000 based on figurespopulation is estimated by you to be Rs. 320000 based on figures
obtained from a sample. In this example, average income based onobtained from a sample. In this example, average income based on
sample is asample is a Point EstimatePoint Estimate of the population. The average incomeof the population. The average income
that falls with in a statistically formed interval of 320000 pluthat falls with in a statistically formed interval of 320000 plus ors or
minus 40000 is called anminus 40000 is called an Interval EstimateInterval Estimate. Any statement such. Any statement such
as the average income in the population is more than Rs. 300000as the average income in the population is more than Rs. 300000
per year is aper year is a HypothesisHypothesis. As a manager, the interval estimate may. As a manager, the interval estimate may
be much more important to you than the rest!be much more important to you than the rest!
Caution: Inferential Statistics assumes that the samplingCaution: Inferential Statistics assumes that the sampling
methodology is random (i.e. based on probability sampling)!methodology is random (i.e. based on probability sampling)!
13. 5) Some Key Terms Used in
Statistics
PopulationPopulation is the collection of allis the collection of all
possible observations of apossible observations of a
specified characteristic of interest.specified characteristic of interest.
An example is all the students inAn example is all the students in
the Quantitative Methods coursethe Quantitative Methods course
in an MBA program.in an MBA program.
SampleSample is a subset of theis a subset of the
population. Suppose you want topopulation. Suppose you want to
select a team of 20 students fromselect a team of 20 students from
200 students in an MBA program200 students in an MBA program
for participating in a managementfor participating in a management
quiz. The total students 200 is thequiz. The total students 200 is the
population. 20 students selectedpopulation. 20 students selected
for the quiz is the sample.for the quiz is the sample.
ParameterParameter is the populationis the population
characteristic of interest. Forcharacteristic of interest. For
example, you are interested in theexample, you are interested in the
average income of a particular classaverage income of a particular class
of people. The average income ofof people. The average income of
this entire class of people is called athis entire class of people is called a
parameter.parameter.
StatisticStatistic is based on a sample tois based on a sample to
make inferences about themake inferences about the
population parameter. If you look atpopulation parameter. If you look at
the previous example, the averagethe previous example, the average
income in the population can beincome in the population can be
estimated by the average incomeestimated by the average income
based on the sample. This samplebased on the sample. This sample
average is called a statistic.average is called a statistic.
14. 6) Types of Data
Qualitative DataQualitative Data are nonnumeric inare nonnumeric in
nature and can't be measured.nature and can't be measured.
Examples are gender, religion, andExamples are gender, religion, and
place of birth.place of birth.
Quantitative DataQuantitative Data are numerical inare numerical in
nature and can be measured.nature and can be measured.
Examples are balance in yourExamples are balance in your
savings bank account, and numbersavings bank account, and number ofof
members in your family.members in your family.
Quantitative data can be classifiedQuantitative data can be classified
into discrete type or continuousinto discrete type or continuous
typetype.. Discrete typeDiscrete type can take onlycan take only
certain values, and there arecertain values, and there are
discontinuities between values,discontinuities between values,
such as the number of rooms in asuch as the number of rooms in a
hotel, which cannot be in fraction.hotel, which cannot be in fraction.
Continuous typeContinuous type can take anycan take any
value within a specific interval,value within a specific interval,
such as the production quantity of asuch as the production quantity of a
particular type of paper (measuredparticular type of paper (measured
in kilograms).in kilograms).
15. 7) Types of Data Measurements-Picture
NominalNominal
OrdinalOrdinal
IntervalInterval
RatioRatio
InformationContentIncreases
16. 7) Types of Data Measurements
Nominal Data:Nominal Data: The weakest dataThe weakest data
measurement. Numbers are used tomeasurement. Numbers are used to
label an item or characteristic.label an item or characteristic.
Categorization is the main purposeCategorization is the main purpose
of this measurement. Examples: Aof this measurement. Examples: A
business school may designatebusiness school may designate
subject specialization by numbers,subject specialization by numbers,
i.e., MBA in Finance =1, MBA ini.e., MBA in Finance =1, MBA in
Systems = 2. Various brands ofSystems = 2. Various brands of
toothpaste; savings bank accounttoothpaste; savings bank account
numbers are other examples ofnumbers are other examples of
nominal data. Note that nominalnominal data. Note that nominal
data cannot be manipulated in adata cannot be manipulated in a
numerical fashion.numerical fashion.
Ordinal or Rank Data:Ordinal or Rank Data: NumbersNumbers
are used to rank. An example isare used to rank. An example is
Customer Preference for your brand.Customer Preference for your brand.
An average preference is rated at 3,An average preference is rated at 3,
a strong preference at 5. Simplea strong preference at 5. Simple
arithmetic operations are notarithmetic operations are not
possible for ordinal data. Ordinalpossible for ordinal data. Ordinal
data can also be verbalized on adata can also be verbalized on a
continuum like excellent, good, faircontinuum like excellent, good, fair
and poor. In ordinal data, distanceand poor. In ordinal data, distance
between objects cannot bebetween objects cannot be
measured.measured.
17. 7) Types of Data Measurements
Continues
Interval Data:Interval Data: If you have dataIf you have data
with ordinal properties and can alsowith ordinal properties and can also
measure the distance betweenmeasure the distance between
objects, you have an intervalobjects, you have an interval
measurement. Interval data aremeasurement. Interval data are
superiorsuperior to ordinal data because,to ordinal data because,
with them, decision makers canwith them, decision makers can
measure the distances betweenmeasure the distances between
objects. For example, frozenobjects. For example, frozen--foodfood
distributors are concerned withdistributors are concerned with
temperature, which is an intervaltemperature, which is an interval
measurement. Interval data havemeasurement. Interval data have
arbitrary zero point. Basicarbitrary zero point. Basic
arithmetic operations are possiblearithmetic operations are possible
with interval datawith interval data
Ratio DataRatio Data:: It is the highest level ofIt is the highest level of
measurement and allows you tomeasurement and allows you to
perform all basic arithmeticperform all basic arithmetic
operations, including division andoperations, including division and
multiplication. Data measured on amultiplication. Data measured on a
ratio scale have a fixed zero point.ratio scale have a fixed zero point.
Examples include business data,Examples include business data,
such as cost, revenue, market sharesuch as cost, revenue, market share
and profit.and profit.
18. 8) Data Sources
Primary DataPrimary Data are collected by the organization itself for aare collected by the organization itself for a
particular purpose. The benefits of primary data are that they fparticular purpose. The benefits of primary data are that they fitit
the needs exactly, are up to date, and reliable.the needs exactly, are up to date, and reliable.
Secondary DataSecondary Data are collected by other organizations or forare collected by other organizations or for
other purposes. Any data, which are not collected by theother purposes. Any data, which are not collected by the
organization for the specified purpose, are secondary data.organization for the specified purpose, are secondary data.
These may be published by other organizations, available fromThese may be published by other organizations, available from
research studies, published by the government, and so on.research studies, published by the government, and so on.
Secondary data have the advantages of being much cheaper andSecondary data have the advantages of being much cheaper and
faster to collect. They also have the benefit of using sources,faster to collect. They also have the benefit of using sources,
which are not generally available. Companies will, forwhich are not generally available. Companies will, for
example, respond to a survey by the Government of India, orexample, respond to a survey by the Government of India, or
Confederation of Indian Industry, but they would not answerConfederation of Indian Industry, but they would not answer
questions from another companyquestions from another company..
19. 9) A Step-By- Step Approach to
Statistical Investigation