INTRODUCTION &

DATA COLLECTION

SESSION-1

Dr. Saswati
IIFT
INTRODUCTION & DATA COLLECTION
•Definition, basic concepts and
applications of statistics

•Why data are needed

•Types of data

•Data measurement scales

•Step-by-step approach to statistical

investigation
 LEARNING OBJECTIVES
After this session, you should be able :
•To understand how statistics is used in
business

•To ascertain sources of data & types of

data used in business

•To understand different data

measurement scales

•To develop a practical approach towards

statistical investigation
.
Tween Survey
•Survey questions asked to 20 tweens:
• Q1. Which radio station was playing
on your drive to the ski resort?
• Q2. Rate the quality of the food at
the resort on a scale of 1 to 4.
• Q3. What time should the main
dining area close?
• Q4. How much of your own money
did you spend at the lodge today?
 Tween Survey
• Survey responses from the 20 tweens.
Tween Survey

1. Classify the tweens’ responses into

the appropriate measurement
scale.

2. Extract useful information from

each measurement scale.

3. Provide management with

suggestions for improvement.
 WHY LEARN STATISTICS

An understanding of statistics is needed for

following four key reasons:

• to know how to properly describe

information
• to know how to draw conclusions about
large populations based only on
information obtained from samples
• to know how to obtain reliable forecasts
• to know how to improve process
What Is Meant by Statistics?
Science of collecting, organizing, presenting,
analyzing, and interpreting data to assist in
making more effective decisions.

Collect

Organize

Present

Analyze & Interpret

What Is Statistics?

•Statistics is the methodology of

extracting useful information from a
data set.

Requirements
•Find the right data.
•Use the appropriate statistical tools.
•Clearly communicate the numerical
information into written language.
Who Uses Statistics?
Statistical techniques
are used extensively
by marketers,
accountants, quality
control personnel,
consumers,
professional sports
people, hospital
administrators,
educators, politicians,
physicians, etc...
Relevance of Statistics

•With knowledge of statistics:

- Avoid risk of making uninformed

decisions and costly mistakes

- Differentiate between sound

statistical conclusions and questionable
conclusions.
Relevance of Statistics

•Example 1. Headline of newspaper

states ‘What global warming?’ after
record amounts of snow in 2010.

Problem with Conclusion:

Incorrect to draw conclusion based on
one data point.
Relevance of Statistics
 Example 2. The CFO of Starbucks Corp.
claims that business is picking up since
sales at stores open at least a year climbed
4% in the quarter ended December 27,
2009.

Problem with Conclusion. The CFO

overstated the company’s financial position
by failing to mention that Starbucks closed
more than 800 stores over the past few
years.
Two Different Branches Of Statistics
Are Used In Business
Statistics
The branch of mathematics that transforms data into
useful information for decision makers.

Descriptive Statistics Inferential Statistics

Collecting, summarizing, Using data collected from a

presenting and small group to draw
analyzing data conclusions about a larger
group
Applications of Statistics in
Various Areas
• Marketing
• Economics
• Finance
• Insurance
• Operations
• Human Resource Management or
Development
• Information Systems
• Data Mining
 Illustrative List of Decision Situations and
Corresponding Statistical Techniques
Area Decision Situation StatisticalTechniques
Applicable
Marketing Assessment/Forecast Time Series
of Demand for the Correlation and
Product or a Service Regression Analysis
Statistical Inference

Customer Profiling Cluster Analysis

Market Research Sample Surveys

Conjoint Analysis
Multidimensional Scaling

Retail Identifying Customer Cluster Analysis

Management Buying Behaviors Correlation and
and Patterns Regression Analysis
Conjoint Analysis 16
Illustrative List of Decision Situations and
Corresponding Statistical Techniques
Area Decision Statistical Techniques
Situation Applicable
Finance and Evaluation of Regression Analysis, Decision
Banking Investment Analysis
Volatility of Stocks ‘b’ Analysis

Predicting EPS Regression Analysis

Derivatives ‘b’ Analysis and Regression

Analysis

Assessing Credit Discriminant Analysis

Worthiness Logistic Regression
Correlation Analysis
Insurance Determining the Probability. Time Series
Premium Regression Analysis 17
 Illustrative List of Decision Situations and
Corresponding Statistical Techniques
Area Decision Situation Statistical Techniques
Applicable

Impact of Different Regression Analysis

Factors on Health and Discriminant Analysis
Life

Operations Controlling and Statistical Quality Control

Improving Production Six Sigma
Process and Quality Sampling Inspections
Statistical Inference

Inventory Management ABC Analysis

HRD Performance Appraisal Normal Distribution

and Reward System Percentiles
18
SOME KEY TERMS AND DEFINITIONS
• Population (Universe)
• Collection of all possible observations of a
specified characteristic of interest.
• Sample
• Finite subset of population.
• Census
A complete enumeration of every item in a
population
• Parameter
• A population characteristic of interest
• Statistic
• A sample characteristic of interest
 Population vs. Sample

Population

Measures used to describe the Measures used to

population are called parameters describe the sample are
called statistics
WHY SAMPLE?
 Census of a population may be:
 Impossible
 Impractical
 Too costly
Sampling
• Prohibitive cost of census
• Destruction of item being studied may be
required
• Not possible to test or inspect all members of
a population being studied
Data, Data Sets & Need of Data
Data are the facts and figures collected, summarized
and analyzed, for presentation and interpretation.
 All the data collected in a particular study are
referred to as the data set for the study.
Why Data needed:
 Obtaining appropriate information is essential to
conduct business
 Data contain information needed to make a more
informed decision in a particular situation
 Any statistical analysis begin by identifying the most
appropriate data collection sources.
 If data are flawed by biases, ambiguities or other type of
errors, even the most sophisticated statistical
methodologies would not likely be enough to compensate
QUALITATIVE VS. QUANTITATIVE APPROACH

Analyzing the Problem

Structuring the Problem Qualitative

Analysis

Define Identify Determine Summary Make

Problem Alternatives criteria Evaluation decision

Quantitative
Analysis
Elements, Variables, and Observations
Elements are the entities on which data are collected.

A variable is a characteristic of interest for the elements.

The set of measurements obtained for a particular

element is called an observation.

A data set with n elements contains n observations.

The total number of data values in a complete data

set is the number of elements multiplied by the
number of variables.
Data, Data Sets,
Elements, Variables, and Observations
Variables
Element Stock Annual Earn/
Names
Company Exchange Sales($M) Share($)

NQ 73.10 0.86
Dataram
N 74.00 1.67
EnergySouth
N 365.70 0.86
Keystone
NQ 111.40 0.33
LandCare
N 17.60 0.13
Psychemedics

Data Set
Types of Variables
Variables

Categorical Numerical

Examples: Discrete Continuous

 Marital Status
 Political Party
 Eye Color
(Defined Examples: Examples:
categories)  Number of  Weight
Children  Voltage
 Defects per hour (Measured
(Counted items) characteristics)
 DATA MEASUREMENT SCALES
• Type of Measurement

• Nominal

• Ordinal
information content
increases
• Interval

• Ratio
 Scales of Measurement
•Scales of Measurement

•Nominal Qualitative Variables

•Ordinal

•Interval
•Ratio Quantitative Variables
 Nominal Scale of Measurement
• Nominal stands for name of category.

• Numbers are used simply as lebels for groups or classes.

• Categorization is the main purpose.

• Used for qualitative rather than quantitative data like

blue, green, male, female, professional classification,
geographic classification, etc.

• Can not be manipulated in a numerical fashion.

• Not amenable to arithmetic operations.

Nominal Scale of Measurement
• The Nominal Scale
• Least sophisticated level of measurement.
• Categories are used for grouping the data.
• No relationships among categories
• No ranking is implied.
• Only possible arithmetic operation is a count of each
category.

Qualitative values may be

converted
to quantitative values for
analysis purposes.
Ordinal Scale of Measurement
• Data elements may be ordered according to their
relative size or quality.

• Numbers are used to rank objects or attributes.

e.g. customer preference for a product can be
ranked by 1,2,3 & 4 where 4 is the best and 1 is
the worst.

• Distance between objects or ranks can not be

measured

• Simple arithmetic operations are not possible for

ordinal data.
 Ordinal Scale of Measurement
The ordinal scale
• classifies data into distinct categories
• in which ranking is implied

Categorical Variable Ordered Categories

\

Product satisfaction Satisfied, Neutral,

Unsatisfied
Faculty rank Professor, Associate
Professor, Assistant
Professor, Instructor
Standard & Poor’s bond AAA, AA, A, BBB, BB, B,
ratings CCC, CC, C, DDD, DD, D
Student Grades A, B, C, D, F
Scales of Measurement
Example: Tweens Survey
• What is the scale of measurement of the radio
station data?

Solution: These are nominal data—the values in

the data differ merely in name or label.
 Scales of Measurement
Example: Tweens Survey
• How are the data based on the ratings of the food quality
similar to or different from the radio station data?

Solution: These are ordinal since they can be both

categorized and ranked.
Interval Scale of Measurement
• Data may be categorized and ranked with respect
to some characteristic or trait.
• Differences between interval values are equal and
meaningful.
• Arithmetic operations of addition and subtraction
are meaningful
• Superior to ordinal data
• Interval data have an arbitrary zero point ► No
“absolute 0” or starting point defined.
• Meaningful ratios may not be obtained.
• E.g. measurement of time of day, measurement of
temperature.
Interval Scale of Measurement
• The Interval Scale
• Fahrenheit scale of temperature.
• Scale is interval because the data
are ranked and differences (+ or )
may be obtained.
• no “absolute 0” (What
does 0F mean?)

80F
What does mean?
40F
 Interval Scale of Measurement
• Highest level of measurement that has the
requisite desirable properties.
• Ratio data may be categorized and ranked with
respect to some characteristic or trait.
• Differences between interval values are equal and
meaningful.
• There is an “absolute 0” or defined starting point.
“0” does mean “the absence of …”
• Meaningful ratios may be obtained.
• Allows to perform all basic arithmetic operations.
• E.g. measurement of money, weight, volume, area
or length, business data such as cost , profit etc.
Interval and Ratio Scales
Scales of Measurement
Example: Tweens Survey
• How are the time data classified? In what ways do
the time data differ from ordinal data? What is a
potential weakness of this measurement scale?

• Solution: Clock time responses are on an interval

scale. With this type of data we can calculate
meaningful differences, however, there is no
apparent zero point.
Scales of Measurement
Example: Tweens Survey
• What is the measurement scale of the money data?
Why is it considered the most sophisticated form of
data?
•

• Solution: Since the tweens’ responses are in dollar

amounts, this is ratio-scaled data; ratio-scaled data
has a natural zero point which allows the calculation
of ratios.
 Scales of Measurement

Data

Categorical Quantitative

Numeric Non-numeric Numeric

Nominal Ordinal Nominal Ordinal Interval Ratio

Synopsis of Tween Survey
• 60% of the tweens listened to KISS108. The resort
may want to direct its advertising dollars to this
station.

• 55% of the tweens felt that the food was, at best,

fair.

• 95% of the tweens would like the dining area to

remain open later.

• 85% of the tweens spent their own money at the

lodge.
 Sources of Data
Primary Sources: The data collector is the
one using the data for analysis
Data from a political survey
Data collected from an experiment
Observed data
Secondary Sources: The person performing
data analysis is not the data collector
Analyzing census data
Examining data from print journals or data
published on the internet.
 Sources of DATA
Primary Data
Collected by the
organization itself for a
particular purpose of its own.
Fit the need exactly.
Up to date and reliable.
Collected through a
statistical sample survey
using a questionnaire.
Secondary Data
Not collected by organization
for the specified purpose
May be published by other
organizations , available from
research studies , published by
government & so on .
Much cheaper and faster to
collect.
Have the benefit of using
sources which are not generally
available.
Collected by other
organizations or for other
purposes.
Step by Step approach to statistical Investigation

• Statistical investigation is purposeful and

lays the structure for decision making.

• Provides answer to various management

problems that the decision makers face.

• Gives a set of actionable recommendation

that will help organizations develop and
implement superior strategies.
Steps For Statistical Investigation Process
Problem Identification

Objectives of the study

Type of Study

Sampling Plan

Data Collection

Data Analysis & Interpretation

Finding of the Study

 Consumers of Detergent
Market

and their Attitude towards

Buying

in BHEL Township, Trichy

A Case Study
1. Problem Identification:

• The market place is crowded with a no. of

brands of washing powder and is characterized
by intense competition.

• To study various aspects of consumer behavior

in the context of purchasing a particular brand
of detergent i.e. the profile of consumers who
are buying detergents and their attitude towards
purchase.
2. Objectives of the study:

• To understand the relationship between income

and choice of brand.

• To study the relationship between choice of

brand and mode of washing.

• To assess customer loyalty.

• To understand the relative importance of various

products attributes perceived by consumers.

• To know who makes the purchase decision.

3. Type of Study:

• A descriptive study that deals with determining various

characteristics of detergent market in the context of
consumer attitude towards purchase.

• Throws light on the frequency with which a marketing

phenomenon occurs, or is associative with other relevant
variables.

• Findings of this investigation will help to grasp the

buying behavior of consumers to a reasonable extent.
4. Sampling Plan:

• Sampling frame: All past and present users of

detergents with income >= Rs. 5000 per month.

• Unit of analysis: Household in BHEL Township in Trichy

• Sampling method used:

• Random sampling procedure was adopted using income as the

basis of selection.
• Categories that were used in classifying income are:
• up to Rs. 5000 per month
• Rs. 5001- 20,000 per month
• Rs. 20,001- 40,000 per month
• Above Rs. 40,000 per month
• A sample of 150 customers was selected for this study.
5. Data Collection:

• Primary data collection method was

adopted using a questionnaire
instrument.

• Data were collected through personal

interview by a group of MBA student
of B.I.M, Trichy.
DATA ANALYSIS AND INTERPRETATIONS
a) What can we say about income vs. choice of brand?
Survey Results
Brands
ARIEL SURF WHEEL HENKO
Income Number Percentag Number Percentag Number Percentag Number Percenta
s e s e s e s ge
per month

≤ Rs. 8 5.33 6 4.00 12 8.00 15 10.00

5000
Rs. 5001- 7 4.67 9 6.00 8 5.33 6 4.00
20000
Rs. 10 6.67 14 9.33 6 4.00 5 3.33
20001-
40000
>Rs. 18 12.00 16 10.67 5 3.33 5 3.33
40000
Note: Percentage in each cell is worked out to the total respondents (150).
INTERPRETATION
• Consumers in the income slab of Rs.20001 and
above prefer premium brands (Ariel & Surf) and
this is about 39%.

• Consumers in the income slab of less than

Rs.20000 prefer Economy brands (Wheel &
Henko) and this constitutes about 27%.

• Consumers in the highest income slab of more

than Rs.40000 clearly prefer Premium brands
(23%) and the Economy brands preference in this
category is only about 7%.
INTERPRETATION
• Also, in the highest income category of more than
Rs.40000, out of the 44 consumers, 34 (77%) prefer
premium brands (Ariel+Surf) and only 10 (23%)
prefer economy brands (Wheel+Henko).

• Likewise, in the lowest income category of upto

Rs.5000, out of the 41 consumers, 27 (66%) prefer
economy brands and 14 (34%) prefer premium
brands.

It seems that the income strata impact the brand

selection. Brand preference is strongly associated
with income level.
DATA ANALYSIS AND INTERPRETATIONS

b) What can we say about choice of brand versus mode of washing?

Survey Results
Brands
ARIEL SURF WHEEL HENKO
Mode of Numbers Percentag Numbers Percentage Numbers Percenta Numbers Percentage
e ge
washing

Self 18 12.00 12 8.00 26 17.33 9 6.00

Servant 6 4.00 6 4.00 6 4.00 6 4.00

Washing 24 16.00 22 14.67 6 4.00 9 6.00

Machine
Note: Percentage in each cell is worked out to the total respondents (150).
INTERPRETATION

• Consumers having washing Machine

predominantly prefer Premium Brands (31%) and
are less enthusiastic about Economy brands
(10%).

• Consumers doing self-wash use Premium brands

(20%) and Economy brands (23%).

• Also, in the category of consumers using washing

machines, out of the 61 consumers 46 (75%) use
Premium brands and only 15 (25%) use Economy
brands.
INTERPRETATION

• Likewise, in self-wash category, out of the 65

consumers, 30 (46%) use Premium brands and
35 (54%) use Economy brands.

• Out of this 54% using Economy brands, 40%

prefer Wheel and only 14% prefer Henko.

It appears that mode of washing influences

choice of brands.
DATA ANALYSIS AND INTERPRETATIONS

c) What can we say about customer loyalty?

Survey Results

Mode of Premium Brands Economy Brands

action
Numbers Percentage Numbers Percentage

Buy another 21 14.00 15 10.00

Brand
Don’t buy 67 44.67 47 31.33
any other
Brand
Note: Percentage in each cell is worked out to the total respondents (150).
INTERPRETATION
• Both in Premium and Economy Brands, consumers are
showing a strong Brand loyalty and are willing to wait till they
get their favourite Brands.

• Overall, 76% of the consumers are sticking to their Brands.

• Out of 88 consumers of the Premium Brands, 67 (76%) are

willing to wait for their favourite Brands and also out of 62
consumers of Economy Brands 47 (76%) are willing to wait
for their favourite Brands.

It points to the fact that proportion of customers waiting to

buy their favourite Brand when it is not available, is much
more than proportion of customers switching to another
Brand.
DATA ANALYSIS AND INTERPRETATIONS

d) Which attributes are more important?

Survey Results
Attribute Numbers Percentage
Pleasant smell 14 9.33
Price 37 24.67
Lather 21 14.00
Dirt removing efficiency 58 38.67

Cloth quality after wash 20 13.33

(fabric care)
Total 150 100.00
INTERPRETATION

• The two most important attributes required for

buying, according to consumers of washing
powders are dirt removing efficiency (39%) and
price (25%).

• Lather and cloth quality after wash are in the

3rd and 4th position respectively.

It points to the fact that all attributes are not

equally weighted by the consumers while
purchasing washing powders.
DATA ANALYSIS AND INTERPRETATIONS
e) Are there significant differences in attribute ranking by consumers between Premium
and Economy segments?
Survey Results
Premium Segment Economy Segment
Attribute Sum of Ranks of Attributes Attribute Sum of Ranks of Attributes
Pleasant 393 Pleasant 221
smell smell
Price 249 Price 93
Lather 295 Lather 296
Dirt removing 161 Dirt removing 150
efficiency efficiency
Clothe quality 222 Clothe quality 170
after wash after wash
Number of respondents = 88 Number of respondents = 62
Note:
As average rank will pose difficulty in interpretation, we have used sum of ranks of attribute as the
basis of interpretation.
Here the attributes are ranked in order of importance by the respondents.
Rank 1 for an attribute indicates the most important; rank 2 the next most important and so on.
An attribute that has the smallest sum of ranks is the best.
INTERPRETATION

•Under Premium segment, dirt removing

efficiency is the most important attribute
followed by cloth quality after wash.

•This seems to weigh more in the minds of

the consumers while purchasing a
particular detergent.

•Price is ranked only third.

INTERPRETATION
• Under Economy segment, price is the most
important attribute followed by dirt removing
efficiency.

• Cloth quality after wash gets the third position.

The results suggest that the ranking of attributes

within the Premium and Economy segments are
not the same and there are differences in attribute
ranking between Premium and Economy brands.
The expectations of these two groups are not
identical.
DATA ANALYSIS AND INTERPRETATIONS

f) Who makes the purchase decision?

Survey Results
Decision Maker Numbers Percentage
Head of the house 33 22.00
Wife 92 61.33
Elders 19 12.67
Shopkeeper 6 4.00
Total 150 100.00
INTERPRETATION

• The results overwhelmingly point to the fact that wives

are the main decision makers when it comes to buying
washing powder.

• It constitutes about 61%.

• Shopkeepers’ influence on the purchase decision is only

4%.

It looks pretty obvious that purchase decision of

washing powder is predominantly made by wives.
FINDINGS OF THE STUDY
• The impact of income levels on the choice of the Brand is
significant
• The higher income group prefers Premium Brands like Ariel and Surf
excel while the lower income group prefers Economy Brands like Wheel
and Henko.

• The choice of the Brand also depends on the mode of washing

• Consumers using washing machines prefer Premium Brands while those
doing self-wash prefer Economy Brands.

• Customer loyalty to the Brand is very strong

• Proportion of customers willing to wait for their preferred Brands when
those are not available, is more than the proportion of customers willing
to switch to another Brand.

• Dirt removing efficiency is the paramount attribute in choosing a

detergent
• Dirt removing efficiency is the most important attribute followed by
Price.Lather and cloth quality after wash are almost tied at third
position.
FINDINGS OF THE STUDY

• There are significant differences in ranking of attributes

by consumers
• It is interesting to note that in the Premium Segment Dirt removing efficiency is the
most important attribute followed by cloth quality after wash and then the Price,
whereas in the Economy segment Price is the most important attribute followed by Dirt
removing efficiency and then the cloth quality after wash.

• The purchase decision is predominantly made by

housewives.
• The study points out overwhelmingly that wives are the most important people in
purchase decision.

Note: All the findings above are statistically verified by

standard test procedures that you will be learning in this
course.
QUESTIONNAIRE
1. Which Brand of washing powder do you use?

2. How long have you been using this powder?

3. Which of the following attributes is the most important for you while
buying a washing powder?
a. Pleasant smell
b. Price
c. Lather
d. Dirt removing efficiency
e. Cloth quality after wash
f. Any (please specify)

4. Rank the following attributes in the order of importance.

Attribute Rank
• Pleasant smell
• Price
• Lather
• Dirt removing efficiency
• Cloth quality after wash
QUESTIONNAIRE
5. What is your mode of washing?
a. Self
b. Servant
c. Washing machine

6. If the washing powder of your choice is not available, what will you do?
a. Try in another shop
b. Wait until your Brand arrives
c. Try a different Brand

7. Who makes the purchase decision in your house?

a. Head of the family
b. Wife
c. Elders
d. Shopkeepers

Classification Section:
A. Number of members in the family:
B. Monthly household income (Rs. Per month):
a. ≤ 5000
b. 5001 to 20000
c. 20001 to 40000
d. Above 40000