CHAPTER 1

Statistics :An Overview

 Overview of Statistics
 Present a broad overview of statistics as a
subject.
 Bring out applications of statistics and its
usefulness in managerial decision-making.
 Describe the data collection process.

1-2
 APPLICATIONS OF STATISTICS

Accounting: Public accounting firms use statistical sampling

procedures when conducting audits for their clients.
Economics :Economists use statistical information in making
forecasts about the future of the economy or some aspect of it.
Marketing : Electronic point-of-sale scanners at retail checkout counters
are used to collect data for a variety of Marketing research applications.

Production: A variety of statistical quality control charts are used to

monitor the output of a production process
Finance Financial advisors use price-earnings ratios and dividend yields
to guide their investment recommendations
 Growth and Development of Statistics

Views held about statistics are numerous, and has different

meanings to different users.
 for a cricket fan, statistics refers to numerical information relating
to runs scored by a cricketer;
 for an environmentalist, statistics refers to information on the
quantity of pollution released into the atmosphere by all types of
vehicles in different cities;
 for the census department, statistics refers to information about
birth rate per thousand and sex ratio in different states;
 for a share broker, statistics refers to information on changes in
share prices over a period of time; and so on.
1-4
 Growth and Development of Statistics

Various types of graphs, tables and charts showing increase

and/or decrease in per capita income, wholesale price index,
industrial production, exports, imports, crime rate etc., are
commonly perceived as statistics.
The sources of such statistics are newspapers,
magazines/journals, reports/bulletins, radio, and television.

1-5
 Knowledge of Statistical Techniques
A knowledge of statistics is like a knowledge of foreign
language or of algebra, it may prove of use at any time
under any circumstances. -- Bowley
The knowledge of statistics enables to ·
 Summarize and describe information (data) more precisely
to understand the process at a glance.
 Capture a population’s characteristics by making inferences
from a sample’s characteristic.
 Understand the nature of relationship between pair of
variables in a process to improve its functioning.
 Make reliable forecasts of certain events of interest

1-6
 Statistical Thinking and Analysis
Statistical thinking is the thought process that focuses on
ways to identify, control, and reduce variations present in
all processes.
An understanding of a process enhances opportunities for
improvement in the quality of products or services and
make interpretations of the variations in a process.
 Management Philosophy -- the catalyst for laying a foundation for
total quality improvement efforts,
 Behavioral Tools -- brainstorming, team-building ,etc. improve
group decision making
 Statistical Methods -- control charts, and descriptive statistics
develop understanding and improving the processes

1-7
 Steps Of Statistical Thinking

Sp ec ify the Aim of th e S tudy

U nd ers tan d H ow the P ro cess W orks

As sess th e C urrent P roce ss Pe rfo rm anc e

Ide ntify S trategies for Im p ro vem ent

Flow Chart of
Test the E ffe ctiv eness of the Propo sed Strate gy Process
Improvement
No
Su cc es sfu l?

Yes

Im p lem ent th e S tra tegy

1-8
 Statistics Defined
The word statistics refers to a set of procedures and principles
useful for collecting and analyzing numerical information to draw
conclusions and making decisions.

 Classified facts respecting the condition of the people in a

state . . . especially those facts which can be stated in numbers
or in tables of numbers or in any tabular or classified
arrangement. -- Webster

 Statistics is the science which deals with the methods of

collecting, classifying, presenting, comparing and interpreting
numerical data collected to throw some light on any sphere of
enquiry. -- Seligman
·
1-9
 Types of Statistical Methods
Descriptive Statistics
Methods of descriptive statistics are used for collecting,
presenting, and indicating center, spread, and shape of the
data set.
These methods include graphic methods and numeric
measures:
• Bar charts, line graphs, and pie charts.
• measures of central tendency, dispersion, skewness, and
kurtosis.
Such methods are helpful to describe various features/
characteristics of data set.
1-10
 Types of Statistical Methods
Inferential Statistics
Methods of inferential statistics are used for estimation of
population characteristics on the basis of sample results and
testing of statistical hypothesis.
These methods include parametric and non-parametric statistical
methods:
 Parametric statistical methods are used to draw inference
about a population for which the sample is drawn on an interval
or ratio scale and population is normally distributed.
 Non-parametric statistical methods are used to draw inference
about a population for which the sample is drawn on nominal or
ordinal scale and population need not be normally distribution .

1-11
 Limitations of Statistics
Statistical methods are to applied directly to study problems that are not
stated and expressed quantitatively.
 Statement like ‘export volume of India has increased during last few
years’ cannot be analyzed statistically. Also, qualitative characteristics
such as honesty, poverty, welfare, beauty, or health, cannot directly be
measured quantitatively.
A single number cannot be considered as statistics, unless it is part of
data relating to any particular field of enquiry.
 Price of a single commodity / increase or decrease in the share price of
a particular company does not constitute statistics.
 Figures representing prices, production, sales volume, and profits over
a period of time or places do constitute statistics.
1-12
 Statistics Can be Misused
Statistics only furnishes a tool though imperfect which is
dangerous in the hands of those who do not know its use
and deficiencies. --
Bowley

Conclusion that smoking causes lung cancer, since 90

per cent of people who smoke die before the age of 70
years, is statistically invalid because nothing has been
mentioned about the percentage of people who do not
smoke and die before reaching the age of 70 years.

1-13
 Terminology
 The elements are the entities on which data are collected.
 A variable is a characteristic of interest for the elements .
 The set of measurements collected for a particular element is call
an observation.
The total number of data values in a complete data set is
the number of elements multiplied by the number of variables.
 Illustration
Observation Variables

Stock Annual EPS

Company Exchange Sales(Rs M) (Rs)

Element
Names Dabur BSE 73.10 0.86
Jaypee NSE 74.00 1.67
India Cement NSE 365.70 0.86
Jindal BSE 111.40 0.33
ITC NSE 17.60 0.13

Data Set

15
 Need for Data
The main reasons for collecting data are :
• To provide necessary inputs to a given process or
situation under study.
• To measure performance of an ongoing process such
as production, service, and so on.
• To enhance quality of decision-making by
enumerating alternative courses of action , comparing
and selecting an appropriate one.
• To understand causes and probable effects of certain
characteristics in a process.
1-16
 Reliability of Data
• Have data come from an unbiased source-- source should
not have an interest in supplying the data that lead to a
misleading conclusion?
• Do data represent the entire population under study. How
many observations should represent the population?
• Do the data support other evidences already available. Is
any evidence missing that may cause to arrive at a
different conclusion?
• Are data support the logical conclusions drawn. Have we
made conclusions which are not supported by data?

1-17
 Scales of Measurement
Data

Qualitative Quantitative

Numerical Non-numerical Numerical

Nominal
Nominal Ordinal Nominal Ordinal Interval Ratio
 Scales of Measurement
Nominal, Ordinal, Interval, and Ratio
 The scale determines the amount of information
contained in the data.

 The scale indicates the data summarization and

statistical analyses that are most appropriate.

1-19
 Scales of Measurement
Nominal Scale
Data are labels used to identify an attribute of the element .
A nonnumeric label or numeric code(either name or category) may be
used in such as way that these values are mutually exclusive and
collectively exhaustive.
 Shirt numbers in a match are measured at a nominal level. A player
wearing a shirt number 24 is not superior or senior of a player wearing a
shirt number 12 and is also not twice the number 12. Numbers recognized
as labels only and have no quantitative value.
 Students of a university are classified by the programme in which they are
enrolled using a nonnumeric label such as Business, Humanities,
Education, and so on. Also a numeric code could be used for the
programme variable (e.g. 1 for Business, 2 for Humanities, 3 for
Education, and so on).

1-20
Ordinal Scale
Numerical values are categorized in the same way as that of nominal scale
but order or rank of numerical values is meaningful stating the magnitude
of differences among the ranks .

 Characteristics like‘ superior to’, ‘happier than’ , ‘greater than’ and so on

without stating the magnitude of difference.
 The difference between ranks 1 and 2 may be more or less than the
difference between ranks 4 and 5. The interval between values is not
interpretable .
 Students of a university are classified by their class standing using a
nonnumeric label such as Junior, or Senior. Also, a numeric code could
be used for the class standing variable (e.g. 1 for senior ,2 for junior and
so on).

1-21
Interval Scale
 Nominal scale make qualitative distinction among variables that can
be grouped into two or more categories that are mutually exclusive .
 Ordinal scale make qualitative distinction among variables that are
mutually exclusive based on rank ordering – determining the
status( superior to’, ‘happier than’ , ‘greater than’ or ‘less than’ ,equal
to,) without stating the magnitude of difference .
Interval scale make distinction among variables according to certain
categories and determine order of these categories. It measures the
magnitude of difference among categories.

Example: Manisha has an MAT score of 1205, while Shreya has an MAT score
of 1090. Manisha scored 115 points more than Shreya.

1-22
Ratio Scale
The data have all the properties of interval data and the ratio of two
values is meaningful.
 Variables such as distance, height, weight, and time use the ratio scale

 This scale must contain a zero value that indicates that nothing exists
for the variable at the zero point
• Manisha’s college record shows 36 credit hours earned, while
Shreya’s record shows 72 credit hours earned. Shreya has twice
as many credit hours earned as Manisha.
• A person weighing 90 kg is twice as heavy as one who weighs 45
kg. Since multiplying or dividing both of these numbers (90 and
45) by any given number will preserve the ratio of 2 : 1

1-23