1

DAILY
CLASS NOTES
Management

Statistics
Lecture – 1
Statistics Overview
 22

John Graunt (1620-1674), the word "Statistics' is of Italian origin and it is derived from the
word 'Stato' and statista means a person who deals with affairs of the That is, initially kings or
monarchs or governments used it to collect the information related to the population,
agricultural land, wealth, etc. of the state. Their aim behind it was just to get an idea about the
men power of the state, force needed for the purpose of a war and necessary taxes to be impose
to meet the financial need of the state. So, it indicates that initially it was used by kings or
monarchs or governments for administrative requirements of the state. That is why its origin lies
in the State craft(The art of managing state affairs).
On the basis of evidences form papyrus manuscripts and ancient monuments in pharaonic
temples, it is assumed that first census in the world was carried out in Egypt in 3050 BC. Yet,
China's census data around 2000 BC is considered as the oldest surviving census data in the
world.

DEFINITION OF STATISTICS
«Statistics is the science of counting- AL. Bowly.
"Statistics is the science of average." -A.L. Bowly.
Statistics is "The science of the measurement of the social organism, regarded as a whole, in all
its manifestations." -A.L. Bowly.
"Statistics are the numerical statements of facts in any department of enquiry placed in relation
to each other." - AL. Bowly.
"By statistics we mean quantitative data affected to a marked extent by multiplicity of causes."
Yule and Kendall.
"Science of estimates and probabilities."- Boddington.
"The method of judging collective natural or social phenomena from the results obtained by the
amalysis of an enumeration or collection of estimaties." -W.I. King.
«Statistics is the science which deals with collection classification and tabulation of numerical
facts as the basis for explanation description and comparison of phenomenon"
- Lovitt.
"The science which deals with the collection, tabulation, analysis and interpretation of
numerical data.» - Croxton and Cowden.
From the above author definition comprehended as
 3

"Statistics is a branch of science which deals with collection, classification, tabulation, analysis
and interpretation of data."

There are two kinds of Statistics, which are descriptive Statistics and inferential Statistics.
1. Descriptive Statistics, the Data or Collection Data are described in a summarized way
2. Inferential Statistics, we make use of it in order to explain the descriptive kind.

DATA
Data play the role of raw material for any statistical investigation and defined in a single
sentence as "The values of different objects collected in a survey or recorded values of an
experiment over a time period taken together constitute what we call data in Statistics"
Each value in the data is known as observation.

Types of Data
Based on the characteristic
Oualitative Data
Ouantitative Data
Based on nature of the characteristic
Discrete data
Continuous data
 44

Based on the level of measurement

Nominal Data
Ordinal Data
Interval Data
Ratio Data
Based on the Time Component
Time Series data
Cross Sectional data

Based on the ways of obtaining the data

Primary Data
Secondary Data

Time Series Data

Collection of data is done to solve a purpose in hand. The purpose may have its connection with
time, geographical location or both. If the purpose of data collection has its connection with
time then it is known as time series data. That is, in time series data, time is one of the main
variables and the data collected usually at regular interval of time related to the characteristic(s)
under study show how characteristic(s) changes over the time.
For example, quarterly profit of a company for last eight quarters, yearly production of a crop in
India for last six years, yearly expenditure of a family on different items for last five years,
weekly rate of inflation for last ten weeks, etc. all form time series data.
If the purpose of the data collection has its connection with geographical location then it is
known as Spatial Data. For example,
(i) Price of petrol in Delhi, Haryana, Punjab, Chandigarh at a particular time.
(in) Number of runs scored by a batsman in different matches in a one day series in different
stadiums.
If the purpose of the data collection has its connection with both time and geographical
location then it is known as Spacio-Temporal Data. For example, data related to population
of different states in India in 2001 and 2011 will be Spacio Temporal Data.
 55

In time series data, spatial data and spacio temporal data we see that concept of frequency have
no significance and hence known as non-frequency data.
For instance, in the example discussed in case of time series data, expenditure of Rs 40000 on
food in 2006 is itself important, here its frequency say 3 (repeated three times) does not make
any sense.
Now consider the case of marks of 40 students in a class out of 10 (say). Here we note that there
may be more than one student who score same marks in the test. Suppose out of 40 students 5
score 10 out of 10,
it means marks 10 have frequency 5. This type of data where frequency is meaningful is known
as frequency data.

Cross Sectional Data

Sometimes we are interested to know that how is a characteristic (such as income or
expenditure, population, votes in an election, etc.) under study at one point in time is distributed
over different subjects (such as families, countries, political parties, etc.). This type of data
which is collected at one point in time is known as cross sectional data. For example, annual
income of different families of a locality, survey of consumer's expenditure conducted by a
research scholar, opinion polls conducted by an agency, salaries of all employees of an institute,
etc.
Types of Data Analysis
1. Descriptive Statistics - provide an overview of the attributes of a data set. These include
measurements of central tendency (frequency, histograms, mean, median, & mode) and
dispersion (range, variance & standard deviation)
2 Inferential Statistics - provide measures of how well your data support your hypothesis and if
your data are generalizable beyond what was tested (significance tests)
Types of Data Analysis
Descriptive
Measures of central tendency
Measures of dispersion
Measures of Skewness
Correlation and regression of two variables
Inferential
Parametric tests-
 6

Hypothesis testing: Z-test; t-test; ANOVA(1 Way); Chi-square test;

Non-Parametric tests-
Mann-Whitney test (U-test); Kruskal-Wallis test (H-test); Rank correlation test
Permissible Statistical Tools in measurement scales
MEAST REMENT SCALE PERMISSIBLE LOGIC REASON
STATISTICAL TOOLS
NOMINAL SCALE Mode, chi-square test and run Here counting is only
test permissible operation.
ORDINAL SCALE Median all positional averages Here other than counting,
like quartile, Decile, order relation (less than or
percentile, Spearman's Rank greater than) also exists.
correlation
INTERVAL SCALE Mean, S.D., t-test, F-test, Here counting, order and
ANOVA, sample multiple and difference operation hold
regression.
RATIO SCALE Geometric mean (G.M.), Here counting, order,
Harmonic mean (H.M.), difference and natural zero
Coefficient of variation exist.

Graphical Presentation of Data

Generally four methods are used to represent frequency distribution graphically. These are
Histogram, Smooth frequency graph, ogive or cumulative frequency graph and Pie chart.
A histogram is a graph used to represent the frequency distribution of a few data points of one
variable. Histograms often classify data into various “bins” or “range groups” and count how
many data points belong to each of those bins. It was first Introduced by Karl Pearson.
 7
7

Smoothed Frequency Polygon: When the sample is very small and the frequency distribution is
irregular the polygon is very jig-jag. In order to wipe out the irregularities and "also get a better
notion of how the figure might look if the data were more numerous, the frequency polygon
may be smoothed." It was first introduced by Karl Pearson.

Ogive or Cumulative Frequency Polygon: by James Whitbread Lee Glaisher

Ogive is a cumulative frequency graph drawn on a natural scale to determine the values of
certain factors like median, Quartile, Percentile etc.
In these graphs the exact limits of the class intervals are shown along the X-axis and the
cumulative frequencies are shown along the Y-axis.
 8

Pie Chart: by William Playfair

A pie chart (or a circle chart) is a circular statistical graphic, which is divided into slices to
illustrate numerical proportion.
In a pie chart, the arc length of each sice (and consequently its central angle and area), is
proportional to the quantity it represents.