Statistics) GTU

MBA First Semester (Business

1.1.2.2. Statistics as Statistical Methods

on the idea that, "Statistics is what
statistics does or statistics is

Statistics as a 'science of statistical methods' is based

Wharstaristicians do. This deinition coñsidersstatistics
as a subject or method.
AiSvareesas

be called the science of countingg'".

According to A.L.. Bowley, "Statistics may
in many cases data collection also depends on

In this detinition only one aspcct is covered, i.e., counting. But,

etc.
estimation, which helps in further classification, tabulation,
be called the science of averages".
According to A.L.Bowley, "Statistics may rightly
correlation coefficient,
data. However, it also uses diagrams, graphs,
Statistics uses averages to summarise the collected make it incomplete.
has been included in the above definition of statistics and hence
etc. for analysis, which not

is body of methods for making

decisions in the face of uncertainty'"
According to Wallis and Roberts, *Statistics
a

analysis and
"Statistics may be defined as the collection, presentation,
According to Croxton and Cowden,
interpretation of numerical data".

1.1.3. Types of Statistics

Statistics can be classified into two main categories:
characterisation of a set of data.
Statistics: This includes the methods of data collection, presentation and
1) Descriptive
All these helpin describing the various.features of the.collected.sampledata.
Descriptive statistics includes graphical
and
example, graphical
For representation includes bar charts, ine graphs
epresentaDon and quantitative measures. skewness and kurtosis denote quantitative measures.
piecharts whereas measures of central tendency, dispersion,
methods that help in characterising a population or
2) Inferential Statistics: Inferential statistics includes the
population. Sample and population are
help in decision-making which i_ based on the sample results of the is referred to as 'population' or
two relative terms. The larger unit about which analysis is to be done
sample'.
universe and thefraction or a porion of that popilation/universe-is.called
1.1.4. Characteristics of Statistics
Basic characteristics of statistics are as follows:
cannot be.considered as statistics as they
1) Statistics are averages of numerical data. Single or isolated figures
birth does not comprise statistics but a number
cannot help in analysis or drawing of conclusions. Single death or
rate.
ofSuchtigures help in deternining the average death or birth
2) Generally, statistics contains quantitative information which means it is always expressed numerically
accurate interpretations. Hence
Qualitative facts can never be measured numerically and therefore it cannot give
this can never be considered as statistics.
be said to be responsible for the
3) Statisucs are affected by various causes or factors. One cause or factor cannot
results after analysis of a given set.of data.
Staistical data is collected in a Systematic nannerfor a predetermined purpose. This means that the reason and

Plan for data collection is predetermined.

S Statistical data may be used for comparative studies. Por example, for comparing the efficiency of two

departments in an office, the performance appraisal can be used.

i.5. Scope/Applications of Statistics

Staistics has afteted almost aul aueas of life as it covers simple households to big businesses, even government also
Some of the arcas where statistics has been used are as follows:
1) Statistics and the Government: Statistics has been used extensively since the begining of organised society
Statistics has been used by the administrativeheads and rulers ofthe states intheform of collecting data on
difierent aopeis for thepurpose offormulatingsoundmiliary und fiscal policies. This data includes figures o
pöpufation, 1x coIEion,miliarysrength, etc: Ta the presenttmes.the governinent is thebiggest collector u
data as well as the bggest.uMLL atistics A huge amount of data i5,collected and interpretecd by varioun
depanments of the govemnient sor formulating effieient policies and decision-making.

2) Statistics and Mathematies: Statistics can be considered as a branch of science which is conceived on th
foundation.of mahematics. A person should have some knowledge of mathenmatics for understanding the busn
fündamentals of statisties
 Probability-(Module
1)
and
Business Stntisties
which.specialises in.data".
Mathematics.
to Connor, "Statistics branch of Applicd
is a
mathematics in as much as it attempts
According
properly be considered as a branch of
"Statistics may varieties".
According to W. I. King, of data of many different
nales of pmeediue applrcable in handing groups
to formujate
definite
Scope/Applleations of Statistics

Covemment
Statistics and the Statistics and Mathematics
m

Statistics and Economics

Statistics and Physical Science

Statistics and Natural Sciences

Statistics and Research

Statistics in Astronomy Statistics in Education

Statistics in Accounting and Auditing

Statistics in Planning

Statistics id Business Management

Statistics and Commerce

Other Areas

3) Statistics and Economics: Statistics is used important tool in economics study and research. Economics is
as an
Statistical tools
maindy concerned with production and distribution of wealth and also savings and investments.
USET iNthe Touowing cconomic interest areas:
Statisticai methods are used for measuring andforecasting Gross National Product (GNP).
Statistical studies of business cycles giveaclear pictureabouttheeconomic stability.
l) Economic policy-making depends on the statistical analysis of population growth, unemployment
figures, rural or urban populaton shits, etc.
iv) Optmumutilisation of resources is possible with the use of econometric models which uses statistical
methods.
v) For the stady of finance, banking, consumersavings and credit availability, financial statistics is necessary.
4) Statistics and Physical Science: The use of statistical methods is continuously increasing in the field of
physical sciences such as Biology, Pbysics, Chemistry,Astronomy, Medicine, ete. Statistcal data are collected
from CairerentrEsuts of different experiments. These are then comparatively studied to find out whether the
differing results are statistically significant or not. As more facts are discovered, the different estimates in
physical science such as distance between two planets in the universe become more accurate.
Statistics and Natural Seiences: Statistics is also
very important in the study of natural sciences such as
astronomy, biokogy, medicine, meteorology, zoology, bolany, etc. For example, for diagnosing the exact disease
of apatient, the doctor Must believe on real dala such as the body temperature, pulse rate, blood pressure, etc.
Statistics and Research: In the current
scenario statisties
is an essential part of research study. Improvement in
knowiedge has been
possible because experimenus ae carried out with the help of
example, experiments abovr crop yields and their corelation with different staúsucai nethods. For
of soil are
designed types of fertilisers and different
the belp of statistical techniques. In the current time, statistical methodstypes
and.studied.
used in al ypes of research
with are
work including medicine and public health.
Statistics in Astronomy: Astronomers were one of the first groups of
movenent of heavenly bodies and eclipses and oiher such people who used statistics in the study of
astronomical
heavily on estimation but iater statistics helped to turn these estimations into issues. Astronomers earlier relied
accurate ideas.
) Statistics in Education: Statistics is used
extensively the field of education because research has
in
comnon
fealure in al branches of acivitues,. In education, statistics plays a vital become a

policies for naew courses to be started, conIderaluon ot trastructural role in formulation of new
from this, there ate many
people involved in research work who requirements
lest past
for new courses, etc. Apart
knowledge with the help of statistics knowledge and develop new

9 Statistics in Accounting and Auditingt counting, exactness is an essential

making purposes, approximatian. is laken iito account. The current asset value is componenton the basis decision- but for
calculated
current walues and the conected yalues are determiued with. the.help of eurrent purchasing power of money its
of
or
the current value of it, while taking
depreciation into consideratiou This is done through the use of price indices
 1.2. DATA AND VARIABLE

1.2.1. Introduction
The term "dala" originated from the singular word called "datum" which literally means "something given". Data is
a collection ofraw and unorganised facts that has no individual meaning. When raw data is processed, organised, and
presented in certain structure însuchaway that it becomes meaningful and useful, it is known as "information'

For example, during census survey, various demographic data are collected such as name, age, occupation
cducation, income, etc., which is of no use till it is analysed and processed to provide some meaningful information
ke literacy rate, unemployment rate, average income, etc.

1.2.2. Types of Data

There are four types of data (or measurement scales):
1) Nominal,
2) Ordinal,
3) Interval and
4) Ratio.

1.2.2.1. Nominal Scale

This is the most fundamental form of measurementscal. These scales are not used to measure the value of an object.
but to categorise or classify the object. The values representedin these scales need not to benecessarily a quantitative
alue. This makes it qualitative in nature. The nominal scales are used extensively by market researchers. Nominal
scales are essentially arbitrary because a researcher can assign any label to any category, without distorting the
results. While the statistical measurements like mean and median cannot be calculated in the outcome of thesescales
the findings of a nominal scale can be further subjected to statistical tools ike mode, average, binomiai and chi-
quare tests.
 MRA First Semester (Husiness Statisties) (rTU

Eamptes of mmaal sealescan be

What s Our genkr (ttck "M-MaBe and F Female)

a t ts vur dair vmur' tnck 'A'-Hown. ®°-Black, 'C"-Blonde, 'D'-Gray. "E'-Other)

A

Numbe:s an also te assigned to the categories, but those would be treated as merely "labels in order to categorise
he tems r peopte in a group Typically, nominal scales are used to ascertain characteristics like gender, ethnicity,
buckgrouads. tastes. predcrences, ete., and not their intensity.

1.22.2 Ordinal Scale

while nominal scale focuses on categorising or classifying individuals or their responses, the ordinal scale seeks to
rank them on the hasis of their characteristics. In other words, it deals with relative positioning of an item on thec
bass of th characteristics of other.items.onthe scale

The articipants of the research rank the objects as per the preferences and tastes. Therefore, the respondents are
required to rank the objects from highest to lowest preterential order.

Thus. in ord1nai scale. the responses have nominal properties but these scales go a step further and attempt to
latively quantify them by assigning relative values. It would be pertinent to point out here that one cannot quantify
the difference between the two variables. These are essentially ranking scales. used extensively by market
Teseærchers to delermine customer preferences and choices. It may be noted that any data coliected through
nienviews or oxher methods of intemogation, always have ordinal properties.

For exanaple. consumers tnay be asked to rank five popular brands of ice cream on a scale of I to 5, with
repreenting the mos preferred and 5 representing the least.

2Kwity Walls
3 Mother Dairy
Crearn Beti
51 Vadiba

1.2.2.3 Interval Scale

niervai siie 1s th nprovcment or refinement over ordinal scale. Here, ubsolute values are assignet to the
e lrefore, the differesnce betwcen wo variables is also equal. The inputs collected from interval can be
eastly copted yith the felp.of Mean, Standard Deyiation,ete.
For erenpla te diffesence between 1X) degrees and 10 degrees is the sanie as between 60 degrees and

A t t kasnpie vf intervaf scale can be:

hti yei ape" (uk e cotect tange

2 20 YCat
4 3 4 4) yria

The diereace bet% eEn ali dhe values is s t i e in the atve example.
 Busincss Statistics and Probability (Module 1)
17
1.2.2.4 Ratio Scale
Patia scale is the most
refined and sophisticated form.ol scales used.primarily in
fintervalsCales, variables have. a relative physical sciences. While in
value, in rati0 scale, the variables do not have
ahsalute value. Hence, they incorporate the value for absence of any characteristics in an relative
a value but an
Canbe denoted with the value zCro It is the basic object. This absence
differentiator between an interval and a ratio scale.
The data obtained through a ratio seale makes the outcome a
meaningful and scientific interpretation.
Ratio scales are endowed with the characteristics of interval scales and the ratios of
the
scales provide important understanding regarding the analysis. In fact, whennumbers or valucs on these
better and
Variables are obtained through open-ended questions, they display ratio-scale responses on descriptive
following few examples properties and features. Consider the
The Kelvin Scale: 100 K is twice as hot as 50
K. The difference between values
ordered. is meaningful and can be

21 Weight: 100 kg is twice as heavy as 50 kg. The values be

can
arranged in an order (ascending/descending).
1.23 Types of Variable
Those factors and elements that.show.some variations.at.different
known as variables. Variables also have the ability to point of time and in different situations are
crucial for any study because with the help of variablesimpact
the outcome of any study.
a researcher is able to
Nonetheless, they are
name suggests,variables have identify the differences. As the
minimum two values. Some of the variables are
weight, height, gender, etc., tangible and visible in nature like
whereas others are very descriptive such as,
1Q. perception,
beliefs, etiquettes, self
esteem, etc. Hence, it can be said that variables are those facets
which one person has different from the others.
In the process of designing of quantitative research, one of the
with the topic of research. On the other hand, important steps is to identify the variables associated
qualitative
variables as their quantitative counterparts give, yet
researchers do not give as much consideration to the
they also have to outline the phenomena they are going to do
research on. The most important categories of variables are discussed in
detail. Though they are explained under the
heads of quantitative research methods, the
qualitative research also comprises of similar examples.
Following are the various types of variable in research:
1) Independent and Dependent Variables: Variables share
they are as follows: mainly two types of relaionship among each other,
i) Independent Variable (IV): Independent variables are those variables which on their own but
also affect the other yariable(s) under research. It is very likely that a variable vary they
which is independent for a
particular study may be a variable_under control for any other study. Similarly, in certain study the
independent variables may slightly be correlated, then in such cases they are not said to be independent
variable. For example, the relationship between crop yield and rainfall is such that the rainfall is an
Jndependent variable, whereas the crop yield depends on it. But, it is not necessary that the rainfail will act
as an
independent variable in all the situations.
11) Dependent Variable
(DV): Dependent variables generally get affected by the changes of independent
variables. As these variables change frequendy, the need of measurement, monitoring, and prediction of
these variables arise. Dependent variables are also known as criterion variable.
Concomitant Variable: Those variables whose values are generally available before the commencement of
CEarch and they are also correlated with the outcome of the research. are known as coneomitant variabies. Also
CSC Váriables are not one of the reasons due to which the research is being conducted. The examples of such
Variables are covariates and blocks. How to include these variables in the research design is one of the major
RCnges of research design process. Strategies used to overcome this challenge are as follows
1) Make
use of concomitant
variables as covariates.
Consider the concomitant variables as blocks and use them as the subject of research.
d e cerlain range to the values of concomitant variables so that the range intervals can be used as blocks
EXatmple,for the respondenls.of different ago groups, divide the groups inthe intervals of 20 years.
Concomitant variables cause the undesired variation among the other dependent and independent
thee h i s characteristic of the concomitant variables reduces the risk of biasness. On the other hand,
di iables give rise to the error variance, which in turn reduces the chances of recognising the actual
ditferences
18 MBA First Semester (BU$ine

To overcome these kinds of demerits, an ideal research design strategy is required which can reduce or nuiny

of undesired variations caused by the concomitant variables. There exist two such strategses, w n
aie
the effect
as follows
i) Experimental control and
i Statistical control
3) Moderating Variables: Every relationship comprises of minimum one dependent and independent variabie. The
second important independent variable under consideration is known as moderating variable. Such va1abies ar
invofvedbecause of the belief that it can make an important contribution towards the relationship of dependent an
independent variables. For example, the incentive-based compensation structure leads to improved performance o
the employees and this effect is more "evident among the young employees Hence, in the stated examples
incentive-based compensation structure is the independent variable and performance of employees is the depende
variable, whereas improvement of performance mainly seen in the young employees is the moderating vanable.
4)
4) Extraneous Variables: In any situation, theextraneous variables exist in a large number and it is very likely tha
they influence the relationship under consideration. But, the effect of these variables is very less, and therefore
them can be ignored, And the remaining, which might be of some importance, are either considered
most of a

independent or as moderating variables. For example, issuing of discount coupon on the purchase of raw cereai
will not heavily affect the sale because of numerous reasons such as, people may think that the government
about to increase the tax rates, election is scheduled, heavy rain is forecasted, etc.
5) Intervening Variables: According to Tuckman, "The intervening variable is that factor which theoretical
affects the observed phenomenon but cannot be seen, measured, or manipulated; its effect must be inferred from
the effects of the independent and moderator variables on the observed phenomenon".
In connection with the above mentioned example of incentive-based compensation structure, some empioyer
can perceive that their overall salary is increased and some may derive job satisfaction from it. These variabie
can be termed as intervening variables.

6) Diserete and Continous Variable: Dicrete variables the non-decimal numbers that means vaue berwernn2
are
to 4.5 are not possible. For example, number of student in class, as number of students only take a specir
vaiues like 1,2,3, and so on. A school cannot have a class with 40.5 students.

Another example of this variable is number of employee in a compnay.

Continous variables take the continous values or contünuous set of numerical value. Heighi, ength, an
these vaiables gives varying degree of precision. The wa
temperature are the few examples. Measurement using
For example, consider you saw
of the measurement is determine the size and accuracy of the measurement.
man and measured his height nearly 121 centimeters.
But this is not the mean that he is exactly 121 cm tal
his height is closest to 121 cm but not exacty. a segmen
because you just gave an approximate measure means
of view this segment extends from 120.5 to k31499
of your line is included by this 12) cun. From one poiut
cm included in 120.5 to 121.5 when rounded.
cm. You can say that 121
1.23. REVISION OF
PROBABILITY
1.23.1. Baye's Theorem propabiy,
or inverse

There are various names

revised
work on esian
Bayes
assigned to this
probability,
famous
probability. This was introduced by Thomasprobability,
like,
e posterior Patician) in
posterior
in hís available the

Decision Theory. This theory states about the Baye (anofEnglish eventtheby considerinmathematician)

theory
considering

finding the
of event Dyof
basis ot probability tneory.
probability
an probability

sample information. According to Baye's Theorem uncertainty can be red. On On the

evidene
and circumstantial
measured.
dditional
evidence
this theorem establishes a ule for
refining a hypothesis by allon t hvpothesis IS ru
niormation which results in a number, representing the degree of probabilhtyna
estimate the probability
be used to
For example, for an event A, a chosen sample of3 defective items out of 100 can

for an event B that a machine is not working properly.

and Az are the events tnat artE mutuainly

Bayesian probability is based on the conditional probability, where Ai as aisplaycd in ne
ne exhaustive. Whereas B is arsimple event which intersects with
each of the A events
and
CXChusive
Venn diagrams as sbown in figure 1.8.

A
A

B
Figure 1.8: Bayesian Probability

This is known as posterior probability as it is calculated after the information is recorded. It is the revised probability
i s derjved by the revision of the prior probabilities under the accumulated additional information. Further.it
e known as inverse probability, 1.e., delermining the probability of a probability. However, the Bayesian, or
e obabilities are always conditional probabilities which are calculated for every events as follows:
1 M u t a l i y Excusíve Events:_I there exIsIs the occurrence of an event E in combination with one of t
then
mutually exclusive events E, E...E,
PIE, )P(EJE,) Where k =1,2,..n
PE) E
PE,PE
aliy Fxciusive and Exhaustive Events: There are two and

he
he occurence
occurrence of the event B is in mutually exclusive and exhaustive events anal
Az and combination with A and
pTbabiity, gven t e event B is as under, Az, then for event A the co
PIA,)P(BA,)
PA,/B)PIA,)P(B/A,)+ P(A,)P(B/A2)
PA)PB/A,)
PLA,3)PiA.P(B/A,) PMA,)P(B/A,) +
 PrODavlili

2.5. HYPOTHESIS

2.5.1. Introduction
It is derived from a Greek word "hypotithenai" which means "to put under" or "to suppose Hypothesis is the
process of taking and using a sample statistics to make an inference for a population parameter.

According to Prof. Morris Hamburg, "A hypothesis in statistics is simply a quantitative Statement about a

population."

According to Palmer 0 Johnson, "A hypothesis is islands in the uncharted seas of thought to be used as bases for
consolidation and recuperation as we advance into the unknown."

HypothesIS generally occurs when we perform inductive reasoning. In inductive reasoning, researcher takes à sertes
of observations to perform a theory. So hypothesis is the first step of any research process. It is very important for
any esearch and formulated in various ways. Its basic function is the prediction of the final result o the
nvestugation.
2.6. HYPOTHESIS TESTING
2.6.1. Introduction
Hypothesis testing plays an important role in the application of statistics to real-life problems. Hypothesis testing
helps the researchers to make the decisions by using sampled data of unknown distribution of a population and its
parameters.

For example, consider a

manufacturing company which makes the geyser and the average life of the geyser is 10KX0
hour when manufactured through old
process and the average life is 1500 hours when the geyser is manufactured hy
the new process. So in this case we can make three
hypothesis:
1) New process is better than old process.
2 Oid process is better than new
process.
3) There is no disference between both the processes.
Purpose of Hypothesis Testing
i) Determine the focus & direction for a research effort.
2) Development of a hypothesis forces the researcher to
clearly state the purpose of the research activity.
3) Determine what vaniables will not be considered in a study, as well as those that will be considered.

2.6.2. Types of Hypothesis

Below are some of the important types of hypothesis
1) Research Hypothesis: It is directional hypotheses which specify the projected direction
earlier research or theory the direction is implied. It is a statement which
of the result. Using
make
generated by
the researchers when they
a guess on the result of an experiment or research.
When needs to test that
one a data support the research hypothesis then he/she requires to transform the data inte
statistical hypothesis.
2) Statistical Hypothesis: It is a hypothesis that can be verified statistically. It is not necessary that the statement is
logical it may be illogical (if statistic verifies it) then this is statistical hypothesis.
It is a statistical
hypothesis that shows statement with one or more parameters (like mean, percentage. etc.) whict
are population measure under study.
3 Substantive Hypothesis: Thishypothesis objective is to providing the answer to the raised questions and answ e
of the felt problem of a research study in a significant
way.
According to the Best and Kalm, "is a formal affirmative statement prediction a single research
tentative explanation of the relationship between two or more variables".

According to the Stangor, "a substantive or research hypothesis can be defined as a specific and falsitiab!e
prediction regarding the relationship between or among two or more variables, the research hypothesis states the
existence of a relationship between the variables of the interest and the specific direction of that relationship"
 pe T Error

3tate Of Nature
Nul aut Nullale
kpi ailto
AchionYectnulN
Cose c olecasón T
Rejet Coe eloustan
wul esror(X) p owe)
Steps (HEAV)

T Ryo thueiz e
Step Stallutha a u l l 8 oltunntwe
Hypoteps

to 2 Tet
StauhisHal te
tep 2 Petriniueft cPpod piaTAN
SFep 3 3 e t t Vaue 0 alpho
SHep 4: kstabukh fe oluton ule-
StepS RatthA sawple doito
Sp6 Analyze data.
TOuk 3Take 8taluHca) Actton
SHp 1keach aSt dotsticalcencluwon

Tosk Detunmin ebusnoss

tg Mabe a businces eeiston