1

Research Methodology

The study of conducting research is Research

Methodology.

Research: The word research is composed of two syllables

Re and Search.

Re is the prefix meaning Again or over again or a

new and Search is the latter meaning to examine closely
and carefully or to test and try.

Together they form, a careful, systematic, patient

study and investigation in some field of knowledge
undertaken to establish principles / policies.

Research can also be defined as

1. Search for knowledge

2. Systematic and scientific search for getting relevant

answers on any taken up specific topic.

3. Scientific enquiry into a subject.

4. Research is a movement from the unknown to the

known.

5. It is the voyage of discovery

Acc to Bulmer,

Research is primarily committed to establishing

systematic, reliable and valid knowledge about the social
world.

Acc. To Clifford Woody,

2

Research comprises of

Defining and redefining problems.

Formulating hypothesis (basic idea)

Collecting

Organizing

Evaluating datas

Making decisions

Suggesting solutions

Reaching conclusions

Finally, carefully testing the conclusions

To determine whether they fit the formulated Hypothesis.

Research Methods: May be understood as all those

methods or techniques that are used by a researcher for
conducting a Research depending upon the methods.

(1) Library Research: analysis of historical

records and documents.

- Statistical compilation, references, abstracts, guides

manipulation (handle with skill)

(2) Field Research: Observation,

questionnaires, personal, Group or telephonic
interviews, case study.

(3) Laboratory Research:

3

Group (team) study, use of audio visual tools.

Research Methodology: is the way do systematically

solve the research problem.

In it we study the various steps that are generally

adopted by a researcher in studying his research problem
logically.

When we talk of Research Methodology, we not only

talk of research methods but also consider the logic behind
the methods we use in the context of our research study
and explain why we are using a particular method or we are
not using a particular method or technique so that research
results are capable of being evaluated either by the
researcher or others.

Steps:

1) Why a particular research study has been undertaken?

2) How the Research problem has been defined?

3) What way and why the hypothesis (basic idea) has

been formulated?

4) Why a particular technique of analyzing data is used?

(or) How the data were collected?

5) How the collected data were interpreted?

6) What deletion was made?

7) What was the conclusion?

Finally what was the solution for the Research problem?

4

Importance of knowing the subject research

Methodology:

1) A student preparing himself for a career of carrying out

research as his profession

- Will be trained better to do research

- Will help him develop disciplined thinking

- Will help him observe the field objectively.

- Will enable thoroughly to understand the logic

behind the research problem.

- Will increase the ability to evaluate the results.

- Face the evaluated results with confidence.

- Useful in various fields such as Govt. Business,

administration, community development & social
work.

To qualify a Research or study:

To be a Good or perfect one,

The Research adapted should process certain

characteristics,

It must as far as possible be 1) Controlled

2) Rigorous
3) Systematic
4) Valid
5) Verifiable
6) Empirical
7) Critical
5

1. Controlled: The research problem should not be

affected or influenced by external factors (i.e. variables
other than the participating facts).

2. Rigorous: The procedures followed to find answers to

questions should be relevant, appropriate & justified. But
the degree of rigiour may vary from one problem to another
problem.

3. Systematic: The investigation should follow a certain

logical sequence (Not in a haphazard manner)

4. Valid & Verifiable: The findings should be valid &

can be verified by you or others at any time.

5. Empirical: The conclusions drawn should be based on

hard evidence, gathered from real life experiences or
observations.

6. Critical: The process of investigation must be

foolproof and free from drawbacks. The process adapted
and the procedures used must be able to withstand any
critical scrutiny.

Types of Research

Research can be classified from the view point or

perspectives as,

From the view point

Application objective
Inquiry mode
6

1) Pure Research 1) Descriptive 1) Quantitative

Research

2) Applied Research 2) Correlative 2) Qualitative

Research

3) Exploratory

4) Explanatory

1) Pure Research: (Basic or Fundamental Research)

Gathering, knowledge is termed as pure or basic

research. Just to gather knowledge in order to formulate or
generalize theories or policies.

Eg) Research on mathematics.

This types of research adds knowledge to the already

existing organized body.

Applied Research: To find an immediate solution for a

pressing practical problem.

Eg: Social, economical and political trends prevailing in

a country.

Applied Vs Fundamental Based on the objectives of

Research:

1) Descriptive Research:

Survey or fact finding enquires of different

kinds. It describes the actual prevailing
state of affairs, existing at present.

Otherwise known as ex post facts means

existing position of facts / issues.
7

Here the variable influencing the research

has no control or the researcher has no
control over the variables.

Eg: Frequency of shopping, customer preference

etc.

2) Correlative Research:

Goes on to discover the existing

relationship or interdependence between
two or more aspects / variables.

Otherwise known as comparative study.

Investigates association between variables.

Eg: Sum of humour and job satisfaction,

(related variable)

Research problem is workers turnover

Analytical Research:

The researcher has to use facts / information already

existing and analyze these data to make a critical
evaluation.

Eg: document study / historical evidence.

Descriptive Vs Analytical Research:

Explanatory Research:
8

Attempts to clarify or explain why and how, any

particular research problem arises and can be solved.

4. Exploratory Research: Study undertake to explore

a new area or an unknown destination.

III. Based on the Inquiry Mode:

1) Quantitative Research:

Relates to aspects that can be quantified and

expressed in terms of quantity.

Otherwise known as structured Research.

In this type of Research, the objectives, design,

sample and all the other factors influencing the
research is pre determined.

The research problem and its solution will be

expressed in terms of quantity and hence statistical and
economic analysis is adapted in this type of Research.

Quantitative Research:

Otherwise known as unstructured research.

The aspects related to quality / kind or texture.

Eg: Behaviour science

Apart from the above, other types of Research are,

Conceptual Research: Research related to some abstract

idea or theory

Used by philosophers or thinkers for developing new

concepts.

Empirical research
9

(based on experiments or experience)

Otherwise known as experimental type of Research.

The result obtained by adapting Empirical Research is

considered to be most powerful (evidence enclosed)

Based on the time consumed to complete a particular

research,

a) one time Research:restricted to a single time period.

b) Longitudinal Research: Conducted over several time

period.

Qualities of a Researcher

Top 10 qualities of a Researcher

1) Ananalytical mind: Constant analysis on a

variety of factors.

2) A people person : For respondents to get the

best out of interviews / focus groups.

3) The ability to stay calm: especially when you have

pressing deadlines. Keep well focused and think
logically there will always be an end point.

4) Intelligence : Researcher requires critical

analysis, but most of all common sense.

5) Curiosity: Have curiosity and be passionate about

developing deeper to unearth more insight.

6) Quick thinker: Things dont always go as you plan, so

you need to be able to think fast.

7) Commitment: Research is a tough job, the hours

may be long, the deadlines short.
10

8) Excellent written and verbal communication

skills: So that different audience can clearly
understand the findings.

9) Sympathetic: Having a sympathetic ear when

listening to some respondents (cry etc) is a good skill,
to have.

10) Systematic: Check, check and check again.

Spending a proper amount of time for checking always
pays.

According to Micheal Foster,

1) Truthful data / facts desire for accuracy of

observation.

2) No expressions like approximately, almost or nearly.

3) Should poccess alert mind. Nature is constantly

changing, be keen and watchful to notice such
changes, no matter how small or insignificant they
may.

4) Scientific inquiry desire for knowledge it requires

moral courage, Steadfast (constant / not changing)
endurance (to tolerate the difficulty, suffer patiently)

- When a research scientist feel defeated or

completely lost, he needs immense courage and the
sense of conviction (found guilty)

Significance or Importance of Search

1) Doubt is better than over confidence for it leads to

inquiry, inquiry leads to invention. Process or the three
stages of research to bring out economic policies.
11

1) Investigation of prevailing economic structure with

the available facts.

2) Analyse or diagnose the data.

3) Prediction for future developments.

2) Research encourages scientific and inductive thinking.

Eg:- Role of Research in :

1) Econ omics:

Researches done on applied (production and sales

of goods in a profitable manner) economics is
increasing in modern days. Govt. & business sectors
have become more complex, they face several
operational problems to solve this problems,
Research is carried on.

To frame Govt. economic policies.

Govt. budget a formulation depends on the

analysis of needs & desires of the people,
available of revenues needs research.

Decision making requires proper research.

Allocation of a countries scarce resource also

needs research.

2) Business Decisions:

In business sectors there are both planning

and operational problems.

a) Problems Research: Investigation of

the present structure and development of
12

the market relating to purchase,

production, promotion and sales.

b) Operational Research: Relates to

application of logical, mathematical and
analytical techniques to solve market
problems there by minimize cost and
profit maximization.

c) Motivational Research: Helps to

determine people behavior or consumer
response.

All the above three are responsible for business

decision making.

3) Social sectors: To gain knowledge on unknown

aspects and do something better and more
efficiently.

Social scientist gain their knowledge for their own sake

and for the development of the society.

1. Formulating the Research problem:-

a) The formulation of a general topic into a specific

Research problem thus constitutes the first step in a
scientific inquiry.

Two steps are involved in formulating the Research

problem,

a) Understanding the problem thoroughly.

b) Rephrasing the same into meaningful terms from an

analytical point of view.

1. Identify a broad field or subject area of interest to you.

13

2. Dissect the broad area into small area.

3. Select what is of most interest to you.

4. Raise Research questions.

5. Formulate objectives

6. Assess your objectives

7. Double check

The best way to understand the problem is to

discuss with his own colleague or guide.

Examine all available literatures to get himself

acquainted (get used to ) with the selected
problem.

Review two types of literature

Conceptual literature :

Concerning concepts & theories

Empirical Literature : Concerning studies made earlier

which are similar to the one proposed.

Outcome of the review will be the knowledge so as to

pre determine what data or materials are available for
operational purposes.

Next step the Researcher rephrases the problem into

Analytical or operational terms.

PUT THE PROBLEM INTO SPECIFIC TERMS

This step is of greatest importance in the entire

research process.
14

The problem to be investigated must be defined

unambiguously or clearly.

Prof W.A. Neiswanger States,

The statement of the objective of the Research

problem is of basic importance because,

(i) It determines the data which are to be collected

(ii) Characteristics of the relevant data

(iii) Choice of techniques to be used in these

explorations

(iv) Frame a Final report

Step II

Extensive Literature Survey:

A brief summary of the problem should be written

down.

Make extensive literature survey

Sources of survey can be, journals, bio-graphics, Govt.

reports, books, conference proceedings etc.

Based on the nature of the problem.

Earlier study if any which is similar to the study in

hand should be carefully studied.

A good library will be a great help to the researcher at

this stage.

Stage III:

Developing Hypothesis : (Development of working

Hypothesis)
15

State in clear terms the working hypothesis (Basic Idea

of the Research problem)

It is a tentative assumption in order to test to logical or

empirical consequences.

Provide the focal point for research.

Hypothesis should be very specific and very well

limited to the place of research in hand because it has
to be tested.

Hypothesis guides the researched by limiting the area

of Research and keep him on the right track.

It sharpens his thinking and focuses attention on

important facets of the problem.

It indicates the type of data required for the study.

Type of methods of data analysis done.

How to develop working Hypothesis?

1) Discuss with collogues / experts, about the problems,

its origin, its objectives and solutions.

2) Examination of data/ records if available.

3) Review similar studies / similar problems.

4) To secure greater insight into the practical aspects of

the problem conduct personnel investigation or field
interviews.

STEP IV:

Preparing the Research Design:

16

Research design is the conceptual structure within

which research is conduction. It constitutes the blue print for
the collection, measurement and analysis of data.

The function of the Research design is to provide

relevant evidence with minimal expenditure of effort, time
and money. It provides an outline of what the researcher is
going to do in terms of 1) Framing the hypothesis, 2) its
operational implications and 3) finally data analysis

The Research design highlights certain decision,

1) The nature of the study

2) Purpose of the study

3) Location where the study would be conducted

4) The nature of data required

5) From where the data would be collected

6) The techniques of data collection that would be

used

7) What time period the study would cover

8) The type of sample design that would be used

9) The method of data analysis that would be adapted

10) The manner in which the report would be

prepared

Type of Research Design : 4 types

1) Sampling Research Design : Deal with selection of

relevant items
17

2) Observational Research Design: Deals with the

observations (field observations) that is to be made.

3) Statistical Research design: Deals with the

information on the data collected & analysed.

4) Operational Research Design: How the above

three are carried out.

Determining sample Design:

All the items considered in any field of inquiry

constitutes a universe or population. Study of the
entire population without leaving out a single item is
known as Census Study

This type of census study is practically not possible.

So we select few items from the entire population for

our study purpose. The items so selected constitutes
what is technically called sample.

The way of selecting such a sample is known as the

Sample Design.

These samples can be either probability samples or non

probability samples.

Probability: Each item in the population has on equal

chance of being selected for the study.

1) Simple random sampling

2) Systematic random sampling

3) Stratified random sampling

4) Cluster / area random sampling.

18

Non Probability sampling: All the items do not have an

equal chance of being selected for the study.

The selection depends upon the convenience &

judgment of the Researcher.

Mixed sampling: When more than one type of sampling

technique is used for a study, it is mixed sampling.

The sample design to be used in a Research study

must be decided by the researcher considering the nature of
the study.

6. Collecting the Data:

Gathering appropriate data which are made use

in Research study.

Data can be collected in several ways either through

(1) Experiment (or) (2) through surveys.

In experimental means, when a researcher

conducts a research, some quantitative
measurements are observed, based on which, he
examines the truth of the underlying hypothesis.

In case of surveys, data are collected by

1) By observations

2) Through personnel interview

3) Through telephone interviews

4) By mailing of questionnaires

5) Through schedules / enumerators

The Researcher should select one of these methods of

collecting the data taking in account the
19

1) Nature of investigation

2) Objective & scope of Inquiry

3) Financial Resources

4) Time frame

5) Desired degree of Accuracy.

6) Execution of the Project: (Putting a plan)

Important step in Research study.

See that the project is executed in a systematic

manner and in time.

Eg) If the survey done in a project is via

Questionnaire the answers can be machine
coded / processed

If interview were conducted, make sure that the

interviewers is well trained to keep the survey as
much as realistic as possible.

8. Analysis of Data :

After the data are collected the researcher turns to

the task of analyzing the data the analysis of data
require closely related operations, like coding,
Editing & Tabulation.

The wide data collected should be condensed into

small manageable groups, for easy analysis.

Coding: The collected data are transformed into

symbols that may be tabulated or counted.
20

Editing: Unwanted & irrelevant data will be

removed.

Tabulation: Technical procedure where the data

are put in the form of tables.

Research Design:

The most important step after defining the Research

problem is preparing the Research Design

Research design is the conceptual structure within

which the research is conducted.

It constitutes the BLUE PRINT for collection,

measurement and analysis of data.

Research design provides an answer to the question,

what the Researcher is going to do with regards to
framing hypothesis, its operational implications and
how to analyse the data?

Research Design: - Decisions

Highlights certain decisions,

1) Nature of the study

2) Purpose of the study

3) Location where the study would be conducted

4) Nature of DATA required

5) From where the DATA can be collected

6) Time period of the study

7) Type of sample design to be used

8) Techniques of data collection

21

9) Methods of Data Analysis

10) Preparation of Report.

Research Design

May be sub divided into,

1) Sampling design: Deals with, the method of selecting

items for the study.

2) Observational design: Relates to the condition under

which the observations are to be made.

3) Statistical Design: Deals with the no of items

selected or the study and how the selected data will be
analysed.

4) Operation design: The technique by which the

sampling, observational and statistical designs can be
carried out.

Research Design Features :

1) Helps to identify the type and source of information

needed for the study.

2) Specifies the methods to be adopted in collecting &

analyzing data.

3) Specifies the time schedule of the research and the

monetary budget involved.

Concepts Relating to Research Design

1) Dependent and Independent variables :

Variables : A magnitude that varies is known as

variable
22

Continuous variable : Values that can be expressed

even in decimal poins are known as continuous variables

Eg: age (4 years 3 months)

Height (5.2 cm)

Weight (45.3 kg)

Non continuous Variables: Value that can be

expressed only in integer values are called Non continuous
variables

Eg: No. of students in a class ( 45)

No. of children in a family (3)

Statistically known as discrete variables

Dependent or Endogenous variables :

When the change in one variable depends on the

change in other variable, it is known as dependent or
Endogenous variable.

Demand ----- Price (independent)

Independent or Exogenous variable

The variable that causes the change in the dependent

variable is known as independent or exogenous variable.

Demand (Dependent) ------- Price ,Income

Here demand is a dependent variable while price /

income is an independent variable.

Extraneous variable :
23

The independent variable which is not directly related

to the purpose of the study but affects the dependent
variable is know as Extraneous variables.

The influence caused by the extraneous variable on

the dependent value is technically known as
Experimental Error

A research study or a Research design should always

be framed in such a manner that the influence of
Extraneous variables on the dependent variable is
completely controlled and the influence of the
independent variable is clearly evident.

Control:

Good Research design should minimize the effect for

Extraneous variables.

Confounded Relationship

The relationship between dependent and independent

variable is said to be confounded by an extraneous
variables.

Research Hypothesis:

When the formulated hypothesis is tested by adopting

scientific methods, it is known as Research Hypothesis.

Experimental & Non Experimental Hypothesis testing:

When the objective of the Research is to test the

hypothesis, it is Research hypothesis.

Research in which the independent variable are

(handled with skill) manipulated, it is experimental
hypothesis testing.
24

When the variables are not manipulated, it is non

experimental hypothesis testing.

Experimental & Control Groups:

When a group is exposed to usual conditions in an

experimental hypothesis, research it is control Groups.

When the group is exposed to special or certain new

conditions, it is experimental groups.

8. Treatments:

The different conditions to which the experimental &

control groups are subject to is known as treatments.

9. Experiment:Fertilizers and crops)

Process of verifying the truth.

Absolute Experiment:

Determine the fact

Comparative Experiment:

Determine the impact in comparison with

another fact.

10. Experimental units

Pre-determined block to which different

treatments are applied.

Eg : animal testing

Types of Research Design

There are three different types of Research design,

25

1) Exploratory Research Design:

Is a Formulative Research design

Main purpose is the discovery of ideas & insights

Should be flexible enough considering different

dimensions of the problem under study.

2) Descriptive and Diagnostic Research Design:

Descriptive Research Design is concerned with

describing the characteristics of a particular
individual or a group.

Study concerned with narration of facts or

characters related to an individual, group or
institution are descriptive research studies.

Diagnostic Research design determines the

frequency with which a variable occurs or its
relationship with another variables.

Both the Research designs should be planned

carefully.

Research design should be Rigid (No flexibility)

3) Hypothesis testing Research Design:

Test the hypothesis of causal relationship

between two or more variables.

Adopt procedure that not only reduce bias but

enhance reliability and facilitates deriving
Inferences (results) about the Research problem.

Importance of Research Design:

26

Facilitates the smooth flow of the various stages of

Research.

Helps yield maximum information with minimum

effort, time and money.

Helps to plan in advance data collecting and analysis

techniques.

Prepare with utmost care to avoid errors.

Attain reliability

Characteristics of a Good Research Design

Posses the qualities of being flexible, suitable efficient

& economical.

Should minimize bias and maximize reliability of data

collection & Analysis.

No experimental error should be allowed

Should yield maximum information

Research problem should be viewed from different

angles or dimensions.

The choice of Research design depends on,

Nature of the Research problem

Objectives of the Research problem

Skills / ability of the Researcher

Methods of gathering information

Availability of monetary support

Time schedule
27

HYPOTHESIS

A Research hypothesis is a predictive statement, which

is capable of being tested using scientific methods, which
involves independent and dependent valuables. (eg) the
female students perform as well as the male students.

This statement is a hypothesis that can be objectively

tested and verified.

It is a proposition that can be put to test in order to

examine its validity.

Characteristics of Hypothesis

1) A hypothesis should be precise and clear. If not clear,

the inferences will not be reliable.

2) It must be capable of being put to test.

3) It should state the relationship between the variables,

in case relational hypothesis.

4) It should be stated in a simple language.

5) It should be consistant and derived from all known

facts.

6) Hypothesis must be amenable to testing within a

reasonable period of time

7) Hypothesis should explain what it actually to explain.

(the solution for the Research problem). The
explanation should be on empirical reference.

Concepts Relating to Testing of Hypothesis

28

1) Null Hypothesis & Alternative

Hypothesis (Statistical Analysis)

Null Hypothesis: Denoted by H0. If both the variables (say

male or female) or (Head or Tail) are equally good, it is Null
Hypothesis.

Alternative Hypothesis: Denoted by Ha or H1. If one

variable is considered superior to other or vice versa or if
there is a difference, it is alternative hypothesis.

Mean Population (u) or (p)

Total / No. of variables

Null Hypothesis

Ho : u = 100

Alternative Hypothesis

Ha : u = 100
Ha : u > 100
Ha : u < 100

Aspects to be considered while formulating Null

Hypothesis
1) The researcher always tries to reject Null hypothesis
since Alternative Hypothesis should be proved.

2) Null hypothesis when it is actually true, when rejected

involves great risk, the level of significance should be
considered.
3) Null hypothesis should be very specific (No
approximation)
29

The level of significance:

Important concept of hypothesis testing.

It is a certain percentage chosen with great care,

reason and thought
(eg) let us consider the level of significance to be 5%.
It means the Researcher takes a risk of rejecting Null
hypothesis (Ho) by 5% when Ho is actually true.

3. Decision Rule

The researcher should make a decision, if to accept or

Reject Ho.

The decision rule should be decided on the number of

items to be tested and the basic of which to accept or
reject.

4. Type I and Type II Errors

(i) Researcher may reject Ho, when it is true Type I Error

(which must have been accepted).

(ii) Researcher may accept Ho, when it is false Type II

Error (which must have been rejected)

5. One tailed and Two tailed Tests:

(i) One tailed test rejects the Null hypothesis when the
sample mean is either greater or lower than the
hypothesized value of the population mean.

Two tailed Test: When the sample mean is both

greater and lower than the hypothesized value of the
population mean.

Procedure for Hypothesis Testing:

30

1. Testing hypothesis refers whether the formulated

hypothesis is valid or not

2. Whether to Accept or Reject Null Hypothesis.

(i) Making a formal statement:

Making a formal statement of the null hypothesis

and alternative hypothesis.

(ii) Selecting a significant level of testing

A pre-determined level of significance should be

specified.

Either 5% or 1% level can be considered for the

purpose.

(iii) Deciding the Distribution to use:

Choice should be made generally relates to Normal

distribution or t-distribution.

(iv) Selection of random sample & computing an

Appropriate value

Selection of Random sample

Computing suitable value

Drawing a sample for furnishing Empirical data.

(v) Calculation of Probability:

The diverged results from the expected results,

when Ho is true.

(vi) Comparing the probability:

31

By making a comparison with the assumed

significance level.

If the value is less than or equal to Ho, in case of

one-tailed test, Ho is rejected. Here type I error is
committed.

If the value is greater than the mean, Ho is

accepted. Were type-I error is committed.

compile, compare & compute the data and come

out with the inference.

Null Hypothesis: The null hypothesis is the proposition

or proposal that implies no effect on the phenomena.

Alternative Hypothesis: is the one predictive statement

that implies some effect on the phenomena.

Concepts Relating to Testing of Hypothesis:

SAMPLE SURVEY

Sampling Design:

An art of obtaining a sample from a given population.

The technique or procedure the researcher adopts for
selecting items for the sample from the population or
universe.

Steps in sampling Design

Type of Universe:
32

1) The first step in sampling design, is to clearly define

the total number of items / cases to be studied, which
is technically known as UNIVERSE

Finite
Universe
Infinite
Finite Universe: The number of items is certain.
Eg: No. of students in a class.
No. of workers in a factory.
Infinite Universe: The number of items is infinite. (No
idea about the number of items)

Eg: Chennai population, No. of stars

2) Sampling Unit:

A geographical area like a state, district or

village.

Family, religious community or a school.

Individual (Researcher can select one or two such

units).

3) Source List: Otherwise known as Sampling

Frame

Consists of names of all items of a universe.

If not available the researcher has to prepare a

Source list.

It must be reliable, comprehensive, correct and

appropriate.
33

It should be the representative of the

population / universe.

4) Size of sample:

Refers to the number of items to be chosen

from the universe.

Size of sample must be optimum. An optimum

sample may defined as the one that satisfies.

The requirements of representatives.

Flexibility

Efficiency

Reliability

Costs or budget should be considered.

Factors Influencing size of sample :

Parameters of Interest:

The items or parameters are selected based on the

researchers own interest.

Budgetary constraint :

Cost consideration exercises a major influence.

a) Sampling Procedure:

The type or technique used by the researcher to select

the items.

The technique should be selected so that for a given

sample size & budget, the sampling error must be very

small or negligible.
34

Sampling Error: may be caused (In case of Non

probability sampling) due to

(1) Interviewer Bias

(2) Mistakes

(3) Non response problems

(4) Questionnaire design flaws

(5) Data processing & analysis errors

In case of probability sampling, (homogenous items )

the sampling error is negligible since the sample is more
accurate.

Characteristics of a Good sample :

Should bind a truly representative sample.

Small sampling error

Should fit into the budgetary constraints.

Result should be applicable in general.

Characteristics of sample techniques :

1) Much cheaper

2) Saves time

3) Much reliable

4) Suitable for carrying out different surveys

5) Scientific in Nature

Advantages of sampling:

1) Very accurate
35

2) Economical in Nature

3) Very reliable

4) Suitable for different surveys

5) Less time consumption

6) In case of large universe, sampling method is the

only practical method for collecting the data.

Different types of sample Design:

Classified under two general categories.

1) Probability sampling

2) Non Probability sampling.

Probability sampling:

Otherwise known as choice sampling or random

sampling.

Every item has an equal chance of being included in

the sample.

Eg: Lotteries (or) subscribers

When done property, probability sampling ensures that

the sample has a similar composition and profile as
that of the entire population.

7 different types of probability sampling,

1) Simple Random sampling

2) Stratified Random sampling

3) Cluster sampling

4) Systematic sampling
36

5) Area sampling

6) Multi stage sampling

7) Sampling with probability propotional to size

(1) Sample Random Sampling

The sample is drawn so that each person or item has

an equal chance of being drawn during the selection.

Eg: Lotteries (in a ball box)

(2) Stratified Random sampling: (strata layers)

- Stratified sampling technique is generally used

when the population is heterogeneous.

- The entire population is divided into sub population

(sub groups) (i.e. the sub population being
homogenous).

- Items are selected from each stratum.

- This method is more reliable & accurate.

- Eg: 50 students of a school having 1000

students on a total were selected & interviewed on
the interest in music.

The students were grouped based on their age, 7

years, 8 years, 9 years, 10 years & 11 years.

From each age group, 5 students were chosen and

totally 50 students were interviewed.

(3) Cluster sampling:

The entire population is sub divided into mutually

exclusive groups or clusters
37

Simple Random sampling is applied and the need

clusters are selected for the study.

If all the elements found in the selected cluster is

taken for the study, then it is one stage cluster
sampling.

If random sampling is applied in selecting elements

found within the clusters, it is two stage cluster
sampling.

(4) Systematic sampling:

- Selecting every nth element for the study.

1st, 5th, 10th, 15th, 20th .

(5) Area sampling: when the clusters are in the form of

some geographical sub divisions.

(6) Multi stage sampling:

- If the researcher selects elements or items at different

stages, it is multi stage sampling.

- Eg: Survey of work efficiency in nationalized baulks

- Stage level

- District level

- Towns

- Villages

Items are selected at four stages / levels.

(7) Sampling with probability proportional to size:

- The probability of inclusion into the study is directly

proportional to the size of the clusters.
38

- This technique is used when the no. of elements

present in each cluster varies.

- Depending on requirement of the researcher the

cluster which is more appropriate can be selected for
the study.

II. Non Probability sampling:

- Each item does not have an equal chance of being

included in the sample.

- 3 types of non probability samplings are,

1) Convenience sampling

2) Quota sampling

3) Judgmental sampling

1) Convenience sampling:

- Choosing items at the convenience of the

Researcher.

Eg: Street interviews (sampling of people who

are at easy access)

Drawback: Lack of accuracy

2. Quota sampling

The researcher simply assume quotas, with certain

restrictions imposed on how they should be selected.

Eg: Caste basic

Benefits: less expensive, very convenient

3. Judgment sampling : (otherwise known as purposive

sampling)
39

Researcher employs his own Expert judgment about

who to include in the sample frame.

Disadvantages of sampling:

1) Inadequacy of samples

2) Chances of bias

3) Problems of accuracy

4) Difficulty of getting the representative sample.

5) Untrained Manpower.

6) Absence of Informants

7) Chances of committing errors.

Sampling Error: Sampling error is the deviation of the

selected sample from the true characteristics, traits,
behavior, qualities or figures of the entire population.

Data Collection

Data Collection is the systematic gathering of

information (data) for a particular purpose from various
sources. (Various sources can be questionnaires, interviews,
observations existing records and electronic devices).

Two Important sources of Information are,

(i) Primary Data

(ii) Secondary Data

Primary Data:

Refers to the data collected for the first time (Original

data)

Example: Proceedings from conferences meetings,

Students records.

Secondary Data:
40

Refers to the data that have already been collected

and used earlier by somebody or some agency.

Example: Online database, Historical books etc.

Example: Taking census (total population) of Government

of India Primary Data.

When research is done by some other scientist on the

basis of this data, it is secondary data.

Selecting A particular source of Data depends on,

(1) Purpose & Scope of the study.

(2) Availability of time.
(3) Availability of Resources.
(4) The degree of Accuracy desired.
(5) Statistical tools to be used.
(6) Sources of Information (data).

1. Purpose & Scope of Data Collection:

Should be clearly stated at the very beginning of the

study.
A statement indicating the Research problem and the
type of information needed for the study in order to
solve the Research Problem, is needed.
Its purpose is to establish a factual information for
making decisions.
Scope of the enquiry means the coverage with regard
to the type of information, the subject matter and
geographical area.

(b) Availability of Time:-

The investigation should be done within a reasonable

period of time.
41

Taking which the information collected may become

outdated.
Example: Demand of a new product launched is
studied, if the result comes out after 2 years, by the
time the producer may attain great lose.

So, make sure the investigation is carried out within a

reasonable period of time.

(c) Availability of Resources:

Investigation or data collection greatly depends, on

resources available like,
1. No. of skilled personnel
2. The Financial Position.

If the no.of skilled personnel to carry our the enquiry is

sufficient and the availability of funds is not a problem,
the datas can be collected from a big area covering a
good number of samples.
(d) The desired/expected Degree of Accuracy:-

Deciding the degree of accuracy is a must for the

investigator.
Because Absolute Accuracy is not possible in
statistical works.
Since Statistics is based on estimates, tools used for
measurements in not always perfect & there may be
unintentional bias on the part of the investigator,
enumerator or informant.
Generally the degree of accuracy depends upon the
objections of the enquiry.
42

Example: During purchase of Gold, even 1/10 th gram in its

weight is significant.

But it is not the same in case of purchasing rice or

wheat.

(e) Statistical Tools to be used:

Well defined or identifiable object or group of objects

that can be measured or counted in a statistical
investigation is called statistical Unit.
In the absence of a clear and precise Statistical Unit
Serious errors may be committed by collecting
irrelevant data. This will ultimately lead to fallacious
(Wrong) conclusions.
(f) Sources of Information:

The researcher has to decide about the source from

which the information can be obtained or collected.

1. First hand data.

2. The data from other published sources.
(Publications, Journal, Magazines etc.)

(g) Method of Data Collection:-

1. Primary Data.

2. Secondary Data.

Primary Data:-

First hand data.

Either Census or Sample technique is to be used.
43

Census: Total no.of items have to be investigated.

Sample: Selected representatives from the total population

have to be investigated.

CENSUS SAMPLE
Total No. of items, 100% Selected Representations,
Accuracy attained, Time 100% Accuracy cannot be
consuming, Expensive More attained, Less time taken, Less
Labour. expensive, Less Laborious.

Should be very cautious and careful while choosing a

particular method.
Methods of Collecting Primary Data:

May be obtained by applying any of the following

methods,
1. Direct Personal Interviews.

2. Indirect Oral Interviews.

3. Information from Correspondents.

4. Mailed questionnaire methods,

5. Schedule sent through Enumerators.

1. Direct Personal Interviews:

A face to face contact is made with the informants.

Interviewer asks them questions regarding the study
and tries to get the desired information.
The information thus collected is first hand and
original.
44

Merits:

(i) Response is encouraging when personally

contacted.
(ii) Information are more accurate (if not found
accurate, he can be reexamined or Cross-examined,
there by try to obtain the information).
(iii) Provides hope for getting supplementary
information, which may be of greater use latter.
(iv) A delicate situation (Some Personnel Questions) can
usually be handled more effectively by a personnel
interview than other survey techniques.
(v) The interviewer can adjust the language according
to the status and educational level of the person
interviewed, thereby can avoid inconvenience and
misinterpretation.
Demerits:

(i) Expensive when the no. of informants is large.

(ii) Greater chance of personnel bias and prejudice.
(taking a decision before finding the full facts).
(iii) Interviewer should be thoroughly trained &
experienced. (untrained personal will spoil the
work)
(iv) Time consuming (Interviewers can be contacted
only at the convenience of the informants)
Conclusion:

Direct personal Interviews can be used in Intensive

Field Survey rather than Extensive Field Survey.
The present day of extreme advancement in
communication system, a good number of survey, can
45

be conducted by News papers & television channels by

replying through e.mails & SMS.
They are less expensive & extremely quick.
Defects No Phone or Television, delicate & sensitive
Questions cannot be asked, value answers.
2. Indirect Oral Interviews:

The investigator contact a third party called

Witnesses who is capable of supplying necessary
information.
Generally adopted when the information to be
obtained is complex or the informer is not willing to
reveal the answers.
Example: When a drug addicted person is interviewed, he
will not be willing to response directly, so the information
are gathered via agents (may be relatives).

The accuracy of this method depends on,

(i) The proven integrity of the Agency/Person.

(ii) Ability of the interviewer to act the right information
from the witness.
(iii) Bribery or other reasons may twist the witness to
give false information there by bringing a wrong
conclusion.
Conclusion:

(i) Let more care should be taken in the selection of

Witness because it is on their views, the final conclusion is
reached.

3. Information From Correspondents:

46

The investigator appoints local agents or

correspondents in different places to collect
information under this method.
These correspondents collect the information and
transfer or transmit the information to the central
office where the data are processed.
Example: News paper Agencies.

Generally these Agencies are paid staff, sometimes

honorary.
Advantages:

1. Cheap
2. Can be used to get regular information at regular

intervals (daily, weekly or monthly).

Disadvantages:

(i) Lacks Accuracy.

4. Mailed Questionnaire Method:

A list of questions pertaining to the survey is known as

Questionnaire. It is prepared and sent to various
informants by post.
The questionnaire contains questions and provides
space for answers.
A request is made to the informants through a
covering letter to fill up the questionnaire and sent it
back within a specified time.
The questionnaire studied can be classified as,

1) The degree to which the questionnaire is formalized or

structure.
2) The disguise/lack of disguise of the questionnaire.
47

3) The communication method used.

4) When no formal questionnaire is used, interviewers
adopt other tactics like showing pictures on which
respondents comments.
When a research follows a prescribed sequence of
Questions it is structured study.
When no prescribed sequence of Question exists, the
study is Non-Structured.
When the questionnaire is constructed in such a way
that the Objective is clear (the questionnaire) it is
known as Non-disguised.
When the objective is not clear, the questionnaire is a
Disguised one.
On this basis, 4 types of studies can be distinguished,
(i) Non-disguised Structured.
(ii) Non-disguised Non-structured.
(iii) Disguised Structured.
(iv) Disguised Non-Structured.
Merits: Questionnaire Methods,

(1) Easily adopted in large populations and when the

informants are wide spread over a large geographical
area.
(2) Relatively cheap & timely.
(3) Information pertaining to personnel life or family or

confidential matters will be revealed in written rather

than personal interviews or telephones.
Demerits:

(1) Applicable only among literate people.

(2) Uncertainty of the Respondents lacks co-
operation.
48

(3) Lacks Accuracy because the information may not

be correct.
Guideline to make this method more Effective:

(i) Prepaid postage stamp should be affixed.

(ii) Sample should be large.
(iii) Questionnaire should be interesting.
(iv) Legal Compulsion should be made to provide in
formations.
5. Schedules sent through Enumerators:-

Sending Schedules through enumerators or

interviewers.

The enumerators contacts the informants, gets replied

to the questions contained in the schedule and fill
them in their own handwriting.
Here the questions are asked face to face and the
response is papered.
Merits:

(1) Applicable among illiterates.

(2) Very little scope for Non-response, as the
enumerators go personally.
(3) Information are more Reliable & Accurate.
Demerits:

(1) Expensive Since enumerators are paid

personals.
(2) Success depends on the efficiency of the
enumerators.
(3) Interviewer requires training and experience.
(4) Variations in answers must be removed to avoid
variations.
Secondary Data:
49

Are those data which have already been collected and

analyzed by some earlier agency for its own use and later
the same data is used by a different agency.

Sources of Secondary Data:

(1) Published Sources.

(2) Unpublished Sources.
1. Published Sources:

The Government, Inter National and local agencies

publish statistical data.

Chief Among them,

(i) Inter National Publications:-

Inter National Institutions & bodies like I.M.J.

(International Monetary Fund), I.B.R.D. (International Bank of
Reconstruction and Development), I.C.A.F.E. (International
Conference on Agriculture & Food Engineering) and U.N.O.
United Nations Organization publish regular & occasional
reports on Economics & Statistical matters.

(ii) Official Publications of Central & State

Governments:

Several departments of the Central and State

Governments publish reports on different subjects.

Example:- Publications are,

(a) Reserve Bank of India Bulletin.

(b) Census of India.
(c)Statistical Abstract of the states.
(d) Agricultural Statistics of India.
(e) Indian Trade Journal.
(iii) Semi Official Publications:
50

(a) Indian Statistical Institute (I.S.I)

(b) Indian Council of Agricultural Research (I.C.A.R.)
(c)Indian Agricultural Statistics Research Institute
(I.A.S.R.I.)
Publish the findings of their research programs.

(iv) Publications of various commercial and financial

institutions.

(v) Reports of various committees & commissions

appointed by the Government.

(a) Raj Committees Report on Agricultural Taxation.

(b) Wanchoo Committees Report on Taxation & Black

Money.

(vi) Journals & News Papers:-

Powerful source of secondary data.

Current & important matter can be obtained.
From Journals & News papers like Economic Times,
Commerce Capital, Indian Finance, etc.,
Unpublished Sources:

Records maintained by Government & Private Offices.

Theses of Research Scholars from universities &
institutions.
Precautions in the use of secondary Data:

Proper scrutiny is made before they are used by

investigator.
Be Extra-Cautious while using secondary data.
Should not be accepted as such because the
secondary data may process,
51

(Bias, Inadequate Size, Substitution, errors of definition

or arithmetical errors)

Factors to be Considered before using the secondary

Data:

(i) Suitability of Data:

make sure that the data available is suitable for the

purpose of enquiry.
(ii) Adequacy of Data:

Make sure that the data are sufficient or adequate for

the present analysis.
(iii) Reliability of Data:

The reliability of data is must, without which there is

no meaning in the research.
The reliability of data can be tested by finding the
agency that has collected the data, if the agency has
used proper methods for collection the data.
EDITING:

Once data have been obtained from primary or

secondary sources the next step in a statistical investigation
is to edit the data. (to Scrutinize).

Objective, editing is to detect possible errors and

irregulations.
Editing needs great care and attention.
Editing Secondary data is simple but the data
collected from survey (Primary Data) need excessive
editing.
Editing Primary Data,

(i) The data should be complete in every respect.

52

(ii) The data should be accurate.

(iii) The data should be consistant.
(iv) The data should be homogenous
1. Editing For Completeness:

The editor should see that each schedule or

questionnaire is complete in all respects.
Answers to every questions is furnished.
If not answered, try to meet them in person to get the
answers.
If not just mark No Answer.
2. Editing For Accuracy:

The reliability of conclusions depends on the

correctness of in formations.
If the information is wrong, the conclusion can never
be valid.
Editor should see that the in formations are accurate
in all respects.
Arithmetic errors can be detected easily & corrected.
If the error is due to fault information supplied, it may
be difficult to verify.
3. Editing For Consistency:

Editor should see that the answer to questions are not

contradictory in nature.
Example: Are you a student? No which class do you study?
X

The answers are contradictory and such answers

should be classified.

4. Editing For Homogeneity:

Understand the questions in the same sense.

53

Check uniform interpretation and make sure the

information supplied by the various informants are
homogenous & uniform.
Example: Income (Yearly, Monthly, Weekly, Daily)

Choice Between Primary & Secondary Data:

A proper choice between the type of data (Primary or

Secondary) needed for a particular statistical investigations
is to be made by considering the nature, objective, scope of
the study, time frame & finances and the degree of
precision aimed at, and the status of the Agency.

Now, Secondary data are generally used from fairly

reliable published data by Government, Private
organizations and research agencies, periodicals
magazines etc.,
In fact, primary data are collected only if there do not
exist any secondary data.
In some cases both Primary & Secondary data may be
used.

QUESTIONNAIRE

Questionnaire can be defined as a group of questions

designed to collect information from a specific subject.

(or)

List of questions sent to a number of persons for

getting answers and which obtains standardized results that
can be tabulated and treated statistically.

(or)
54

Media of communication between the investigator and

the respondent.

Generally used in social research when the population

is varied, large, diverse & Scattered.

Should be designed with utmost care & caution so that

all the needed information are collected without any
difficulty.
Drafting a Good questionnaire Requires Care, Skill,
Wisdom, efficiency and experience.

Points to Remember: While Drafting A Questionnaire

(1) Size of the Questionnaire:

(a) No. of questions should be as small as possible

depending on the nature, objectives & scope of the study.

(b) Large no.of questions may irritate the informants and

may be difficult to Edit or Scrutinize by the investigator.

(c) Avoid irrelevant and unimportant questions.

(d) Average No. of questions should be 15 to 25 (at the

most).

(e) If it is more than 25, divide it into various sections.

2. The Questions should be Clear:

Should be Easy, Brief, Unambiguous(Clear in

meaning), Non offending, courteous in tone,
corroborative (Supportive) in nature & to the point.
3. The Questions should be arranged in a Logical
Sequence:
55

When arranged Logically, the answers can be easily

tabulated or coded and does not leave any chance of
omissions.
Example: To find if a person owns a television.

4. Questions should be simple to understand:

Vague & Double meaning words should be avoided.

Example: Price/Cost/Rate/ Capital Income/Salary.

5. Questions should be Comprehensive(Includes

Everything) and Easily Answerable:

Questions should be comprehensive (i.e.) it should

include all the needed in formations.
Easy to be answered. Avoid mathematical calculations
like Ratios, Percentages etc.,
6. Questions of Personal And Sensitive Nature Should
Not Be Asked:

Avoid personal questions which the respondent may

feel shy or irritated to answer.
Example: Do do drink ?

If such questions are unavoidable, a highest amount of

politeness should be used.
7. Types of Questionnaire:

(a) Shut Questions:

Where possible answers are suggested by the frames

& the respondents are requested to the tick one of
them.
Two types of shut Questions.
(i) Simple Alternative Questions:
56

(Otherwise known as Dichotomous questions) Choose

from two clear cut alternatives Yes or No/ Right or Wrong.

(ii) Multiple Choice Questions:

When it is difficult to define a clear cut alternative,

additional Questions between Yes & No is inserted,

Example: To find if a person smokes? Do you smoke?

(a) Yes, Regularly ( )

(b) No, Never ( )

(c) Occasionally ( )

(d) Seldom (rarely) ( )

Easy & Convenient to answer.

Save Time.
Easy to tabulate.
8. Leading Questions should be Avoided:

Long Questions leading to several answers should be

avoided. It should be framed into short questions.
Example: Why do you use a particular type of car, say
Maruti Car, Avoid this continuous questions.

Instead ask,

Which car do you use ?

Why do you prefer it ?

9. Cross Checks:

Should be designed to provide internal checks on the

accuracy of the in formations given by the
respondents.
57

10. Pre-Testing the Questionnaire:

Try out the Questionnaire on a small scale before using

in a large scale.
The drawbacks, short comings and problems faced in
the small scale informants can be improved or
modified when used in large scale.
11. A Covering Letter:

A Covering Letter should be enclosed for the purpose

regarding definitions, concepts & purpose.
Attach a self addressed envelope in case of mailed
questionnaire.
Mentions about Awards or incentives for quick reply.
Promise to send a survey copy of the report.
--------------

SAMPLING

A carefully designed sample may actually be better

than a poorly planned and executed census.

Merits:

1. It saves time:

Saves time because fewer items are collected and

processed.

2. It Reduces Cost:

Since only few items are studied, there is reduction in

cost & reduction in man power.
58

3. More Reliable Results can be Obtained:

Sampling is more Reliable because

(i) fewer chance of sampling error.

(ii) Experience, Trained & Technical people can be employed

to process & analyze the data.

4. It provides more detailed in formations:-

More detailed information can be obtained by sample

survey.

5. Only Sampling Method to depend upon:

When the population is large and finite, the only

method applicable is sampling.

6. Administration Convenience:

The organization and administration is easy in sample

survey.

7. More Scientific:

Results can be tested since more scientific.

Shortcomings (or) Demerits

1. Illusory (False) Conclusion:

If sampling is not carefully planned & executed, the

conclusions may be false.

2. Sample Not Representative:

If the sample taken from the population is not the right

representative, the result may be false or misleading.
59

3. Lack of Experts:

If there is a lack of experts to plan, execute and

analyze the samples, the result would be unsatisfactory.

4. Personal Bias:

There may be personal bias & prejudice in choosing

the sampling techniques.

5. Size of Sample:

If the size of the sample is not appropriate, it leads to

untrue conclusions.

Essentials of Sampling:

1. It must be the right representative:

The Sample selected should process the similar

characteristics of the original universe.

2. Homogeneity:

Selected samples should be homogenous with the

samples & the universe.

3. Adequate Samples:

A good number of items should be included for the

study.

4. Optimization:
60

A proper size of sample should be maintained to have

optimized results in terms of cost & efficiency.

Statistical Laws:

Induction:

The logical process of drawing a general conclusion

from the study of representative items is called Induction.

Sampling is based on two fundamental principles of

Statistics theory

(i) Law of Statistical Regularity

(ii) The Law of Inertia of Large Numbers.

The Law of Statistical:

Regularity: (Mathematical Theory of Probability), States,

A moderately large number of items chosen at

random from a very large group are almost sure to have the
characteristics of the large group.

Proof:

1. Average income of 1,000 people is to be found out,

2. We take a sample of 100 people & find the average.

3. Another person takes 100 people & find the average.

The Average income found by both the persons will

have least difference.

If the average income of the same 1000 people is

found out by census, the result will be more or less the
same.

2. Law of Inertia of Large Numbers:

61

It States, Other Using being equal, as the sample size

increases, the results tend to be more accurate & reliable.

Sampling Error:

The deviations or difference between the actual

population and the sample representative.

Reasons For Sampling Error:

1. Faulty Selection of Sample

2. Substitution

3. Faulty Demarcation (Demographic limit) of

sampling Unit:

In case of Area sampling the sampling units at the

borders should be decided if to take it or reject it.

4. Faulty estimation techniques:

Wrong selection of sampling techniques.

Types of Sampling Errors:

(i) Bias Error:

Caused due to bias or prejudice on the part of the

informant.

(ii) Unbias Error:

Error caused due to the Normal Course of

investigation.
62

Reducing Sampling Error:

Sampling Error can be reduced by increasing the size

of the sample.

--------

EXPERIMENTS

Experiment is the process of examining the truth of a

statistical Hypothesis related to some research problem.

Experiments are of two types,

1. Absolute Experiment.

2. Comparative Experiment.

Absolute Experiment:

When a researcher wants to determine the impact of a

fertilizer on the yield of a crop, it is a case of Absolute
Experiment.

Comparative Experiment:

When a researcher wants to determine the impact of

one fertilizer as compared to the impact of some other
fertilizer, it will be called as Comparative Experiment.

Research Design are of three types,

1. Research design in case of descriptive & diagnostic

studies.

2. Research design in case of exploratory Research studies.

3. Research design in case of Hypothesis Testing Research

Studies.
63

Research Design In case of Hypothesis Testing

Research Studies:

Hypothesis testing research studies are generally

known as Experimental studies.
The researcher test the casual relationship between
the variables.
Professor Fisher is considered as the pioneer of this
type of studies. (Experimental Studies)
He performed this study when he was working at a
Agricultural Research Station in London.
His found out that, by dividing plots into different
blocks and then by conducting experiments in each of
these blocks, whatever in formations is collected and
inference drawn from them can be more reliable
Professor Fisher laid three principles of Experimental
Designs,
1. The Principal of Replication
2. The Principal of Randomization.
3. The Principal of Local Control.
The Principal of Replication :

The Experiment should be repeated more than once.

The treatment is applied to many experimental units.

The information collected and the inference drawn
from these experimental units will be more reliable
and statistically accruable.
Aim: To examine the effect of two varieties of paddy.

Example: A paddy field is divided into 2 parts. Grow one

variety in one part and the other variety in the other. Then
we compare the yield of the two parts.
64

Draw conclusion on that basis.

No Principle of Replication is

Field
rrrrr rrrrr
Part I rrrrr rrrrr Part I
rr rr
Treatment Compare the yield of
rrrrr rrrrr
the two parts.r r

One variety Another

of Paddy Variety of Paddy.
When Principle of Replication is used:

First divide the field into several parts.

Grow one variety in half of the parts and the other
variety in the remaining parts.
Collect the information of the two varieties and draw
the conclusion by comparing both.
The Results so obtained will be more reliable and
accurate compared to the results drawn without using the
principle of Replication.

The Experiment can be repeated several times.

Field

rr rr R r r
Treated
rr rr R r r
rr rr R r r
rr rr R r r Conclusion drawn.

rr rr R r r
65

Parts

2. The Principle of Randomization:

Principle of Randomization Provides us a protection

against the effects of Extraneous Variables.
The variations or effects caused by these extraneous
variables can be combined under the heading
Chance.
Example: When the researcher grows one variety of paddy
in the first half of the field and the other variety in the next
half of the field, there may be a possibility or chance that
the soil fertility of the first half of the field may be different
in comparison to the next half.

In this case, he may go on to cultivate the two

varieties of paddy in different parts of the field on the
basis of some random sampling technique.
(i.e.) He may apply Randomization principle and protect
himself from the effects of the Extraneous Factors.

By using Randomization Principle a better estimate

can be drawn.

rr rr r r r
rr rr r r r
rr rr r r r
rr rr r r r
rr rr r r r
66

When treated

Conclusion
drawn is more
accurate.
(Can protect Effects of Extraneous
Variables)

3. The Principle of Local Control:

The extraneous variable which is a known source of

variability can be made to vary extensively or
deliberately over a wide range.
Now the variability it causes can be measured and
eliminated.
In short, through the principle of Local Control, we can
eliminate the variability due to extraneous factors
from the experimental error.
The extraneous variable is brought to a control.

Kinds of Experimental Design:

67

Experimental Design refers to the framework of the

structure of an experiment.
Classified into 2 Broad Categories,

1. Informal Experimental designs.

2. Formal Experimental designs,
Informal Experimental Designs:

Designed based only on the difference between the

magnitudes or performance.

Three Types,
1. Before and after without control design.
2. After Only with Control design.
3. Before and after with control design.
Before and after without control design:

Consider a test group,

Step.1: The dependent variable is measured before

introduction of the treatment.

Step.2: The treatment is introduced.

Step.3: The dependent variable is measured after the

treatment has been introduced.

Step.4: Inference:

The effect of the Treatment : The level o the

phenomenon after the treatment.

The level of the phenomenon before the treatment.

68

Test Area Level of Phenomenon Treatment Level

of Phenomenon
Introduced

Before Treatment (X) After Treatment

(Y)

Effect of the Treatment = (Y) (X)

Demerit:

With the passage of time, several extraneous variable

may be there in the treatment effect.

(2) After only with control Design:

Step.1: Two Areas are selected, the control Area & the test

area.

Step.2: The treatment is introduced in the test area alone.

Step.3: The dependent variable in both the areas are

measured, at the same time.

69

Step.4: Treatment Effect is calculated by subtracting the

value of the dependent variable in the control area from its

value in the test area.

Treatment: 1

Effect = Value of dependent variable in the

control Area Value of Dependent Variable in the test area.

Test Area Treatment Introduced Level of

Phenomenon (Y)

Control Area No Level of

Phenomenon (Z)

Treatment

(3) Before And After with Control Design:

Step.1: In this design, two areas are selected and the

dependent variables in both the areas are measured for an
identical time period before treatment.

Step.2: Treatment is introduced only in the test area.

Step 3 : The dependent valuable is measured on both the

areas (control
area & test area) for an identical time period.
Setp4 : The effect of the treatment is determined by
subtracting the change in the dependent valuable in the
control area with the charge in the dependent valuable of
the test area.
70

Treatment :-

Effect = ((Y) (X)) ((Z)-(A))

Merits: Avoids Extraneous variables resulting from passage of

time and non

comparability of control and test areas.

II Formal Experimental Design:

Offer relatively more control and use specific statistical

procedures for analysis types,

1) Complete Randomized design (Generally called C.R.

Design)
2) Randomized Block Design (R.B. Design)
71

3) Latin Square Design (L.S. Design)

4) Factorial Designs .
(1) Completely Randomized Design :-

Involves two principals, the principle of replication and the

principle of Randomized of the experimental designs.

The items are randomly assigned do experimental

treatments.

This design is simpler and easier.

Example: It the research has 2 items of 20 parts and if he
wishes to test to under treatment B, this completely
randomized design gives every possible group of 10 items
selected from a set of 20, an equal chance of being
assigned to treatment A & treatment B.

One way analysis of variance (one way ANOVA) is used to

analyze such a design.

2. Randomizes Block Design:-

The subjects or items are first divided into groups, known as

Blocks

See that, the items in each group or black is homogenous.

Randomly select items from each given block and assign

treatment.

Extraneous variables can be fixed and can be measured.

72

The main feature of this study is, each treatment appears

the same no of times in each block.

This design is analyzed two way analyses of variance (two

way ANOVA) technique.

3. Latin Square Design:-

Used in Agricultural Research.

L.S Design is used when two or more extraneous

variables is found.

Example: Effect of fertilizer on the field of wheat is do be

determined.

Here along with the effect of fertilizer, the fertility of the

soil must be considered.

If the facility of the soil is not considered along with the

fertilizer the result obtained may be dependable.

Similarly the impact of the various seeds used many also

vary the yield.

To over come this difficulty L.S design is used.

Each fertilizer (X1, X2, X3, X4, X5) will appear 5 items
but will be used only once in each row and in each
coloumn.

Example: No treatment occurs more than once.

I II III IV V

X1 A B C D E
X2 B C D E A
X3 C D E A B
73

X4 D E A B C
X5 E A B C D

Conclusion :

The field is divided into several blocks (I, II, III, IV & V) and

there are variety of fertilizer (X1, X2, X3, X4, X5).

But each fertilizer is used in each block only once.

a two way ANOVA technique.

4. Factorial Design :

Are used in experiments where the effect of the depended

variable, when affected by more than one variable is to be

determined.

Used in social & economic studies where usually large no of

factors affect a particular problem.

Factorial design are of two types:

I . Simple Factorial design

II. Complex Factorial designs.

Simple Factorial Design :

When the effect of the dependent variable is affect by only

two factors, it is simple factorial designs.

Otherwise known as TWO factors Factorial Design.

Complex Factorial Design :

74

This design is used when more than two factors at a time

affects the dependent variable.

Or the design considers three or more independent variable.

The greater the no of independent variable, the higher the

order of interaction, analysis possible.

Advantage :

Accuracy

Can determine the effects of more variable in a single

experiment.

OBSERVATION

Observation is defined as a planned method of watching

that involves constraints (steps) to improve accuracy.

Characteristics of Observation :

i. Observation are direct

ii. takes place in natural situations

iii. Less Structured.

75

iv. Makes only quantitative study.

Applicable in :

1. Life styles

2. Encounters / Settlement.

3. Relationships

4. Groups / Organization.

Acc. to Block & Camion :

1. Observed in natural surroundings

2. Understands events affecting social relations.

3. Identifies regulatives in social life.

4. Hypothesis free enquiry.

5. Avoids manipulations of independent variable.

6. Recording is not selective.

Differentiate Experimental Technique & Observation

Technique :

Experimental Technique Observation Technique

No such controls Few Controls.

Not Always Observation is natural

conducted in large unit. Fewer
Conducted in smaller units
subjects are watched for long
No so. Study is towards period .Study is directed
76

sharpening the judgment. towards sensitizing the

observer / events.
No so.
Behavior observed is more
different.

STATISTICAL ANALYSIS

Probability: IS a measure of the expectation that an certain

event will occur.

Probability value ranges from 0-1.

The Main terms pertaining to probability theory:-

1.Random Experiment: An experiment which can be repeated

under the same conditions and the outcome cannot be prod iced

is known as Random Experiment.

Example:- When a coin is tossed, we cannot predict whether

head or tail is going to occur.

77

2.Sample Space:- A set of possible outcomes of a random

experiment is know as sample space.

Example: When a coin is tossed twice the possible outcomes are

HH, HT, TH & TT, IT is represented,

S = (HH, HT, TH, TT)

3.An Event: Any possible outcome of an experiment is know as

an event.

Example: When a coin is tossed twice, HH is an event.

An event can be classified as,

a. Simple Event: Which has only one sample point

Example: HH, TT.

b. Compound Event: Which has more than one sample point.

Example : TH.

d. Complimentary Event : A and A are complementary events,

if A consists of all the sample point which is not included in A

than the sum of the probability of the sample space is equal to

1.Hence P(A)-P(A) P(A)+P(A) = 1 P(A) = 1 P(A).

Example: When a dice is thrown, the probability of odd Numbers

turn up are complimentary to even number turn up.

A = 1,3,5
78

A1 = 2,4,6

e. Mutually Exclusive Event: A and B two mutually exclusive

event, if A prevents the occurrence of B.

Example: When a coin is tossed once the occurrence of Head

prevents the occurrence of Tail.

If A and B are mutually exclusive events than the probability of

occurrence of A or B is the sum of their individuals probability.

P(AUB) = P(A) + P(B).

If A and B is joint sets, than the addition theorem of probability

can be stated as.

P(AUB) = P(A) + P(B) P(AB)

f. Independent Event: A and B are in dependant event, if the

occurrence of A does not influence the occurrence of B these two

events are called independents events.

Example: When a coin is tossed twice the occurrence of head in

the first toss dose not influence the toss in the second coin.

Product of A and B is the product of their individuals probability

P(AB) = P(A) X P(B).

Probability Distribution: IF X is total no of success discrete

Random variables which takes the value of X1,X2, X3........... Xn,

P1,P2,Pn then follows the probability distribution.

79

Properties of probability Distribution / 2 Main properties:

1. P(X1) is greater than or equal Zero and less than or equal /

one (Expressed in fractions).

2. The sum of all be probability distribution will be equal to

one.

Example: When a coin is tossed Twice the probability

distribution is, X( probability of obtaining hed) = 0,1,2 P(X1) = ,

, = .

Expectation of Probability: Let X be the discrete Random

Variable, which takes the value X1, X2, X3..........Xn

Respective probability is P1, P2, P3 ............ Pn

Expectation of Probability distribution: P1X1 + P2X2............PnXn.

Probability Distribution = (0 x 1/4) + (1 x 1/2) + (2 x ) = 1.

Binomial Distribution: A Binomial experiment is a statistical

experiment. It has the following properties,

(i) The experiment consists of n repeated trials.

(ii) Each trail can result in just two possible outcomes. We

call one of this outcomes as Success and the other

Failure .

(iii) The probability of success is denoted by P, in every trail

and the probability of failure is denoted by l p or q.

(iv) The trials are independent.

80

(v) The outcome on one trail dose not affect the outcome of

other trials.

Notations: X The number of successes that result from the

Binomial Experiment.

n - The no of trail in the binomial experiment.

P The probability of success on an individual trial.

C - No of coefficient .

Binomial Formula : Suppose a Binomial experiment consists of n

------- and result in X successes & if the probability of success on
an individuals trial is P, then the Binomial probability is B (x, n,
p) = nCx X Px X (1 P)
4

Coefficient of Binomial Distribution: The binomial coefficients are

the coefficients in the expansion of two terms (x + 1)n.

The coefficient of xr in (x+1)n is denoted by nCr or (n/r).

Example: The coefficient of (x+1)2 = (x+1) (x+1)

= 1x2 + x +x+1

= 1x2 + 2x +1

The Confidents are = 1+2+1

The coefficient of (x+1)3 = (x+1) (x+1) (x+1)

= (x2+2x+1) (x+1)
81

= x3 + x2 +2x2 +2x +x+1

= x3 + 3x2 +3x +1

The Coefficient is = 1. 3 .3 1

The Pascal triangle lists out all the Binomial Coefficient.

1 1

1 2 1 (x+1)2

1 3 3 1 (x+1)3

1 4 6 4 1 (x+1)4

1 5 10 10 5 1 (x+1) 5

1 6 15 20 15 6 1 (x+1)6

1 7 21 35 35 21 7 1 (x+1)7

Example: A coin is tossed Four Times what is the probability of

obtaining two or more heads? .

Step I : When a coin is tossed One time, the probability of Head

of tail is equal,

(ie) P = q =1/2.

Step II : The various possibilities of Head and tail events will be,

(p+q)4 = 1p4 + 4p3q +6p3q + 6p2q2 + 4pq3 +1q4

-------------------------------------------------------------

1p4 = (1/2) where P = 1/2) (q = 1/2.)

= x x x 1/2
82

= 1/16

4p3q = 4x(1/2)3 x = 4 x x x x

6p2q2 = 6 x(1/2 x x x1/2 = 3/8

Therefore, the probability of obtaining 2 or more heads is,

3/8 + + 1/16 = 11/16

2. POSSION DISTRIBUTION:

When P is very small (Success rate is extremely small) and

n is very large (total no of trail items of events is large) then

POISSON distribution is used.

P O (Successes approach zero) (np = m is finite)

The experimental result in outcomes that can be classified

as Successes or failure).

X The Actual Number of successes that occurs in a specific

region.

P (x, u) = (eu) (ux)

------------------------
x1
83

This is Poisson formula here we conduct a Poisson

experiment in which the average number of successes within a

given region is U. Then the Poisson probability is as above .

Where x is the Actual number of successes.

e is equal to 2.71828.

u is the mean of the distribution.

The average number of successes (u) that occurs in a

specified region is known.

The probability of success is proportional to the size of the

region.

The probability of successes occurring in an extremely

small region virtually zero.

Notations:

e = A constant equal to approximately 2.71828.

u = The mean (average) no of success that occurs in a specific

region.

Example: The average no of homes sold by A really company is 2

Homes per day. What is the probability that exactly 3 homes will

be sold tomorrow?.

u = 2 (Average of 2 homes sold per day)

84

x = 3 (3 homes will be sold tomorrow)

e = 2.71828 (Constant)

Poisson Formula:

P (x, u) = (eu) (ux)

------------------------
x

P(3, 2) = (2.72828) (2)

-------------------------------
1x2x3

= (0.13534) (8)/6

= 0.180

Normal Distribution and its properties:

Normal distribution refers do a family of continuous

probability distribution described by the normal equation.

Normal Equation:

The value of the random variable Y is - (x u) /2

1
Y= x C (Coefficient)
85

Where X is a normal Random variable.

u is the mean

is the standard deviation

is constant (3.14159)

e is constant (2.71828)

Standard Deviation:

Represented by it means how much variance

(difference) or dispersion exist from the average.

Example: = Variance (Root of its variance let us consider a

population has eight values, 2,4,4,4,5,5,7,9.

Mean: 2+4+4+4+5+5+7+9
-------------------------
8

= 40/8 = 5 1) difference between the mean & the mean & the

valiance value is taken.

Standard Deviation 25 square the value.

(2 - 5) = (-3) = 9 ( 4 5) = (-1) =1 (5 5) = 0 = 0

(4 5) = -1 = 1 ( 4 5) = (-1) =1 (7 5) = 2 = 4

(5 5) = (0) = 0
86

Rate of 9+1+1+1+0+0+4+16 38
---------------------------- = = 4/-
8 8

Example: An average light bulb manufactured by Acme

Corporation lasts 300days with a standard deviation of 50 days.

Assuming that the bull life is normally distributed what is the

probability that an Acme light bulb will last at most 365 days?

Answer: The value of the normal Random valuable (X) = 365

days.

The mean (u) = 300 days standard deviation = 50 days.

Normal Distribution Y = 1 x e(xu)

2
1
=
502 x 3.14159 x 2.71828 (365 300) /2 x 50

1
=
50 x 6013 x 2.71828/100 = 1/306.5 x 271 = 884//

Y = .88 or 88%

Hence there is an 88% chance that the bulb will last most

365 days.
87