Sie sind auf Seite 1von 75

PPG INSTITUTE OF TECHNOLOGY

PPG BUSINESS SCHOOL


BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
SUBJECT: BUSINESS RESEARCH METHODS
UNIT - I
1 INTRODUCTION
1.1 BUSINESS RESEARCH DEFINITION AND SIGNIFICANCE 1.2 RESEARCH PROCESS 1.3 TYPES
OF RESEARCH 1.4 THEORETICAL AND EMPIRICAL RESEARCH 1.5 CROSS SECTIONAL AND TIME
-SERIES RESEARCH 1.6 RESEARCH QUESTIONS/PROBLEMS 1.7 RESEARCH OBJECTIVES 1.8 RES
EARCH HYPOTHESES
1.1 INTRODUCTION BUSINESS RESEARCH DEFINITION Research is a systematic and objec
tive process of gathering, recording and analyzing data for aid in making busine
ss decisions. Business research is a systematic and organized effort to investig
ate a specific problem encountered in the work setting that needs a solution
SIGNIFICANCE OF RESEARCH Research inculcates scientific thinking: Research incul
cates scientific and inductive thinking and it promotes the development of logic
al habits of thinking and organization. Increasing role of research: The role of
research in several fields of applied economics, whether related to business or
to the economy as a whole, has greatly increased in modern times. The increasin
gly complex nature of business and government focused attention on the use of re
search in solving operational problems.
1

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Research provides the basis for nearly all government policies in economic syste
m. Solving operational and planning problems: Research has its special significa
nce in solving various operational and planning problems of business and industr
y. Operations research and market research, along with motivational research, ar
e considered crucial and their results assist, in more than one way in taking bu
siness decisions. Important for social scientists: Research is equally important
for social scientists in studying social relationships and in seeking answers t
o various social problems. It provides the intellectual satisfaction knowing a f
ew things just for sake of knowledge and also has practical utility for the soci
al scientists to know the sake of being able to do something better or in a more
efficient manner. Significance of research can also be understood keeping in vi
ew the following points: 1) To those students who are write to masters or ph. D t
hesis, research, may mean a careerism or a way to attain a high position in the
social structure; 2) To professionals in research methodology, research may mean
a source of livelihood; 3) To philosophers and thinkers, research may mean the
outlet for new ideas and insights; 4) To literary men and women, research may me
an the development of new styles and creative work; 5) To analysis and intellect
uals, research may mean the generalization of new theories 1.2 RESEARCH PROCESS
Formulating the research problem The formulation of a general topic into a speci
fic research problem thus constitutes the first step in a scientific enquiry. Es
sentially two steps are involved in formulating the research problem, viz.,
understanding the problem thoroughly, and rephrasing the same into meaningful te
rms from an analytical point of view. Extensive Literature survey The abstractin
g and indexing journals and published or unpublished bibliographies
2

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Formulating the working hypotheses After extensive literature survey, researcher
should state in clear terms the working hypothesis. It is tentative assumption
made in order to draw out and test its logical or empirical consequences. Prepar
ing the research design Research design includes the means of obtaining the info
rmation, explanation of the way in which selected means of obtaining information
will be organized and the reasoning leading to the selection. Determining Sampl
e design A sample design is a definite plan determined before nay data are actua
lly collected for obtaining a sample from a given population. Collecting the dat
a Data are two types Primary data and Secondary data. Primary data can be collec
ted by observation, through personal interview, through telephone interviews, by
mailing of questionnaires, through schedules. Analysis of data The analysis of
data requires a number of closely related operations such as establishment of ca
tegories, the application of these categories to raw data through coding, tabula
tion and then drawing statistical inferences. Interpret and report. Finally, the
researcher has to prepare the report of what has been done by him. The main tex
t of the report should have the following parts 1. Introduction 2. Summary of fi
ndings 3. Main report 4. Conclusion
3

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
RESEARCH PROCESS
Review the literature
Review Concepts And theories
FF
FF
Design Research (Including Sample Design) Analyse Data (Test Hypothesis if any)
Define Research Problem
Formulate hypothesis
Collect Data (Execution)
Interpret and report
I
Review Previous Research findings
F
V
F
VI VII
III
IV
II
F F FF
Feed Back
Feed Forward
1.3 Types of research Pure Research is undertaken for the sake of knowledge with
out any intention to apply it in practice
Not necessarily problem oriented Disco
very of new theory / refinement of existing theory.
Ex : inventions like steam e
ngine, EDP, telecomm. Applied research is carried on to find solution to a real
life problem requiring an action or policy decision. Problem oriented
Action dir
ected It seeks an immediate and practical result Ex: Marketing research carried
on for developing a new market
4

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Exploratory Research analyses the data and explores the possibility of obtaining
as many relationships as possible.
It is a preliminary study of an unfamiliar p
roblem about which the researcher has little or no knowledge.
To see what is the
re rather than to predict the relationships that will be founded
EX: Doctors initi
al investigation of a patient suffering from an unfamiliar disease. Descriptive
research It is a fact finding investigation with adequate interpretation.
It foc
uses on particular aspects or dimensions of the problem studied Ex: Consumption
behavior of people in a village Diagnostic study It is to discover what is happe
ning, Why it is happening and What can be done It aims in identifying the cause
of the problem and the possible solution for it
Evaluation studies It is for assessing the effectiveness of social or economic p
rogrammes implemented Ex: (Polio drops)
For assessing the impact of development projects Ex: (irrigation projects)
Action Research It is a concurrent evaluation study of an action programme launc
hed for solving a problem for improving existing situation
5

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

Ex: (Creating awareness about HIV)


Experimental Research It is to assess the effects of particular variables on a p
henomenon by keeping the other variables constant or controlled To determine whe
ther and in what manner variables are related to each other The factor , which i
s influenced , by other factors is called a dependent variable, and the other fa
ctors , which influence it are known as independent variables EX: agricultural p
roductivity (i.e) is a dependent variable and the factors such as soil fertility
, irrigation, quality of seed etc. which influences the yield are independent va
riables. Analytical studies It is a system of procedures and techniques of analy
sis applied to quantitative data It consists of mathematical model It aims in te
sting hypothesis and specifying and interpreting relationship Used to measure va
riables, comparing groups and examining association with factors
Historical research Study of past record and other information sources Its main
objective is to draw explanations and generalizations from the past trends in or
der to
understand the present and to anticipate the future. Surveys It is fact finding
study It involves collection of data directly from a population
6

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

It requires expert and imaginative planning, careful analysis and rational inter
pretation of the
findings Case Study It is an in-depth comprehensive study of a person, a social
groups , an episode, a process Ex: a study of the financial health of a business
undertaking A study of labor participation in management in a particular enterp
rises A study of life style of working women
Field studies It is a scientific enquiries aimed at discovering the relations an
d interactions among sociological, psychological and educational variables in so
cial institutions and actual life situations like communities, school, factories
etc A social or institutional situation is selected and the relations among the
attitudes, values,
perceptions and behaviors of individuals and groups in the selected situation ar
e studied. 1.5 On the basis of extent theory research are two types:
Theoretical
Research Empirical Research
Theoretical research: Theoretical research generally uses the findings from exis
ting works to develop new ideas through analyzing existing theory and explanatio
ns. These new ideas are not tested through collecting evidence in the form of pr
imary data. Theoretical research is held to be a classical way of adding somethi
ng to the value of the body of knowledge. In the business and management studies
world theoretical research is not always well received. In fact some academic r
esearchers would argue that the process described as theoretical research should
not be regarded as proper academic research. The basis of such a claim is that th
is type of theoretical research does not have a test component. This fact is use
d by those who are not enthusiastic about
7

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
theoretical research, to imply that theories can postulated without any proof . How
ever this type of thinking is a misunderstanding of the nature of research. All
research processes requires conceptualization. One of the primary roles of theor
etical research is to rework already established ideas in order to improve insig
hts into the subject matter. Such improvements could well-constitute adding some
thing of value to the body of knowledge. Evaluating theoretical research: theore
tical research does not rely on data or evidence, collection, analysis and synth
esis it is sometimes often said to be more difficult. Theoretical research relie
s heavily on creativity and imagination. Al though these attributes are still re
quired for empirical research they are often required to a greater extent in the
oretical research. Empirical research: empirical means based upon observation or
measurement rather than theoretical reasoning. It supports the development of n
ew ideas through the collection of data. The researcher who develops a theory of
spot fan violence through visiting a library and developing their own explanati
on through reading existing work will be undertaking theoretical research. The r
esearcher to take this one step further and collects data test their explanation
will be undertaking empirical research. For example, computer simulations gener
ate scores from random number routines. The cases and measures are not involved.
Analytical researchers use mathematical operations to work from initial assumpt
ions to conclusions there are no cases, measures, or scores. Empirical research
involves three activities, as which are as follows: Measurement: it involves act
ivities associated with measuring the factors that from the expected relationshi
p. In other situations, a researcher may begin with measures already developed a
nd assess their suitability for a study at hand. Research design: it establishes
procedures to obtain cases for study and to determine how scores will be obtain
ed from those cases. Analysis: empirical research also involves analysis of scor
es. Analyses are performed to describe crosses on single measures and, especiall
y, to identify relationships that may exist between scores across different meas
ures.
8

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Benefits of empirical research 1) Understand and respond to dynamics of situatio
ns. 2) Respect contextual differences. 3) Build upon what is already known to wo
rk 4) Meet accepted professional standards of research. 5) Integrate professiona
l knowledge with empirical data to inform instructional development decisions. 6
) Establish relationship between intervention and behavioral response. Limitatio
ns of Empirical Research 1) Time: Since empirical research requires soliciting p
articipation and data gathering from various off campus of researchers. 2) Cost: F
ield research requires on-sites visits by researchers may be require cash outlay
s for travel, lodging, and other expenses not required in conceptual research, w
hich can usually be accomplished in the local academic setting. 3) Access to fir
ms: they cannot gain access to the types of the firms necessary for their studie
s. 4) Access to data: even if they gain access to business firms, such firms may
be reluctant to release any or all the data necessary for the studies. 5) Skill
s: they do not possess the requisite skills necessary to design such empirically
based studies, to gather and analyze the oftentimes huge data efficiently, or t
wo interpret the results in a manner meaningful to and rewarded by both the busi
ness and academic worlds. 1.6 On the basis of time dimension: Two types:
Cross-s
ectional Research Longitudinal Research
9

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Cross-sectional research: in this research, researchers observe at one point in
time. Cross-sectional research is usually the simplest and least costly alternat
ive. A cross- sectional designs a snapshot of the variables included in the stud
y, at one particular point in time. It may reveal how those variables are relate
d. Longitudinal Research: Researchers using longitudinal research examine featur
es of people or other units at more than one time it is usually more complex and
costly than cross sectional research, but it is also more powerful, especially
where researchers seek answers to questions about social change. Three types of
longitudinal research which as follows; 1) Time-series research 2) Panel study 3
) Cohort study Time series research: the time design collects data on the same v
ariable at regular intervals (weeks, months, year) etc Time series designs are u
seful for:
Establishing a baseline measure, Describing charges over time, Keepin
g track of trends and Forecasting future trends.
Panel study: it is a powerful type of longitudinal research. It is more difficul
t to conduct than time series research. In panel study, researchers observe exac
tly the same people, group, or organization across time period. Participants who
are examined over repeated time points may be affected by having previously com
pleted the measure being used. (This is known as sensitization) Cohort study: it
is similar to the panel study, but rather than observing the exact same people,
a category of people who share a similar life experienced in a specified time p
eriod is studied.
10

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
1.7 Research Problem
The term problem means a question or issue to be examined.
Re
search Problem refers to some difficulty /need which a researcher experiences in
the context of either theoretical or practical situation and wants to obtain a
solution for the same. The first step in the research process definition of the
problem involves two activities:
Identification / Selection of the Problem
Formu
lation of the Problem
This step involves identification of a few problems and se
lection of one out of them, after evaluating the alternatives against certain se
lection criteria. Formulation is the process of refining the research ideas into
research questions and objectives.
Formulation means translating and transformi
ng the selected research problem/topic/idea into a scientifically researchable q
uestion. It is concerned with specifying exactly what the research problem is. C
RITERIA OF SELECTION The selection of one appropriate researchable problem out o
f the identified problems requires evaluation of those alternatives against cert
ain criteria. They are:
Internal / Personal criteria Researchers Interest, Resear
chers Competence, Researchers own Resource: finance and time.
External Criteria or
Factors Researchability of the problem, Importance and Urgency, Novelty of the
Problem, Feasibility, Facilities, Usefulness and Social Relevance, Research Pers
onnel. SOURCES OF PROBLEMS
Reading
11

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Academic Experience
Daily Experience Exposure to Field Situations
Consultations
Brainstorming Research Intuition Problem Formulation For a researcher, the probl
em formulation means converting the management problem to a research problem. Ex
amples Management problem- Want to increase the sale of product A Research probl
em- What is the current standing of the product A? While problem is formulated,
the following should be considered 1. Determine the objectives 2. Consider envir
onmental factors 3. Nature of the problem 4. Stating the alternatives Determine
the objectives To increase the sales or does it means it has improved the knowle
dge of the audience.
12

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
If the advertisement by the company was indeed ineffective, what course of actio
n does the company intend to take? Increase the budget for the next Ad Use diffe
rent appeal Change the media Go to a new agency. Consider environmental factors
If a company introduce a new product Purchasing habits of consumers Presently, w
ho are the competitors in the market with similar product? What is the perceptio
n of the people about other products of the company? Size of the market and targ
et audience. Nature of the problem Initial investigation could be carried by usi
ng a focus group of consumers or sales representatives Did the customer ever inc
lude this companys product in his mental map? If the customer is not buying, the
reasons for that Why did the customer turn to the competitors product? Stating th
e alternatives The researcher would be better served by generating as many alter
natives as possible during the problem formulation.
13

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
For every alternative, a hypothesis has to be developed and data to be collected
and to be proved whether it is best alternative or not. 1.8 Research objective
Its not long term goal, but is the step towards the long term goal. It defines th
e purpose of the proposed research. It should be phrased in such a way that cent
ral hypothesis clearly grows out of it An ideal research objective -Hypothesis d
riven -Innovative -To study mechanism -Realistic & focused -Doable in the reques
ted budge and time 1.9 Hypothesis Testing It considered as a principal instrumen
t in research. Hypothesis is a mere assumption to be proved or disproved. Hypoth
esis is defined as the proposition or a set of proposition set forth as an expla
nation for the occurrence of some specified group of phenomena, either asserted
merely as a provisional conjecture to guide some investigation or accepted as hi
ghly probable in the right of established facts. Characteristics of hypothesis 1
) Hypothesis should be clear and precise 2) A good hypothesis is assumption or e
xplanation of why or how something occurs 3) Hypothesis should be capable of bei
ng tested. 4) Hypothesis should state relationship between variables.
14

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
5) Hypothesis should be limited in scope and must be specific. 6) Hypothesis sho
uld be tested in most simple terms so that the same is easily understandable by
all concerns. 7) Hypothesis should be consistent with most known facts, in other
words, it should be the one which judges accept as being the most likely. 8) Hy
pothesis should be agreeable to testing with a reasonable time. 9) Hypothesis mu
st explain the facts what it claims to explain. It should have empirical referen
ce. Eg: Companies manufacturing washing machines spend at least 10% of their ann
ual profits on advertising. Testing Hypothesis: This is a statement or propositi
on that we would like to verify whether it is true or not. Concept of Null and a
lternative Hypothesis A Null hypothesis is a statement about a population parame
ter (such as mu) and the test is used to decide whether or not to accept the hyp
othesis. It is identified by the symbol Ho It is always stated that There is no s
ignificant difference between the samples. If the H0 is false, something else mu
st be true. That is called alternative hypothesis It is identified by the symbol
H1. It should be clear that both Null and alternative hypotheses cannot be true
and only one of them must be true. For any exercise, our conclusion must result
into the acceptance of one hypothesis and rejection of the other.
Eg: Suppose a person is facing a legal trial for committing a crime. The judge l
ook into all the evidence for and against it listens very carefully the prosecut
ions and defendants arguments and then decides the case and gives his verdict.
15

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
The verdict could be H0: The person has not committed the crime H1: The person h
as committed the crime
Procedure in Hypothesis testing There are five steps involved in testing a hypot
hesis 1. Formulate a hypothesis. We have to set the null and alternative hypothe
sis (H0 and H1) 2. Set up a suitable significance level 3. Significance level me
ans the confidence with which a null hypothesis is rejected or accepted depends
upon the significance level used for the purpose. 4. Select Test criterion: Ther
e are many techniques from which one is to be chosen.
Eg: If sample size > 30- Z test If sample size <30- t-test. 5. Compute This step
involves various computations necessary for the application of that particular
test. These computations include the testing statistic as also its standard erro
r. 6. Make decisions: This step involves in the process of accepting or rejectin
g the null hypothesis at a given level of significance. Two types of Errors Type
I error: it occurs when one rejects the null hypothesis and accepts the alterna
tive, when it fact the null hypothesis is true. Type II error: it occurs when on
e accepts the null hypothesis when in fact the null hypothesis is false.
16

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
UNIT -II
2.1 RESEARCH DESIGN MEANING AND TYPES 2.2 EXPLORATORY RESEARCH DESIGN 2.3 CONCLU
SIVE DESIGN 2.4 EXPERIMENTAL/CAUSAL RESEARCH 2.5 VARIABLES IN RESEARCH 2.6 MEASR
UEMENT AND SCALING 2.7 VALIDITY AND RELIABILTIY OF INSTRUMENTS
2.1 Research Design Meaning & Types A research project conducted scientifically
has a specific framework of research from the problems identification to the pre
sentation of the research report. This framework of conducting research is known
as the research design. A research designs simply the framework or plan for a s
tudy that is used as a guide in collecting and analyzing the data. It is bluepri
nt that is followed in completing study . TYPES OF RESEARCH DESIGN 1) Exploratory
Research i) Literate Research/Study of Secondary Data ii) Survey of knowledgeabl
e persons or experience survey iii) Case Groups iv) Focus Groups v) Two-Stage De
sign
17

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
2) Conclusive Research i) Descriptive a) Longitudinal Study b) Cross-sectional S
tudy ii) Experimental or Casual Research 2.2 Exploratory Research Design Explora
tory research studies are also termed as formulative research studies. The main
purpose of such studies is that of formulating a problem for more precise invest
igation or of developing the working hypotheses from an operational point of vie
w. The major emphasis in such studies is on the discovery of ideas and insights.
As such the research design appropriate for such studies must be flexible enoug
h to provide opportunity for considering different aspects of a problem under st
udy. Objectives of Exploratory Research 1) Precise formulation of the problem 2)
Provide more knowledge to the researcher about the problem environment 3) Estab
lishes priorities for further research 4) To design appropriate information coll
ection procedure for the given situation. 5) To determine nature of relationship
between various factors associated in the problem. 6) Gathering information on
the problems associated with doing conclusive research. 1. Study of Secondary Da
ta: The quickest and most economical way is to find possible hypotheses from the
available literature. The past researches may be suitable sources of informatio
n to develop new hypotheses. The findings of marketing research are generally pu
blished in trade and professional journals, which can be fruitful sources of inf
ormation.
18

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
2) Depth Interview: Experience survey means the survey of people who have had pr
actical experience with the problem to be studied. These individuals can be top
executives, sales managers/executives, wholesalers and retailers possessing valu
able knowledge and information about the problem environment. 3) Case Study: The
third general type of exploratory research is the case method. This research me
thod has long been considered soft or nonscientific, but with the modern surge in
qualitative research the case method has received more attention. Indeed, the ca
se method might be considered one variation of the survey of individuals with id
eas. It involves the comprehensive study of one, or a few, specific situations a
nd lends itself particularly to the study of complex situations in which the int
errelations of several individuals are import for example, the effective managem
ent of distributor relations or what constitutes good marketing management. 4) F
ocus Group: Focus group originates from sociology studies. They have been extens
ively used in marketing research. Focus groups studied are generally conducted t
o evaluate the potential of a new product idea or concept. A focus group compris
es several persons, who are led by a trained moderator. The moderators task is to
lead the team in generating and exchanging ideas on a particular issue. The pro
cess starts by issuing a topic for discussion among participants by the moderato
r. In such discussions, the moderators role will be to silently watch the proceed
ings and ensure that the discussion is going on as expected. However, the modera
tor needs to intervene to ensure that all individuals in the group participate.
Once the focus groups observations and recommendations are obtains, the informati
on is evaluated by the moderator,. This forms the basis for further research. 5)
Two-Stage Design: A two-stage design is beneficial approach for designing resea
rch. In this method, the exploration is conducted in two stages. The first stage
consists of clearly defining the research problem, while the second stage compr
ises developing the research design. A two-stage design is beneficial, when the
problem is vaguely defined and the researcher is not clear about the particular
topic that has to be studied.
19

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
2.3 Conclusive Research Design Conclusive research provides information, which h
elps the executive to make a rational decision. The marketing executive has to a
rrive at a suitable decision from the various alternative decisions. The various
alternative conclusions and selecting the most suitable conclusion may be done
by descriptive research design or experimental research design. i. Descriptive R
esearch
Descriptive studies, as their name implies, are designed to describe something f
or example, the characteristics of users of a given product; the degree to which
product use varies with income, age, sex, or other characteristics, or the numb
er who saw a specific television commercial. A majority of marketing studies are
of this type. Objectives of Descriptive Research 1) To describe the characteris
tics of relevant groups 2) To estimate the percentage of units in a specified po
pulation exhibiting a certain behavior. 3) To determine the perceptions of produ
ct characteristics. 4) To determine the degree to which marketing variable are a
ssociated. Types of Descriptive Studies 1) Case Method: Case studies are more ap
propriate to exploratory research than descriptive research. They are not widely
used in descriptive research, but they are worth some comment in the descriptiv
e context and perhaps should be used more than they have been in the past. 2) St
atistical Method: The statistical method is the most widely used method in marke
ting research and is the method usually implied when a survey is referred to. The
name comes from the statistical techniques that are used in analyzing the data c
ollected techniques that vary from simple means and percentage to very sophistic
ated techniques that require computers to manipulate the data.
20

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Uses of Descriptive Research 1) Consumer profiles 2) Market potential studied 3)
Product usages studies 4) Attitude surveys 5) Sales analysis 6) Media research
7) Price surveys Descriptive Research Analysis 1) Longitudinal Design/Panel Anal
ysis: Longitudinal studies are based on panel data and panel methods. A panel is
a sample of respondents who are interviewed and then re-interviewed from time t
o time. Generally panel data relate to the repeated measurements of the same var
iables. Each family included in the panel, records its purchases of a number of
product at regular intervals, say, weekly, monthly or quarterly. Over a period o
f time, such data will reflect changes in the buying behavior or families. 2) Cr
oss-Sectional Design: A cross-sectional study is concerned with a sample of elem
ents from a population. Thus, it may deal with households, dealers, retail store
s, or other entitles. Data on a number of characteristics from the sample elemen
ts are collected and analyzed. The crosssectional study is the most frequently u
sed descriptive design in marketing research. Crosssectional design involves the
collection of information from any given sample of population elements only one
. They may be either single cross- sectional or multiple cross-sectional. Types
of Cross-Sectional Design i. Field Studies ii.Survey Research
21

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
2.4 Casual or Experimental Research Although descriptive research in identifying
co-variation between variables (e.g., blue packages outsell red ones, consumpti
on rate varies by education level) it cannot truly indicate causality (e.g., col
or causes sales, education causes consumption). When we are in need of determini
ng whether two or more variables are causally related we must turn to casual res
earch procedures. While there might be a tendency to see many research objective
s from a casual perspective (We really want to know what causes consumers to act
that way ), there is a difference between causality in the vernacular and how it i
s defined by scientists. Types of experimental research design Informal
fter without control Before-after with control After only with control Ex-post f
acto design Panel design Simple time series experiments Recurrent time series ex
periments

Before

Formal
Completely randomized design Randomized block design Latin square design
Factorial design
22

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Informal design Before and after without control In such a design a design a sin
gle test group or area is selected and the dependent variable is measured before
the introduction of the treatment. The treatment is then introduced and the dep
endent variable is measured again after the treatment has been introduced. After
only with control design In this design two groups or areas (test are and contr
ol area) are selected and the treatment is introduced into the test area only. T
reatment impact is assessed by subtracting the dependent variable in the control
area from its value in the test area. Before and after with control design In t
his design two areas are selected and the dependent variable is measured in the
both the area for an identical time period before the treatment. The treatment i
s then introduced into the test area only, and the dependent variable is measure
d in both for an identical time period after the introduction of the treatment.
Ex post facto design One variable of the after only design is called the ex post f
acto design. This differs from the after only design because the experimental and
control groups are selected after the experimental variable is introduced instea
d of before. One advantage is that the test subject cannot be influenced, pro or
con, toward the subject by knowing they are being tested, since they are expose
d to the experimental variable before being selected for the sample. Panel desig
n A permanent set of experimental units used in market research investigation is
known as a panel. Panel can be used both for exploratory and conclusive research.
In such an experimental observation are recorded at some pre d determined inter
vals of time and experimental variables can be introduced if and
23

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
when desired. Here any two set of successive measurements between which some exp
erimental variable is introduced can be considered as before and after experimen
tal measurements. Simple test series experiments Some dealers or retailers are s
elected for recording observation over certain period of time. Eg: to study the
impact of some advertising policy on sales, one may select some dealer or retail
ers. the sales during a certain period before the advertisement and after the ad
vertisement are recorded. Recurrent time series design Here the advertising poli
cy is introduced, removed and introduced over different period of time and sales
over these periods are recorded. Formal design Completely randomized design The
main feature of this design is that the experimental treatments are assigned to
the test units completely at random. No prior precaution is needed to some extr
aneous variable before the assignment is randomly made. Randomized block design
It is an improvement over the CR design. In this design the principal of local c
ontrol can be applied along with the other two principles of experimental design
. In this design subjects are first divided into groups, known as blocks, such t
hat within that group the subjects are relatively homogeneous in respect to some
selected variables Latin square design This design suggest that test will from
a square because there will be as many tests units are treatments. This design i
s used to control important extraneous influence. It is assumed that each treatm
ent occurs once with each store on a block. There are several stores in a block,
there must be as many blocks as there are treatments. It may be three, four and
so on.
24

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
2.5 Variables in research Dependent and Independent variables An independent var
iable is the presumed cause of the dependent variable- the presumed effect. When
it can say A cause B , it means A is independent variable and B is dependent va
riable. The independent variable thus is one which explains or accounts variatio
n in the dependent variable. Experimental and measured variable The experimental
variable spell out the detail of the investigators manipulation while the measur
ed variable refer to measurement. For example, rural development(measured variab
le) may be assessed in terms of increase in income, literacy, infrastructure....
.. Qualitative and quantitative variables The Quantitative variable is one whose
values or categories consist of number and differences between its categories ca
n be expressed numerically. Eg: age, income, size......The qualitative variable
is one which consist of discreet categories rather than numerical units Categori
cal and numerical variables Numerical variables are broken down into units in wh
ich the numbers used carry mathematical meaning. The numbers may be either discr
ete (1,2,3,4..)which cannot be broken down into smaller fractional quantities(no
. Of children)or continuous. 2.6 Measurement and scaling By measurement we mean
the process of assigning numbers to objects or observations, the level of measur
ement being a function of the rules under which the numbers are assigned. Accord
ing to kenneth D. Bailey: Measurement is the process of determining the value or
level, either qualitative or quantitative, of a particular attribute for a parti
cular unit of analysis . Basic process of measurement I. II. Selecting observable
empirical events Developing a set of mapping rules- a scheme for assigning numbe
rs or symbols to represent aspect of the event being measured.
25

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
III.
Applying the mapping rules to each observation of that event
Mapping rules In measuring, one devices some mapping rule and then translate the
observation of property indicants using this rule. For each concept or construc
t, several types of measurement are possible; the appropriate choice depends on
what you assume about the mapping rules. Each one has its own set of underlying
assumption about how the numerical symbols correspond to real world observation.
Importance of measurement 1) Measurement allows researchers to quantify abstrac
t construct and variables. 2) The level of statistical sophistication used to an
alyze data derived from a study is directly dependent on the scale of measuremen
t used to quantify the variables of interest. Functions of measurement Empirical
description: it facilitates empirical description of social and psychological p
henomena. Eg:-in a study of a tribal community, the researcher has to classify a
nd categorize the cultural patterns and behaviors. 1) Facilitates statistical tr
eatment: measurement renders data amenable to statistical manipulation and treat
ment. The statistical techniques for comparing groups, studying relationship bet
ween variables. 2) Aids testing of hypothesis: measurement facilitates testing o
f theories and hypothesis. 3) Provide differentiation in objects: measurement en
ables researchers to differentiate between objects or people in terms of specifi
c properties they possess.
Measurement scales 1) Nominal scale
26

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
2) Ordinal scale 3) Interval scale 4) Ratio scale Nominal scale It represents th
e most elementary level of measurement. a nominal scale assigns a value to an ob
ject for identification or classification purposes. The value can be a number be
cause no quantities are being represented. In this sense, a nominal scale is tru
ly a qualitative scale. Nominal scales are extremely useful even though they can
be considered elementary. Marketing researchers use this scale quite often. For
example, suppose three old drinks were experimented with taste. The researcher
would like the experiment to be blind, so when subject were asked to taste one o
f the three cold drink, the drinks were labeled A,B or C. Ordinal scaling Ordina
l scales have nominal properties, but they also allow things to be arranged base
d on how much of some concept they possess. In other words, an ordinal scale is
a ranking scale. The ordinal scale indicates the relative position of two or mor
e objects or some characteristics. The consumers are asked to rank preference fo
r several brands, flavor or package designs. The measures of such preference are
ordinal in nature. Interval scale The interval scale has all characteristics of
the ordinal scale and in addition, the units of measures or intervals between s
uccessive positions are equal. Eg:- a researcher scaled brand A,B and C on an in
terval scale regarding the buyers degree of liking of the brands. Brand A receiv
es the highest liking score 6, B received 3 and C receives 2. First the liking f
or brand A is more favorable than that for brand B. second the degree of liking
between A and B is three times greater than the liking between B and C.
27

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Ratio scale Ratio scale represents the highest form of measurement. They have al
l the properties of interval scale with the additional attribute of representing
absolute quantities. Interval scale represents only relative meaning, whereas r
atio scale represents absolute meaning. In other words, ratio scale provides ico
nic measurement. Zero, therefore, has meaning in that it represents an absence o
f some concept. An absolute zero is a defining characteristic in determining bet
ween ratio and interval scale. Classification of scaling ttechniques SCALING TEC
HNIQUES Comparative scales Paired comparison Rank order Constant sum Non-compara
tive scales Continuous rating scales Itemized rating scales Likert Semantic diff
erential Stapel Types of scaling Techniques
COMPARATIVE SCALES Involve the respo
ndent directly comparing stimulus objects. e.g. How does Pepsi compare with Coke
on sweetness
NON-COMPARATIVE SCALES Respondent scales each stimulus object independently of o
ther objects e.g. How would you rate the sweetness of Pepsi on a scale of 1 to 1
0
28

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Paired comparison items
Please indicate which of the following airlines you prefer by circling your more
preferred airline in each pair: Air Canada Air Transat Horizon Air WestJet Air
Canada WestJet
Comparative constant sum scales Allocate a total of 100 points among the followi
ng soft-drinks depending on how favorable you feel toward each; the more highly
you think of each soft-drink, the more points you should allocate to it. (Please
check that the allocated points add to 100.) Coca-Cola 7-Up Mirinda Fanta Pepsi
-Cola Total _____ points _____ points ____ points
_____ points _____ points 100 points
Comparative rank order scales Rank the following soft-drinks from 1 (best) to 5
(worst) according to your taste preference: Coca-Cola 7-Up Fanta Pepsi-Cola ____
_ _____ _____ _____
29

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Mountain Dew
_____
Semantic differential scale Here are a number of statements that could be used t
o describe Tesco. For each statement tick ( ) the box that best describes your f
eelings about Tesco. Modern store Low prices Unfriendly staff Stapel Scale QUALI
TY SERVICE VARIETY +5 +4 +3 +2 +1 HIGH -1 -2 -3 -4 -5 +5 +4 +3 +2 +1 POOR -1 -2
-3 -4 -5 +5 +4 +3 +2 +1 WIDE -1 -2 -3 -4 -5 Old fashioned store High prices Frie
ndly staff
Likert scale or 5 points scale
30

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Strongly disagree
Disagree
Neither agree nor disagree
Agree
Strongly agree
Characteristics of good mmeasurement scales 1. Reliability 2. Validity The degre
e to which a measure faithfully represents the underlying concept (it asks the r
ight questions) 3. Sensitivity The ability to discriminate meaningful difference
s between attitudes. The more categories the more sensitive (but less reliable
eliability can be more easily determined than validity If it is reliable, it may
or may not be valid If a measure is valid, it may or may not be reliable If it
is not reliable, it cannot be valid If it is not valid, it may or may not be rel
iable Example of low validity, high reliability
Scale is perfectly accurate, but
is capturing the wrong thing; for example, it measures consumers interest in cre
ative writing rather than preference for kinds of stationery. The degree to whic
h a measure accurately captures a true outcome without error synonymous with rep
etitive consistency
31

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

Example of modest validity, low reliability Scale genuinely measures consumers in


terest in kinds of stationery, but poorly worded items, sloppy administration, d
ata entry errors lead to random errors in data
2.6 Reliability Reliability refers to how consistent a measuring device is. A me
asurement is said to be reliable or consistent if the measurement can produce si
milar results if used again in similar circumstances. Validity This refers to wh
ether a study measures or examines what it claims to measure or examine. Valid m
easures will ALWAYS be reliablebut reliable measures are not necessarily valid. R
eliability' of any research is the degree to which it gives an accurate score ac
ross a range of measurement. It can thus be viewed as being 'repeatability' or '
consistency'. In summary: Inter-rater: Different people, same test. Test-retest:
Same people, different times. Parallel-forms: Different people, same time, diff
erent test. Internal consistency: Different questions, same construct. TEST-RETE
ST RELIABILITY 2 measures yield identical (or similar) results at 2 different ti
mes. The test-retest reliability method is one of the simplest ways of testing t
he stability and reliability of an instrument overtime. For example, a group of
respondents is tested for IQ scores: each respondent is tested twice - the two t
ests are, say, a month apart. Then, the correlation coefficient between two sets
of IQ-scores is a reasonable measure of the test-retest reliability of this tes
t. PARALLEL FORMS RELIABILITY
32

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Parallel forms reliability is used to assess the consistency of the results of t
wo tests constructed in the same way using the same content. To create the paral
lel forms a large pool of test questions that measure the same quality are creat
ed and then randomly divided into two separate tests. Each test is given to the
same sample of people and the correlation between the two parallel forms is used
as an estimate of the reliability. Content (Face) validity Is the degree to whi
ch a test measures an intended content area, e.g., achievement tests. Example: t
o measure knowledge of parenting skills could be obtained by consulting experts
such as social workers, parents. Judgment is dependent upon the knowledge of the
experts Construct validity Is the degree to which a test measures an intended h
ypothetical construct? i.e., a non-observable trait, such as intelligence, which
explains behavior Criterion validity Describes the extent to which a correlatio
n exists between the measuring instrument & standard empirical evidence. E.g., t
he relationship between College Board examination and student academic success i
n college. Two measures need to be taken: the measure of the test itself & the c
riterion to which the test is related Difference between reliability and validit
y Reliability: the degree to which a measurement procedure produces similar outc
omes when it is repeated. E.g., gender, birthplace, mothers name should be the sa
me always. Validity: tests for determining whether a measure is measuring the co
ncept that the researcher thinks is being measured, i.e., Am I measuring what I t
hink I am measuring?
33

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
UNIT - III
3 INTRODUCTION
3.1 DATA COLLECTION-TYPES 3.2 PRIMARY DATA VS SECONDARY DATA 3.3 METHODS OF PRIM
ARY DATA COLLECTION 3.4 SURVEY VS OBSERVATION 3.5 SAMPLING PLAN AND SAMPLE SIZE
3.6 PROBABILITY AND NON-PROBABILITY SAMPLING METHODS
2. INTRODUCTION: 3.1 TYPES OF DATA: The task of data collection begins after a r
esearch problem has been defined and researches design/chalked out. While decidi
ng about method of data collection to be used for the study, the researcher shou
ld keep in mind two types of data viz ,primary and secondary data. The primary d
ata are those data, which are collected afresh and for the first time, and those
happen to be original in character. The secondary data, on the other hand, are
those which have already been collected by someone else and which have already b
een passed through the statistical process. Statistical data can be classified u
nder two categories 1) primary data 2) secondary data
34

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Primary data Primary data is the one, which is collected by the investigator him
self for the purpose of a specific inquiry or study. Such data is original in ch
aracter and is generated by survey conducted by individuals or research institut
ions or any organization. The objectives of primary data are formulated on the b
asis of research objectives. Objectives set the guidelines and direction researc
h planning. Formulating the objectives offers the best feasible means of solutio
n. Significance of primary data.
Reliability
Availability of a wide range of tec
hniques
Addresses specific research issues Greater control
Efficient spending fo
r information Limitations
Time consuming High cost
Not always feasible
Large vol
ume of data
Reluctance of respondents
Secondary data Secondary data are those data which have been already collected a
nd analyzed by some earlier agency for its own use; and later the same data are
used by a different agency. Secondary data are statistics that already exist. It
can be classified as - Internal secondary data -External secondary data
35

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

Internal secondary data is a part of the company's record, for which research is
already conducted. Eg: Daily production report, monthly collection report. Exte
rnal Secondary data The data collected by the researcher from outside the compan
y. This can be divided into four parts:
Census data Cen
de Census of the retail trade Population Census Census of manufacturing industri
es Individual project report being published Encyclopedia of business informatio
n sources Syndicated data is an important form of secondary data which may be cl
assified into Consumer purchase data Retailer and whole sale data Advertising da
ta
Advantages of secondary data Economy Quickness Quality No need of measuring inst
ruments Availability Bases for comparison Useful in exploratory research Generat
es feasible alternatives
36

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Disadvantages of secondary data
The data may not fit into the needs of investiga
tion Less accuracy Existence of obsolete information Nondisclosure of research f
indings There may be difficulties in the identification of source Errors may be
there in recording or transferring information from secondary sources
3.2 Primary data Vs secondary data Basis of comparison Object Primary data Secon
dary data for some other
Originate with the specific Gathered research undertaking
purpose but are applicable to present investigation
Cost involved Time consumption
Collection is expensive
Collection is cheaper time usually
Collection can take weeks or Collection even months
involves hours or days
Nature of errors
Errors can be there due to There may be inaccuracies due interviewer biases and
respondent to errors in recording or transferring of the original data
Accuracy and validity
The information is more valid, The validity of information reliable and relevant
should be judged/evaluated before using secondary data
Mode of collection
The information is to be Information already exists in generated either by vario
us sources. Data are
questioning the people or by obtained by searching these observing selected acti
vities sources and then recording from various sources only.
37

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Need of auxiliary instruments
Data collection instruments No need of data collection are to designed according
to instruments. the need of investigation
3.3 Methods of primary data collection
Methods of primary data collection
Survey method
Observation method
Survey techniques Survey techniques can be divided into three broad categories a
s in figure below.
Survey techniques
Interview method Schedule
Questionnaire method
Interview method Interviewing is one of the prominent methods of collection. It
may be defined as a two-way systematic conversation between an investigator and
an informant, initiated for obtaining information relevant to a Specific study.
Interviewing requires face to face contact over telephone and calls for intervie
wing skills. It is done by using a structured schedule or an unstructured guide.
38

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Characteristics of interview method
Needs proper introduction
Incorporates trans
itory relationships Caters to a specific purpose Verbal interaction
Facilitates
telephonic conversation Group studies possible Interactional process
Simultaneou
s recording Types of interview Personal interview
Unstructured and direct interv
iew Structured and direct interviews
Unstructured and indirect interviews
Teleph
one interview Panel interview
Electronic interview Limitations of interview meth
od Expensive
Subject to bias and personal traits
Ineffective in some areas
Recor
ding complexities
demands skilled interviewers subjective
39

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Questionnaire method The questionnaire is the list of questions to be asked from
the respondents. It also contains a suitable space where the answers can be rec
orded. A questionnaire is a method of obtaining specific information about a def
ined problem so that the data, after analysis and interpretation, results in a b
etter appreciation of the problem. a questionnaire form ,which has to be complet
ed by an interviewer, is often referred as schedule Types of questionnaire
tured, non-disguised questionnaire Non-structured, non-disguised questionnaire N
on-structured, disguised questionnaire Structured, disguised

Struc

Process of Questionnaire designing


Determine what information is needed What ty
e of questionnaire to be used Decide on the type of questions Decide on the word
ing of questions Deciding on the layout Pretest Revise and prepare final questio
nnaire
Validation of questionnaire To achieve high quality survey result, a critical co
mponent is validating the instrument (questionnaire) reliability and validity. T
he validity of questionnaire is assessed by three components 1. Content validati
on: It often refers face validity. Face validity is determined by comparing the
questionnaire with other similar questionnaire surveys.
40

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
2. Sampling validity: It is another component of validation. A large sample size
can ensure low sampling errors and high sampling validity. 3. Empirical validit
y: It examines the survey result by comparison with other studies. The aim is to
check consistency with previous results. Empirical validation of questionnaire
reliability often involves two techniques: i. ii. Test-retest techniques: It det
ermines stability of measured indicators. Construct validity : It is a score to
determine internal consistency reliability, measured by the Cronbach alpha Schedu
le It is a device in social research, which is most frequently used in collectin
g field data especially where the survey method is employed. It is used in indir
ect interview. It contains questions and blank tables, which are to be filled in
by the investigators themselves after getting information from the respondents.
Difference between Questionnaire and schedule Basis of difference Mode Question
naire Schedules
The questionnaire is generally It is generally filled out the sent through mail
to researcher, who can interpret
informants to be answered as questions when necessary. specified a covering lett
er, but otherwise without future
assistance from the sender. Economy To collect data is through The data collecti
on is
questionnaire
relatively relatively expensive.
cheap and economical. Chances of non-response Non-response is usually in Non-res
ponse case of questionnaire. Identification of respondent is generally
very low in case of schedules. case of of schedule respondent the is
In case of questionnaire, it is In
not always clear as to who identity
41

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
replies. Time consumption
known. case of schedule the
The questionnaire method is In
likely to be very slow since information is collected well many respondents do n
ot in time as they are filled in by
return the questionnaire, in researcher. time reminders. Personal contact Person
al contact is generally In case of schedules direct not possible in case of pers
onal contact is established with respondents. case of schedule the despite sever
al
questionnaire. Influence literacy of
respondents Questionnaire method can be In
used only when respondents information can be gathered are literate and co-opera
tive. even the respondents happen to be illiterate.
Coverage and distribution
Wider and more representative In respect of schedule there distribution of sampl
e is usually reminds the difficulty
possible under questionnaire in sending enumerators over a method. Accuracy of i
nformation relatively wider area.
Risk of collecting complete In case of schedules, the and right information more
is information collected complete is and
relatively
under generally accurate.
questionnaire method. Success
The success of questionnaire In case of schedules much method lies more on the d
epends upon the honesty and quality of questionnaire itself. competence of resea
rcher.
Appearance of questionnaire
In order to attract the attention This may not be so in case of of respondents,
the physical schedules as they are to be appearance of questionnaire filled in b
y enumerators and must be quite attractive. not by respondents
42

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Observation Method Structured or unstructured method Disguised or undisguised me
thod Direct-indirect observation Human-mechanical observation
Structured-Unstructured Observation Structured Observation How many of his custo
mers visit the hotel with their families and how many come as single customers.
Unstructured Observation How single customers and those with families behave and
their attitude Disguised-Undisguised Observation In disguised observation, the
respondents do not know that they are being observed In non-disguised observatio
n, the respondents are well aware that they are being observed. Direct-Indirect
Observation In direct observation, the actual behavior or phenomenon of interest
is observed. In in-direct observation, the results of the consequences of the p
henomenon are observed. Eg: Inorder to know the soft drinks consumption, he may
like to observe empty bottles dropped into the bin. 3.4 Survey Vs observation me
thod Basis of comparison Objective Survey method Observation method
This method of collecting data This is decidedly superior to is useful when popu
lation size survey is very large. research,
experimentation, or document study for collecting data in behavior research.
Response
Responds in survey method Response in observation is based on verbal answers to
neither as restrictive nor as limited set of questions artificial as either the
survey
43

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
or experiment. Difficulties of quantification Measurement form of the in survey
Measurement in observational observers form of the observers un quantified percep
tions.
studies generally takes the studies generally takes the
quantitative measure. Sample size
Survey studies conducted for Observational studies tend to large sample size. us
e a smaller sample than survey studies, but a larger sample than experiments.
Qualitative techniques of Data collection There are four major techniques in Qua
litative research. They are:
Depth Interview Delphi Technique Focus Group Projec
tive Technique
Depth interview Unstructured, direct interview is known as a depth interview. It
is free from restrictions imposed by a formal list of questions. Eg: What did y
ou mean by that statement? Why did you feel this way? What other reasons do you
have Advantages o It is its ability to discover motivations o The second advanta
ge of the depth interview procedure is that it encourages respondents to express
any ideas they have. o The third advantage is that it provides a lot of flexibi
lity to the interviewer.
44

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Limitations o Longer duration o Difficult to find the qualified and trained peop
le for conducting depth interview o No quantifiable data is obtained in the dept
h interviewing process Delphi technique This is a process where a group of exper
ts in the field gather together. The group members are asked to make individual
judgments about a particular subject, these judgments are compiled and returned
to the group members, so that they can compare with those of others and revise,
then reach conclusion after 5 to 6 rounds. Projective techniques In projective t
echniques, respondents are asked to interpret the behavior of users, rather than
describe their own behavior. In interpreting the behavior of others, respondent
s indirectly project their own motivation and feelings into the situation. The g
eneral categories of projective techniques are: 1. Word association test 2. Comp
letion technique 3. TAT and 4. Cartoon test Word Association Test This is consis
ts of presenting a series of stimulus words to the respondent. For eg: What bran
d of detergent comes to your mind first, when I mention washing of an expensive
cloth? Completion techniques Sentence Completion Eg: Earnings of software profes
sional Story Completion: A situation is described to a respondent who is asked t
o complete the story based on his opinion and attitude. Thematic Apperception Te
st TAT is a projective technique. It is used to measure the attitude and percept
ion of the individual.
45

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Some picture cards are shown to respondents. The respondent is required to tell
the story by looking at the picture. When the subjects start telling the story,
the researcher notices the respondents expression, pauses and emotions to draw th
e inference.
3.5 Sampling A sample is a part of a target population, which is carefully selec
ted to represent the population. Sample Frame Sampling frame is the list of elem
ents from wh ich the sample is actually drawn. Actually, sampling frame is nothi
ng but the correct list of population. Eg: Telephone directory, Product finder,
Yellow pages Distinction between Census and Sampling Census refers to complete i
nclusion of all elements in the population. A sample is a sub-group of the popul
ation Sampling Process: 1. Define the population 2. Identify the sampling frame.
3. Specify the sampling unit 4. Selection of sampling method 5. Determination o
f sample size 6. Specify sampling plan Define the population
Elements- Companys p
roduct Sampling unit-Retail outlet, super market Extent- Hyderabad and Secundera
bad Time-April 10 to May 10
Identify the sampling frame Sampling frame could be
46

Telephone Directory

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

Localities of a city using the municipal corporation listing Any other list cons
isting of all sampling units.
Specify the sampling unit Individuals who are to be contacted are the sampling u
nits. If retailers are to be contacted in a locality, they are the sampling unit
s. Selection of sampling method This refers to whether a. Probability b. non-pro
bability methods are used Determine the sample size We need to decide how many e
lements of the target population are to be chosen? For eg: If it is an explorato
ry research, the sample size will be generally small. For conclusive research, s
uch as descriptive research, the sample size will be large. Specify the sampling
plan A sampling plan should clearly specify the target population. Improper def
ining would lead to wrong data collection. 3.6 Sampling Types/ Methods/ Techniqu
es
Sampling is divided into two types.
Probability sampling: In a probability sa
mple, every unit in the population has equal chances for being selected as a sam
ple unit.
Non-probability sampling: In the non-probability sampling, the units i
n the population have unequal or negligible, almost no chances for being selecte
d as a sample unit. Probability sampling techniques
Random Sampling Stratified r
andom sampling Systematic sampling Cluster sampling Multi-stage sampling
Random Sampling
47

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Simple random sample is a process in which every item of the population has an e
qual probability of being chosen.
Lottery method: We can now write down all the
combination, put them in a box. Mix them and pull one at random. Systematic Rand
om sampling Sampling interval K is determined by the following formula K=No. of
units in the population ______________________________ No. of units desired in t
he sample. Stratified Random Sampling
A probability sampling procedure in which
simple random sub-samples are drawn from within different strata that are, more
or less equal on some characteristics. Proportionate stratified sampling: The nu
mber of sampling units drawn from each stratum is in proportion to the populatio
n size of that stratum.
Disproportionate stratified sampling: The number of samp
ling units drawn from each stratum is based on the analytical consideration, but
not in proportion to the size of the population of that stratum. Cluster Sampli
ng The population is divided into clusters.
A simple random sample of few cluste
rs is selected. All the units in the selected cluster are studied Multi-stage Sa
mpling The name implies that sampling is done in several stages. This is used wi
th stratified cluster designs. The management of a newly opened club is solicits
new membership. During the first rounds, all corporate were sent details so tha
t those who are interested may enroll. Having enrolled, the second round concent
rates on how many are interested to enroll for various entertainment activities
that club offers such billiards, indoor sports. information, you might stratify
the interested respondents After obtaining this
48

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Area Sampling If clusters happen to be some geographic subdivisions, in that cas
e cluster sampling is better known as area sampling. Eg: If someone wants to mea
sure the sales of toffee in retail stores, one might choose a city locality and
then audit toffee sales in retail outlets in those localities
Non-Probability Sampling
Judgment Sampling The investigator uses his discretion in selecting sample obser
vations from the universe. Eg: Test market cities are being selected, based on t
he judgment sampling, because these cities are viewed as typical cities matching
with certain demographical characteristics.
Sequential Sampling This is a method in which the sample is formed on the basis
of a series of successive decisions. Eg: If the evidence is not conclusive after
a small sample, more samples are required. If the position is still inconclusiv
e, still larger samples are taken.
Quota Sampling Quota sampling is quite frequently used in marketing research.
Ca
tegory General merit
Sport
NRI
SC/ST
Total Suppose, 2,00,000 students are
appearing for a competitive examination. We need to select 1% of them based on q
uota sampling. Quota 1,000 600 100 300 2000
49

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Snow ball Sampling In this method, the initial group of respondents is selected
randomly. Subsequent respondents are being selected based on the opinion or refe
rrals provided by the initial respondents
Panel Samples To give an example, suppose that one is interested in knowing the
change in the consumption pattern of households. A sample of households is drawn
. These households are contacted to gather information on the pattern of consump
tion. Subsequently, say after a period of six months, the same households are ap
proached once again and the necessary information on their consumption is collec
ted.
Errors in Sampling/ Sampling bias Sampling error is the gap between the sample m
ean and population mean. An MNC bank wants to pick up a sample among the credit
card holders. They can readily get a complete list of credit card holders, which
forms their data bank. From this frame, the desired individuals can be chose. I
n this example, sample frame is identical to ideal population namely all credit
card holders. There is no sampling error in this case
Eg:2 Assume that a bank wants to contact the people belonging to a particular pr
ofession over phone to market a home loan product. The sampling frame in this ca
se is the telephone directory. Reasons may be People might have migrated, Number
s have changed, Numbers may not be listed. Thus in this case, there will be a sa
mpling error
Non-Sampling Error/ Non-response Error
This occurs, because the planned sample a
nd final sample vary significantly.
Eg: Marketers want to know about the televis
ion viewing habits across the country. They choose 500 households and mail the q
uestionnaire. Assume that only 200 respondents reply. If there is no response, t
hen its Non-response error.
50

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Data Error
This occurs during the data collection, analysis or interpretation. R
espondents sometimes give distorted answers unintentionally for questions which
are difficult, or if the question is exceptionally long and the respondent may n
ot have answer. How to reduce Sampling Error
To choose appropriate sample size.
Non-sampling error Provide incentives to collect data, against the golden rule o
f research. Do not ask sensitive questions Training the interviewer Pretest the
questionnaire Modify the sampling frame to make it a representative of the popul
ation
How will you decide the sample size? First factor must be considered in estimati
ng sample size, is the error permissible.
Greater the desire precision, larger w
ill be the sample size Higher the confidence level in the estimate, the larger t
he sample must be. The greater the number of sub-groups of interest within the s
ample, the greater its size must be.
Cost is a factor that determines the size o
f the sample.
The issue to be considered in deciding the necessary sample size i
s the actual number of questionnaires that must be sent out. Calculation wise, w
e may send questionnaires to the required number of people, but we may not recei
ve the response.
51

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
UNIT - IV
4 INTRODUCTION
4.1 DATA ANALYSIS-EDITING 4.2 UNIVARIATE ANALYSIS 4.3 BIVARIATE ANALYSIS 4.4 MUL
TIVARIATE ANALYSIS 4.5 DISCRIMINANT ANALYSIS 4.6 FACTOR ANALYSIS 4.7 CLUSTER ANA
LYSIS 4.8 CONJOINT ANALYSIS 4.9 MULTI-DIMENSIORNAL SCALING 4.10 APPLICATION OF S
PSS FOR DATA ANALYSIS
1. INTRODUCTION: 4.1 Editing: Data editing is the activity aimed at detecting an
d correcting errors (logical inconsistencies) in data. The customary first step
in analysis is to edit the raw data. Editing detects errors and omissions, corre
cts them when possible, and certifies that maximum data quality standards are ac
hieved. Alternately, recorded raw data is normally less than perfect and the fir
st phase through which this data must pass is editing. The editors purpose is to
guarantee that data are:
52

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
1. Accurate 2. Consistent with the intent of the question and other information
in the survey 3. Uniformly entered 4. Complete 5. Arranged to simplify coding an
d tabulation Objectives of data editing
To ensure the accuracy of data To establ
ish the consistency of data To determine whether or not the data are complete To
ensure the coherence of aggregated data; and To obtain the best possible data a
vailable
Different stages of Editing: The editing may be done in two stages they are as f
ollow: 1. FIELD EDITING 2. OFFICE EDITING Field Editing: The Field editing is a
preliminary editing done to detect the glaring omissions and inaccuracies in the
data. It is useful to controlling the field force and removing misunderstanding
. For example: If interviewers did not follow the correct patterns or if open en
ded responses reflect a lack of probing. When poor interview is detected; superv
isor may train the interviewer. Office Editing: It is another type of editing jo
b of data collection performed by a centralized office staff to perform. The res
earcher must set up a centralized office with all facilities for editing and cod
ing purpose by which coordination can be accomplished.
53

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
The office editing is done after the field editing. This implies a complete and
thorough scrutiny of the questionnaire. There should be expert editors in the of
fice to evaluate and examine the completed returns of the respondents. WHAT IS D
ATA CODING?
A systematic way in which to condense extensive data sets into smalle
r analyzable units through the creation of categories and concepts derived from
the data. The process by which verbal data are converted into variables and catego
ries of variables using numbers, so that the data can be entered into computers
for analysis. WHEN TO CODE?
When testing a hypothesis (deductive), categories and
codes can be developed before data is collected. When generating a theory (indu
ctive), categories and codes are generated after examining the collected data. o
Content analysis o How will the data be used?
Categories and Variables
Variables:
Gender
Age
Do you like ice cream?
Categories:
Male
Female
18-25 26-33 3441
yes
no
54

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
DATA ENTRY The process transforming data from a research project, such as answer
s to a survey questionnaire, to computers is referred to as data entry. The proc
ess of entering data into a
computerized database or spreadsheet.
55

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
4.2 Univariate Analysis Only one variable (Eg: Blood types) Can calculate percen
tage (Eg. 30% have A blood group etc.) 4.3 Bivariate analysis is the simultaneou
s analysis of two variables (attributes). It explores the concept of relationshi
p between two variables, whether there exists an association and the strength of
this association, or whether there are differences between two variables and th
e significance of these differences. There are three types of bivariate analysis
. Numerical & Numerical Categorical & Categorical Numerical & Categorical
56

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
ANOVA Tests the significance of group differences between two or more groups Tes
ts with two or more categories only determines that there is a difference betwee
n groups, but doesnt tell which is different eg: Do CAT scores differ for low- mi
ddle- and high-income students?
Analysis of Variance (ANOVA) The ANOVA test assesses whether the averages of mor
e than two groups are statistically different from each other. This analysis is
appropriate for comparing the averages of a numerical variable for more than two
categories of a categorical variable. 4.4 Multivariate Analysis Many statistica
l techniques focus on just one or two variables. Multivariate analysis (MVA) tec
hniques allow more than two variables to be analysed at once. Imagine out of the
five senses you only had sight. From your perspective you could see the world b
ut you would not be able to hear the sounds around you, smell, and taste or feel
things. Your understanding of the world would be more limited. Most of us use a
ll of our senses to understand the world around us i.e. not just one measurement b
ut the combination of several senses working together. In multivariate analysis
we use the information from many sources simultaneously to get a better picture
of our surroundings. MANOVA The general purpose of multivariate analysis of vari
ance (MANOVA) is to determine whether multiple levels of independent variables o
n their own or in combination with one another have an effect on the dependent v
ariables.
57

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
4.5 Discriminate Analysis In this analysis, two or more groups are compared. IN
the final analysis, we need to find out whether the groups differ one from anoth
er. Eg; where discriminate analysis is used: 1. Those who buy our brand and thos
e who buy competitors brand. 2. Good salesman, poor salesman, medium salesman. 3.
Those who go to Food world to buy and those who buy in a kirana shop. 4. Heavy
user, medium user and light user of the product. 4.6 Factor analysis In purpose
of Factor analysis is to group large set of variable factors into fewer factors.
Each factor will account for one or more component. Each factor a combination o
f many variables. Customer feedback about a two-wheeler manufactured by a compan
y. The MR Manager prepares a questionnaire to study the customer feedback. ident
ified six variables or factors for this purpose. They are as follows: 1. Fuel ef
ficiency (A) 2. Durability (B) 3. Comfort 4. Spare parts availability(D) 5. Break
down frequency(E) 6. Price(F) A, B,D,E into Factor-1 F into Factor-2 C into Fac
tor-3 Factor-1 can be termed as Technical factor Factor-2 can be termed as price
factor; Factor-3 can be termed a s personal factor The researcher has
58

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
For future analysis, while conducting a study to obtain customers opinion, three
factors mentioned above would be sufficient. One basic purpose of using factor a
nalysis is to reduce the number of independent variables in the study. 4.7 Clust
er Analysis It is used: 1. To classify personal or objects into small number of
clusters or group. 2. To identify specific customer segment for the companys bran
d. Cluster analysis is a technique used for classifying objects into groups. Thi
s can be used to sort data (a number of people, companies, cities, brands or any
other objects) into homogeneous groups based on their characteristics. The resu
lt of cluster analysis is a grouping of the data into groups called clusters. Th
e researcher can analyze the clusters for their characteristics and give the clu
ster, names based on these. A housing finance corporation wants to identify and
cluster the basic characteristics, lifestyles and mindset of persons who would b
e availing housing loans. Clustering can be done based on parameters such as int
erest rates, documentation, processing fee, number of installments. Etc. Process
There are two ways in which Cluster Analysis can be carried out: 1. First, obje
cts/respondents are segmented into a pre-decided number of clusters. In this cas
e, a method called non-hierarchical method can be used, which partitions data in
to the specified number of clusters. 2. The second method is called the hierarch
ical method. 4.8 Conjoint Analysis It is concerned with the measurement f the jo
int effect of two or more attributes that are important from the customers point
of view. Eg: An airline would like to know, which is the most desirable
combination of attributes to a frequent traveler: a) Punctuality b) Air fare c)
Quality of food served on the flight, and d) Hospitality and empathy shown.
59

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Process Design attributes for a product are first identified. For a shirt manufa
cturer, these could be design such as designer shirts vs. plain shirts, this pri
ce of Rs 400 versus Rs. 800. The outlets can have exclusive distribution or mass
distribution. All possible combinations of these attribute levels are then list
ed out. Each design combination will be ranked by customers and used as input da
ta for conjoint analysis. Then the utility of the products relative to price can
be measured. There are three steps in conjoint analysis a. Identification of re
levant products or service attributes. b. Collection of data c. Estimation/Evalu
ate the worth for the attribute chosen. 4.9 Multidimensional scaling (MDS) It is
a set of related statistical techniques often used in information visualization
for exploring similarities or dissimilarities in data. MDS is a special case of
ordination. An MDS algorithm starts with a matrix of itemitem similarities, and
then assigns a location to each item in N-dimensional space, where N is specifie
d a priori. For sufficiently small N, the resulting locations may be displayed i
n a graph or 3D visualization. Types MDS algorithms fall into a taxonomy, depend
ing on the meaning of the input matrix: 1. Classical multidimensional scaling Al
so known as Torgerson Scaling or TorgersonGower scaling, takes an input matrix gi
ving dissimilarities between pairs of items and outputs a coordinate matrix whos
e configuration minimizes a loss function called strain. 2. Metric multidimensio
nal scaling A superset of classical MDS that generalizes the optimization proced
ure to a variety of loss functions and input matrices of known distances with we
ights and so on. A useful loss function in this context is called stress, which
is often minimized using a procedure called stress majorization.
60

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
3. Non-metric multidimensional scaling In contrast to metric MDS, non-metric MDS
finds both a non-parametric monotonic relationship between the dissimilarities
in the item-item matrix and the Euclidean distances between items, and the locat
ion of each item in the low-dimensional space. The relationship is typically fou
nd using isotonic regression. Louis Guttman's smallest space analysis (SSA) is a
n example of a non-metric MDS procedure. 4. Generalized multidimensional scaling
An extension of metric multidimensional scaling, in which the target space is a
n arbitrary smooth nonEuclidean space. In case when the dissimilarities are dist
ances on a surface and the target space is another surface, GMDS allows finding
the minimum-distortion embedding of one surface into another. 4.10 Application o
f SPSS 1. Start SPSS. Go to Windows Start menu and choose Programs, and the SPSS
for Windows. Then the Data Editor window will open. 2. Step 2 Appearing in the
list boxes will be the variable names. Often it is best when these variable titl
es are in alphabetical order so you may have to change the order. From the menu
choose Edit then Options, then go to the General Tab and select Display labels i
n the Variables list group. Select Alphabetical and then click OK twice. 3. Step
3 Open a Data File. From the menu choose File, Open, Data. The Open File box wi
ll display. Double click Tutorial folder, double click sample file folders, clic
k the file demo.sav, click Open. From the menus choose View and then Value Label
s. 4. Step 4 Run an Analysis. From the menus choose Analyze, Descriptive Statist
ics, then Frequencies. The frequencies dialog box will be displayed and the icon
s will provide the information needed about the data type and level of measureme
nt.
61

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
How to use SPSS 1. Open SPSS and import your data. You can import your data set
from an Excel file or any other CSV file. To import your data, click "Open Anoth
er Type of File" and choose the file you would like to import. If you would like
to enter new data, simply click "Type in Data". When you have chosen a data sou
rce, click "Ok." 2. Step 2 Edit your raw data in the variable view. There are tw
o views in SPSS, (1) data view and (2) variable view. Click the "Variable View"
tab located on the bottom of the application and edit your raw data. Here you ca
n edit categories the name of your variable, type of variable and measurement ca
tegory. It is important to properly edit your variables, as many statistical tes
ts will rely upon properly formatted data. 3. Step 3 Choose a statistical test.
Once you have entered and formatted your data, you will be ready to run a statis
tical test. The most common tests are found in the "Analyze" tab located across
the top of the application. 4. Step 4 Paste your syntax. Before completing a sta
tistical test, you should always paste your syntax by clicking "Paste" in the di
alog box. This will copy your syntax into a separate file. If the application cr
ashes, or you need to run the same test again, you can use the syntax file to in
itiate a statistical test. 5. Step 5 View your output. Once your statistical tes
t has been run, you can view the results in an output file that will open in a s
eparate window Advantages of SPSS SPSS is the statistical package most widely us
ed by political scientists. There seem to be several reasons why:
SPSS has been
around since the late 1960s. Statistical Package for the Social Sciences, Of the
major packages, it seems to be the easiest to use for the most widely used stat
istical techniques
62

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

One can use it with either a Windows point-and-click approach or through syntax
(i.e., writing out of SPSS commands Many of the widely used social science data
sets come with an easy method to translate them into SPSS; this significantly re
duces the preliminary work needed to explore new data. Disadvantages of SPSS
There are also two important limitations that deserve mention at the outset:
SPS
S users have less control over statistical output than, But, once a researcher w
ants greater control over the equations or the output, she or he will need to ei
ther choose another package or learn techniques for working around SPSS
Once a r
esearcher begins wanting to significantly alter data sets, he or she will have t
o either learn a new package or develop greater skills at manipulating SPSS. Ove
rall, SPSS is a good first statistical package for people wanting to perform qua
ntitative research in social science because it is easy to use and because it ca
n be a good starting point to learn more advanced statistical packages.
63

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
UNIT - V
5 INTRODUCTION
5.1 RESEARCH REPORT 5.2 TYPES OF REPORT 5.3 CONTENT OF A BUSINESS RESEARCH REPOR
T 5.4 EXECUTIVE SUMMARY 5.5 CHAPTERISATION 5.6 ROLE OF AUDIENCE 5.7 READABILITY,
COMPREHENSION, TONE, FINAL PROOF 5.8 ETHICS IN RESEARCH 5.9 SUBJECTIVITY AND OB
JECTIVITY IN RESEARCH
1. INTRODUCTION: 5.1 RESEARCH REPORT
The research report is the compilation of f
indings from a piece of research A research report is a precise presentation of
the work done by a researcher while investigating a particular problem RESEARCH
REPORT WRITING Report writing is the final stage of the business research and it
is concerned with making the findings available to the readers with varied inte
rests. It is important to understand as to how to write a report. Your final rep
ort should be in accordance with the writing style used at your university. What
ever style you adopt, the content of the research report never varies. The final
report of a research exercise takes a variety of forms.
64

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

A research report funded by an educational institution may be in the form of wri


tten document. A research report may also take the form of an article in a profe
ssional journal.
NEED FOR RESEARCH REPORT
The purpose of research is to search for knowledge. (It
is just to analyze a particular situation and finding out some solution, that s
olution/result will be finished in the form of report.)
Reporting is the process
through which a basis ground is prepared for the exchange of ideas or thoughts.
Reporting helps the researcher to make specific recommendation for a course of
action over, the phenomena, he studied. This is what actually expected in case o
f any study. 5.2 TYPES OF REPORT 1. Oral report 2. Written report a) The Popular
report b) The report for the administration c) The technical report d) Formal r
eport ORAL REPORT The oral reporting is that the oral presentation in meetings.
For example: seminars, conferences, symposia, etc. is mainly oral presentation.
WRITTEN PRESENTATION When compare to oral report, the preparation and presentati
on of written is somewhat difficult because in case of oral report the presenter
can talk in their own style, but in case of written they should be very careful
about the alignment, meaning, words, language, etc.
65

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Written reports themselves are different types. In the context of reporting to m
anagement of a company, reports are classified as: external and internal reports
; routine and special reports; and operating and special reports. A useful class
ification of research reports seems to be the one based on the audience, i.e., t
he people to whom the reports is meant. On this basis, written reports can be ca
tegorized as follows:
The popular report The report for the administration The t
echnical report Formal report
Popular report: This is the report meant to be read by public in the development
s taking place around them. For example: a researcher has worked on denudation o
f forest and ecological balance (research on forest i.e., about cause and effect
s of cutting and destroying trees in forest).the public in this context would be
interested in such facts as the extent of forests, denudation, impact of denuda
tion on ecology and specific sectors like agriculture. The report for the admini
stration: Many of the business reports are of this type. They may be submitted t
o any level. Usually, Supervisors submit periodical reports about production, ma
chinery maintenance, overtime, etc. Similar reports are also submitted by the mi
ddle level managers to the top level management The technical reports: A technic
al report is written by an expert to be read by another expert. In this sense, a
thesis is a technical report intended to be read by another researcher. Formal
report: A formal report is used to document the results of an experiment, a desi
gn, or to pass on any type of information in a formal style. When writing a form
al report it is important to ensure good English use and to follow the correct f
ormat as like as follow:
Abstract or summary Outline
66

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

Introduction Discussion Conclusion Recommendations appendix


Research report format: The following outline is the suggested format for writin
g the research report 1. Title page 2. Letter of authorization 3. Summary of fin
dings 4. Table of content
List of tables List of figures
5. Introduction Background to the research problem Objectives Hypothesis
6. Methodology 7. Data collection

Sample and sampling method

8. Statistical or qualitative methods used for data analysis 9. Sample descripti


on 10. Findings 11. Limitations 12. Results, interpretation and conclusions. 13.
Recommendation 14. Appendices 15. Bibliography
67

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013

5.3 CONTENT OF A BUSINESS RESEARCH REPORT:


Problem definition
s Background material Methodology Sampling design Research design Data collectio
n Data analysis Limitation Findings Conclusions Recommendations Appendices Bibli
ography Index Conclusion
5.4 EXECUTIVE SUMMARY Executive summary is a term used in business for a short d
ocument that summarizes a longer report, in such a way that readers can rapidly
become acquainted with a large body of material without having to read it all. S
teps to write an executive summary: Step 1: Plan to create a summary each time y
ou write a business report exceeding four pages. Write the summary after you wri
te the main report, and make sure it is no more than 1/10 the length of the main
report.
68

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Step 2: List the main points the summary will cover in the same order they appea
r in the main report. Step 3: write a simple declarative sentence for each of th
e main point Step 4: Add supporting or explanatory sentences as needed, avoiding
unnecessary technical material and jargon. Step 5: Read the summary slowly and
critically, making sure it conveys your purpose, message and key recommendations
. You want readers to be able to skim the summary without missing the point of t
he main report. Step 6: Check the errors of style, spelling, grammar and punctua
tion. Ask a fellow writer to proofread and edit the document. Step 7: Ask a nont
echnical person- for example, your parents or your spouse to read the document.
If it confuses or bores them, the summary probably will have the same effect on
other nontechnical readers. 5.5 CHAPTERISATION Chapterisation means scanning of
the entire report taken by the researcher. The subject of the report is to be di
vided into different parts, arrange them in a systematic way and mention which a
spects of them in a systematic way and mention which aspects of the research wil
l be studied in which chapter. It should be planned that one chapter will seems
to be a continuation of the previous one. CHAPTERS AND THEIR CONTENT:
Introducti
on Review of related literature
Design of the study
Analysis and interpretation
of data Main findings and recommendation Summary
69

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Writing a Report During your studies you may be required to research a particula
r area and produce a report. For Instance depending on your area of study you mi
ght be asked to write a report on the performance. Some of the reasons we write
reports are to Inform Make proposals or recommendations for change Analyze and s
olve problems Present the findings of an investigation or project Record progres
s Your lecturer or teacher will usually provide you with the following informati
on The topic or subject of the report The required length and due date A clear i
dea of its purpose and who will read it The format headings to be used and their
order 5.6 ROLE OF AUDIENCE Audience Research is an important tool to study the
characteristics of target audience for various media including demographic and p
sycho-graphic details of the audience, their exposure to various media, listenin
g/viewing/reading habits, needs and tastes for various media contents and moreov
er, to estimate the size of audience for various programmes and programme rating
s. Audience Research on the one hand provides programme feedback to programme pr
oduces to prepare audience friendly programmes and on the others provides audien
ce share for the various media contents to advertisers and marketers which in tu
rn , helps in fixing rates for the various programmes
70

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
and channels. Thus, this gives consumer insight to the stakeholders and works as
eyes and ears for the media organizations. 5.7 READABILITY Readability is the e
ase in which text can be read and understood. Various factors to measure readabi
lity have been used, such as "speed of perception," "perceptibility at a distanc
e," "perceptibility in peripheral vision," "visibility," "the reflex blink techn
ique," "rate of work" (e.g., speed of reading), "eye movements," and "fatigue in
reading." Readability is distinguished from legibility which is a measure of ho
w easily individual letters or characters can be distinguished from each other.
Readability can determine the ease in which computer program code can be read by
humans, such as through embedded documentation. COMPREHENSION In general usage,
and more specifically in reference to education and psychology, it has roughly
the same meaning as understanding. Reading comprehension measures the understand
ing of a passage of text. Reading comprehension It is defined as the level of un
derstanding of a text. This understanding comes from the interaction between the
words that are written and how they trigger knowledge outside the text. TONE IN
WRITING: In written composition, tone is often defined as what the author (rath
er than the reader) feels about the subject. (What the reader feels about it, by
contrast, is referred to as the mood.) Tone is also sometimes confused with voi
ce, which can be explained as the authors personality expressed in writing. Tone
is established when the author answers a few basic questions about the purpose o
f the writing: Why am I writing this? Who am I writing it to?
71

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
What do I want the readers to learn, understand, or think about? Tone depends on
these and other questions. In expository, or informative, writing, tone should
be clear and concise, confident but courteous. The writing level should be sophi
sticated but not pretentious, based on the readers familiarity with or expertise
in the topic, and should carry an undertone of cordiality, respect, and, especia
lly in business writing, an engagement in cooperation and mutual benefit. FINAL
PROOFREADING After finishing the documentation, one is ready to proofread the re
port and to prepare final manuscript. Proofreading is the process of checking wo
rk for errors in spelling, grammar, usage, level of language, capitalization, pu
nctuation, and documentation. Final editing of the report should be taken-up aft
er completing the writing of research report. This helps in identifying mistakes
, if any, better and correcting the mistakes. GUIDELINES FOR PROOFREADING
Double
check the spellings of proper names, such as the names of people and places. Ch
eck to see that the quotations you have used fit grammatically into the sentence
s in which they appear. Check to see that your language is not too informal Chec
k all titles of works to make sure that these rules have been followed. Check ev
ery sentence to make sure that it has an end mark. If the sentence ends with a p
arenthetical citation, make sure that the citations appears before the end mark.
In the case of a long, indented quotation , the citation should follow the end
mark
Check every quotation in the body of the text to make sure that it begins a
nd ends with quotation mark. Check to see that you have used points of ellipsis
properly in edited quotations. Make sure that every citation corresponds to an e
ntry in the works cited list. Make sure that quotation, summary, or paraphrase i
s followed by a parenthetical citation.
72

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
5.8 ETHICS IN RESEARCH Although most people acquire their sense of right and wro
ng during childhood, moral development occurs throughout life and human beings p
ass through different stages of growth as they mature. Ethical norms are so ubiq
uitous that one might be tempted to regard them as simple commonsense. ETHICAL B
EHAVIOUR OF RESEARCH The following is a rough and general summary of some ethica
l principles that various codes address*: Honest: Strive for honesty in all scie
ntific communications. Honestly report data, results, methods and procedures, an
d publication status. Do not fabricate, falsify, or misrepresent data. Do not de
ceive colleagues, granting agencies, or the public. Objectivity: Strive to avoid
bias in experimental design, data analysis, data interpretation, peer review, p
ersonnel decisions, grant writing, expert testimony, and other aspects of resear
ch where objectivity is expected or required. Avoid or minimize bias or self-dec
eption. Disclose personal or financial interests that may affect research. Integ
rity: Keep your promises and agreements; act with sincerity; strive for consiste
ncy of thought and action.
Carefulness: Avoid careless errors and negligence; carefully and critically exam
ine your own work and
the work of your peers. Keep good records of research activities, such as data c
ollection, research design, and correspondence with agencies or journals. Openne
ss: Share data, results, ideas, tools, resources. Be open to criticism and new i
deas. Respect for Intellectual Property: Honor patents, copyrights, and other fo
rms of intellectual property. Do not use unpublished data, methods, or results w
ithout permission. Give credit where credit is due. Give proper acknowledgement
or credit for all contributions to research. Confidentiality: Protect confidenti
al communications, such as papers or grants submitted for publication, personnel
records, trade or military secrets, and patient records.
73

PPG INSTITUTE OF TECHNOLOGY


PPG BUSINESS SCHOOL
BATCH: 2011-2013
LECTURE NOTES - II SEMESTER
ACADEMIC YEAR: 2012-2013
Responsible Publication: Publish in order to advance research and scholarship, n
ot to advance just your own career. Avoid wasteful and duplicative publication.
Competence: Maintain and improve your own professional competence and expertise
through lifelong education and learning; take steps to promote competence in sci
ence as a whole. Legality: Know and obey relevant laws and institutional and gov
ernmental policies. Human Subjects Protection: When conducting research on human
subjects, minimize harms and risks and maximize benefits; respect human dignity
, privacy, and autonomy; take special precautions with vulnerable populations; a
nd strive to distribute the benefits and burdens of research fairly. 5.9 SUBJECT
IVITY AND OBJECTIVITY OF RESEARCH: SUBJECTIVITY refers to that the results are r
esearcher -dependent. Different researchers may reach different conclusions base
d on same interview. In contrast, when a survey respondent provides a commitment
score on a quantitative scale, it is thought to be more objective because the n
umber will be the same no matter what researcher is involved in the analysis. Su
bjectivity guides everything from the choice of topic that one studies, to formu
lating hypotheses, to selecting methodologies, and interpreting data. OBJECTIVIT
Y pre-supposes an independent reality that can be grasped. If there is no indepe
ndent reality, or if reality cannot be apprehended, or if reality is mere the co
ncoction of the observer, then the notion of objectivity is moot. DIFFICULTIES I
N ACHIEVING OBJECTIVITY OF RESEARCH: Objectivity is the first condition of resea
rch. It means willingness and ability to examine the evidence dispassionately. I
n other words, objectivity, means basing conclusion on facts without any bias ju
dgment. This difficulty arises out of the adverse influences of: 1. Personal pre
judices and bias, 2. Value judgments, 3. Ethic dilemma, and Complexity of social
phenomenon
74