RESEARCH METHODOLOGY
Module IV Research Design
4.A RESEARCH DESIGN
A research design is a comprehensive plan guiding researcher to achieve its objectives. It is
a detailed blueprint of the research. A research design consists of 1)Definition of the
problem 2) Sources of data 3) Methods of data collection 4)Sampling plan 5) Methods of
data analysis 6) Layout of research report
4.B TYPES OF RESEARCH DESIGNS
4.B. 1 EXPLORATORY RESEARCH
Managers often conduct preliminary investigation to find out problem and formulate
research problem. The research conducted to get more insight into the problem and
understand its nature or to create new ideas or various possible solutions is called as
exploratory research. The exploratory research is conducted in the initial phase of
marketing research to explore more about problem and with an understanding that a
detailed research will follow with inputs from this research. It is used to generate
hypothesis or identifying variables to be studied. The exploratory research may also be
used for concept testing. E.g. Exploratory research may be conducted to new product
ideas which will followed by a detailed research to study its acceptance and feasibility.
Exploratory Research is highly flexible in nature and uses unstructured techniques like
focus group, observation, projective techniques, Case studies, brainstorming etc.
and analysis of secondary data.
While there are several types of exploratory techniques possible these are the three
techniques with the widest applications for business researchers.
• Secondary data analysis is also called a literature search. Within secondary data
exploration, researchers should start first with an organization’s own data archives.
The second source of secondary data is published documents prepared by authors
outside the sponsor organization.
• Experience surveys are semi-structured or unstructured interviews with experts
on a topic or a dimension of a topic. Experience surveys are sometimes called expert
interviews or key informant surveys. Even though the term survey is in the name, it
is not a closed-ended, structured survey. Rather, experience surveys are interviews
designed to extract as much information as possible from the expert’s knowledge.
Broad questions guide the discussion. Some examples of groups who might be
identified for an experience survey include potential car buyers, dealer sales
representatives, advertising columnists, and automotive industry analysts.
• Focus groups are discussions on a topic involving a small group of participants led
by a trained moderator. Focus groups are widely used in business research. They
are led by a trained moderator and typically include 6-10 participants. The
facilitator uses group dynamics principles to focus or guide the group in an
exchange of ideas, feelings, and experiences on a specific topic. Focus groups can
take place in a variety of settings, but many take place in a focus group room
equipped with one-way window and recording devices.
For example, Researcher may want to identify causes of non-acceptance of online
marketing.
4.B.2 DESCRIPTIVE RESEARCH DESIGN
The Descriptive Research as the name suggest, is concerned with ‘what’,’where’,’when’,
’how’ and ‘where’ aspects of the marketing decision problem. It may be used to
ascertain certain magnitude (e.g. percentage of buyers of a particular brand) or
describe characteristics of customer, phenomena. Some examples of descriptive studies
are:-
1) Determining the sales or marketing share of the market.
2) Describe demographic profile of the customer.
3) Stating the reasons for market growth of a particular product.
The descriptive research is used in examining well formulated hypothesis. It is typically
characterized by a fair degree of structure in research design, clearly defined areas of
enquiry, and a detailed plan of the sources of data as well as methods of data collection
to be employed. The information obtained in descriptive research serves as the basis
for decision making. The descriptive research designs may be cross-sectional or
longitudinal. Cross-sectional studies are carried out at a single moment in time,
therefore the applicability is temporal (time) specific and conducted on a sub-section of
the respondent population. E.g. we study investor behaviour at particular period of the
study using a sample of investors. Longitudinal studiesinvolve selection of a
representative group as a [Link] are repeated measurements of the researched
variable on this panel over fixed intervals of time. Once selected the panel composition
needs to stay constant over the study period. E.g. Brand switching behaviour can be
studies using a panel of consumers monitored over six months for usage of a particular
product.
4.B.3 CAUSAL OR DIAGNOSTIC RESEARCH DESIGN
The causal research design is concerned with examining cause and effect relationships.
It is concerned with finding answers to ‘why’ aspect of a problem. The causal research
aims at examining the relationship between observed (Dependent) variable and its
possible causes (Independent Variables).
Some of the examples of causal research are –
1) Let us assume that the price of a product is reduced by 10% during a month. If the
sales at the end of the subsequent quarter rise by a percentage significantly higher
than the corresponding quarter of previous year could this be attributed to the
reduction in price?
2) Will the increasing promotion expenses bring in growth in sales volume?
3) Does the age and income levels have decisive role in selection of saving options?
Causal research studies tend to be more complex and require a well-defined problem, a
clear understanding of dependent and independent variables to be studied, knowledge
of sources of data and methods to be used for data collection. Experimental method is
most commonly used in this type of research design.
4.3.B.1 IMPORTANT EXPERIMENTAL DESIGNS
Experimental design refers to the framework or structure of an experiment and as such,
there are several experimental designs. We can classify experimental designs into two
broad categories, viz., informal experimental designs and formal experimental designs.
Informal experimental designs are those designs that normally use a less sophisticated
form of analysis based on differences in magnitudes, whereas formal experimental designs
offer relatively more control and use precise statistical procedures for analysis.
Important experiment designs are as follows:
(a) Informal experimental designs:
(i) Before-and-after without control design.
(ii) After-only with control design.
(iii) Before-and-after with control design.
(b) Formal experimental designs:
(i) Completely randomized design (C.R. Design).
(ii) Randomized block design (R.B. Design).
(iii) Latin square design (L.S. Design).
We may briefly deal with each of the above stated informal as well as formal experimental
designs.
1. Before-and-after without control design: In such a design a single 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 dependent variable is measured again after the
treatment has been introduced. The effect of the treatment would be equal to the level of
the phenomenon after the treatment minus the level of the phenomenon before the
treatment.
2. After-only with control design: In this design two groups or areas (test area and
control area) are selected and the treatment is introduced into the test area only. The
dependent variable is then measured in both the areas at the same time. Treatment impact
is assessed by subtracting the value of the dependent variable in the control area from its
value in the test area.
The basic assumption in such a design is that the two areas are identical with respect to
theirbehaviour towards the phenomenon considered. If this assumption is not true, there is
the possibility of extraneous variation entering into the treatment effect. However, data can
be collected in such a design without the introduction of problems with the passage of time.
In this respect the design is superior to before-and-after without control design.
3. Before-and-after with control design: In this design two areas are selected and the
dependent variable is measured in both the areas for an identical time-period before the
treatment. The treatment is then introduced into the test area only, and the dependent
variable is measured in both for an identical time-period after the introduction of the
treatment. The treatment effect is determined by subtracting the change in the dependent
variable in the control area from the change in the dependent variable in test area. This
design is superior to the above two designs for the simple reason that it avoids
extraneousvariation resulting both from the passage of time and from non-comparability of
the test and control areas. However, at times, due to lack of historical data, time or a
comparable control area, we should prefer to select one of the first two informal designs
stated above.
4. Completely randomized design (C.R. design): It is the simplest possible design and its
procedure of analysis is easier. The essential characteristic of the design is that subjects are
randomly assigned to experimental treatments (or vice-versa). For instance, if we have 10
subjects and if we wish to test 5 under treatment A and 5 under treatment B, the
randomization process gives every possible group of 5 subjects selected from a set of 10 an
equal opportunity of being assigned to treatment A and treatment B. One-way analysis of
variance (or one-way ANOVA)* is used to analyze such a design.
5. Randomized block design (R.B. design) is an improvement over the C.R. design. In the
R.B. design the principle of local control can be applied along with the other two principles
of experimental designs. In the R.B. design, subjects are first divided into groups, known as
blocks, such that within each group the subjects are relatively homogeneous in respect to
some selected variable. The variable selected for grouping the subjects is one that is
believed to be related to the measures to be obtained in respect of the dependent variable.
The number of subjects in a given block would be equal to the number of treatments and
one subject in each block would be randomly assigned to each treatment. In general, blocks
are the levels at which we hold the extraneous factor fixed, so that its contribution to the
total variability of data can be measured. The main feature of the R.B. design is that in this
each treatment appears the same number of times in each block. The R.B. design is
analyzed by the two-way analysis of variance (two-way ANOVA)* technique.
Let us illustrate the R.B. design with the help of an example. Suppose four different forms of
a standardised test in statistics were given to each of five students, (selected one from each
of the fiveI.Q. blocks) and following are the scores that they obtained.
If each student separately randomized the order in which he or she took the four tests (by
using random numbers or some similar device), we refer to the design of this experiment
as a R.B. design. The purpose of this randomization is to take care of such possible
extraneous factors (say as fatigue) or perhaps the experience gained from repeatedly
taking the test.
6. Latin square design (L.S. design) is an experimental design very frequently used in
agricultural research. The conditions under which agricultural investigations are carried
out are different from those in other studies for nature plays an important role in
agriculture. For instance, an experiment has to be made through which the effects of five
different varieties of fertilizers on the yield of a certain crop, say wheat, it to be judged. In
such a case the varying fertility of the soil in different blocks in which the experiment has to
be performed must be taken into consideration; otherwise the results obtained may not be
very dependable because the output happens to be the effect not only of fertilizers, but also
it may also be the effect of fertility of soil. Similarly, there may be impact of varying seeds
on the yield. To overcome such difficulties, the L.S. design is used when there are two major
extraneous factors such as the varying soil fertility and varying seeds. The Latin-square
design is one wherein each fertilizer, in our example, appears five times but is used only
once in each row and in each column of the design. In other words, the treatments in a L.S.
design are so allocated among the plots that no treatment occurs more than once in any
one row or any one column. The two blocking factors may be represented through rows
and columns (one through rows and the other through columns). The following is a
diagrammatic form of such a design in respect of, say, five types of fertilizers, viz., A, B, C, D
and E and the two blocking factor viz., the varying soil fertility and the varying seeds:
The above diagram clearly shows that in a L.S. design the field is divided into as many
blocks as there are varieties of fertilizers and then each block is again divided into as many
parts as there are varieties of fertilizers in such a way that each of the fertilizer variety is
used in each of the block (whether column-wise or row-wise) only once. The analysis of the
L.S. design is very similar to the two-way ANOVA technique.
4.C ERRORS IN RESEARCH DESIGN
Types of errors in research design can be classified as: -
1. Population Specification Error: I t is defined as the “non-correspondence of the
required population to thepopulation selected by the investigator”. It occurs when
aresearcher selects an inappropriatepopulation fromwhich to obtain data. For
example, many times packagegoods manufacturers conductsurveys amongst
housewivesbecause they are easy tocontact and because it is assumedthat as they are
theend users they make the purchasedecisions. This assumption may not be always
validsince husbands and children may significantly influence thebuying decisions.
2. Sampling Error: It is defined as the “non-correspondence of sample selected by
probabilitymeans and the representativesample selected by the researcher”. It
occurswhen a probability samplingmethod is used to select asample and this sample is
notrepresentative of the population concerned. For example, a random sample of 500
people composed only of peoplebetween 35-50 years of age may not be representative
ofadult population. Samplingerror is affected by the homogeneity of the population
under study. In general – morehomogenous is the population;the smaller the sampling
error. Sampling error falls tozero in case of a census.
3. Selection Error: It is defined as the “Non-correspondence of sample selected by
nonprobability means and therepresentative sample soughtby the researcher.” In other
words – it is a sampling errorfor the sample selected bynon-probability [Link]
is a natural tendencyfor the investigator to selectthose respondents who aremost
accessible and [Link] samples are oftencomprised of friends and
associateswho more or lessrepresent the desired population. Samples of this type may
not be representative ofthe population but are certainlynot selected randomly –
leading to statistical problemsin inference.
4. Frame Error: It is defined asthe non-correspondence of the sought sample with the
required sample. A sampling frame is a means of accounting for all the elements of the
population. It is usually a listing of all the elements thatidentify a population. A
perfectframe identifies eachpopulation only once and doesnot include elements of
other population, which may lead tooverlap. For example, a sampling frame that
specifies the population as all adults usingoral care products – may wellleave out
people who prefer using neem and babool sticks, homemade toothpaste and powders –
leading to a frameerror in defining the population.
5. Non Response Error: A nonresponseerror occurs, whenthe obtained sample
differsfrom the original selectedsample. Non response can occurin two ways – (a) Non-
Contact i.e. the inability tocontact all the members ofthe sample and (b) Refusali.e. the
non- response of someor all the items of the [Link]-contact
errors arise dueto the inability to reach therespondent. This may be becausethe
respondent is NAH (Not at Home) on the initial call (or call backups) or mayhave
moved away from thearea either permanently or forthe period of the survey. Non-
Contact errors can be reducedby careful analysis of the [Link] arises
when the respondentdoes not respond toa particular item or to multiple items of the
[Link] Household Income,Religion, Sex and Politics are topics that may
elicititem refusal – normally categorized as refused. Don’tKnow / Can’t Say (DKCS)
refusalsarise when the respondentis aware of the item butis unable to provide an
adequateanswer to the [Link] of time on thepart of the respondent, a bad
experience with some previous interviewer, ill health [Link] be other reason for
[Link] rates could bebrought down to manageablelevels by giving training to
the interviewers and continuously monitoring the investigation process.
6. Surrogate Information Error: This is defined as the non-correspondence of the
information being sought by the researcher and that is required to solve the problem
or in other words, information is obtained from substitutes rather than original
sample. The necessity to accept surrogateinformation arisesfrom either the inability or
theunwillingness of the respondentto provide the neededinformation. Decisional
oriented behavioral research is always concentrated with prediction of behavior
usually non-verbal. This limits most marketing researchprojects to use
proxyinformation – data from pastbehaviour. Attitudes, beliefsand SEC classification
are allexamples of surrogate information because based onthese information we try to
predict the future behaviour of the respondents. Secondary sources of data are another
source of surrogate information. Surrogate information error can be minimized by
ensuring that the information used is highly correlatedwith the actual
informationobtained.
7. Measurement Error: Thismay be defined as the non-correspondence of information
obtained by measurementprocess and the information sought by the researcher. It is
generated by the measurement process itself and represents the difference between
informationgenerated and informationwanted by the [Link] errors can
potentiallyarise at any stage of themeasurement process – fromthe development of the
instrument t ill the analysis [Link] error can also occur at transmittal stage -
when theinterviewer is questioning the respondent. Faulty wording of question, non-
preparation ofnon-verbal clues, behaviour of the interviewer etc may all contribute to
how the respondent interprets the quest [Link] the response phase – whenthe
respondent is replying –error may occur because the respondent gave a wrong answer
or the correct answer was wrongly interpreted and recorded. In the analysisphase,
errors of incorrectediting, coding and/or descriptive summarization and inferences
can contributesubstantially to measurement error.
8. Experimental Error: It can be defined as the non-correspondence of the “true impact
of” and the “impact attributed to” the independentvariable. When an experimentis
conducted, the researcherattempts to measure the impactof one or more
manipulatedindependent variable onsome dependent variable –while controlling the
impact ofexogenous variable. Unfortunatelycontrol over all the exogenousvariable is
not alwayspossible – which maylead to an inclusion of bias inthe experiments. For
examplea study – trying to find out reasons for cancer may conclude that as all the
patients under observation used to eatbread therefore eating breadis the cause of
cancer.
