Research Design

Exploratory Research Design

• Exploratory Means to Explore the hidden things, which are not clearly
visible. Exploratory research is a type of Research conducted for a problem
that has not been clearly defined. Exploratory Research Studies are also
termed as formulate Research studies.
• Exploratory Research provides insights into and comprehension of an issue
or situation. It draws definitive conclusions only with extreme caution.
Exploratory research is a type of research conducted because a problem
has not been clearly defined.
• Exploratory research helps determine the best research design, data
collection method and selection of subjects. Given its fundamental nature,
Exploratory Research often concludes that a perceived problem does not
actually exist.
• Exploratory research often relies on secondary research such as reviewing
available literature an/or Data , or qualitative approaches such as informal
discussions with consumers, employees, management or competitors and
more formal approaches through in – depth interviews, focus groups,
projective Methods, case studies or pilot studies.
 Conclusive Research Design
• Conclusive Research Design is typically more formal and structured
than exploratory research.
• It is based on large representative samples, and the data obtained are
subjected to quantitative analysis.
• Conclusive Research is designed to assist (he decision maker in
determining, evaluating and selecting the best course of action to take
in a given situation.
• Conclusive research designs may be either descriptive or causal and
descriptive designs may be either cross-sectional or longitudinal.
• The techniques used in conclusive research contrast with exploratory
research as they are typically more formal and structured. Most
conclusive research techniques are based on large representative
samples and data obtained through is subjected to quantitative
analysis.
 Causal Research Design
• One of the common problem of the descriptive design is it do not
provide direct cause and effect relationships. On the other hand,
managers continually make decisions based on assumed causal
relationships.
• As these assumptions are based on intuitions, they are hardly
justifiable and validity of such causation should be examined with
causal research.
• For example, one of the common causation related judgements
relates to pricing decisions. Managers are constantly facing the
challenge of setting the right price and knowing the impact of price
increase or decrease on sales, brand image or other such variables is
utmost important for them.
• Causal design provides answer to such questions by explaining which
variables are the cause (independent variables) and which are the
effect (dependent variables).
 Descriptive Research Design
• Descriptive research design is typically concerned with determining
the frequency with which an event occurs or the relationship
between two variables.
• This type of design is typically guided by an initial relationship
between two variables.
• For example, an investigation of the trends to understand the
consumption of cola drinks in relation to respondents’ age, income,
occupation etc. would be a descriptive study.
• Descriptive research design is a scientific method which involves
observing and describing the behavior of a subject without
influencing it in any way.
Comparison of Research Design
 Cross-sectional Design
• The cross-sectional design is the most common and most familiar way
of conducting marketing research. It involves collection of information
from any given sample of population elements only once.
• In simple terms, cross-section studies are just conducted once.
• For example, the manager of a cola company wants to know the
preference of teenagers regarding their cola brand. This kind of study
provides a snapshot of the variables of interest at that point in time,
as contrasted to the longitudinal study that provides a series of
pictures, which, when pieced together, provide a movie of the
situation and the changes that are occurring.
• The objective of cross-sectional design many times is to establish
categories such that classification in one category implies
classification in one or more other categories.
 Single Cross-Sectional Design

• Only one sample of respondents is drawn from the target population.

• Information is obtained from this sample once.
• Sample survey research designs
 Multiple cross sectional designs
• Two or more samples of respondents
• Information from each sample is obtained only once.
• Information from different samples is obtained at different times over
long intervals.
• Comparison at the aggregate level but not at the individual
respondent level.
• Cohort Analysis: It consists of a series of surveys conducted at
appropriate time intervals.
• A cohort is a group of respondents who experience the same event
within the same time interval.
 Longitudinal Design
• A longitudinal design is much more reliable than a cross-sectional
design for monitoring changes over time, because it relies less on
consumers’ mental capabilities and more frequently monitors events
as close to their time of occurrence as feasible.
• The primary objective of longitudinal design is to monitor change
over a period of time.
• It involves a fixed sample of population elements that is measured
repeatedly.
• The sample remains the same over a period of time, thus providing a
series of pictures which, when viewed together, portray a detailed
illustration of the situation and changes that are taking place over a
period of time.
 Measurement & Scaling
• The data consists of quantitative variables, like price, income, sales
etc., and qualitative variables like knowledge, performance , character
etc.
• The qualitative information must be converted into numerical form
for further analysis.
• This is possible through measurement and scaling techniques.
• A common feature of survey based research is to have respondent’s
feelings, attitudes, opinions, etc. in some measurable form.
• Measurement is the process of observing and recording the
observations that are collected as part of research.
• Scaling is the assignment of objects to numbers or semantics
according to a rule. In scaling, the objects are text statements, usually
statements of attitude, opinion, or feeling.
 Measurement Scales
• Typically, there are four levels of measurement scales or methods of
assigning numbers:
• (a) Nominal scale,
• (b) Ordinal scale,
• (c) Interval scale, and
• (d) Ratio scale.
 Nominal Scale
• Nominal Scale is the crudest among all measurement scales but it is also
the simplest scale. In this scale the different scores on a measurement
simply indicate different categories.
• The nominal scale does not express any values or relationships between
variables. The nominal scale is often referred to as a categorical scale. The
assigned numbers have no arithmetic properties and act only as labels.
• The only statistical operation that can be performed on nominal scales is a
frequency count. We cannot determine an average except mode.
• For example: labeling men as ‘1’ and women as ‘2’ which is the most
common way of labeling gender for data recording purpose does not mean
women are ‘twice something or other’ than men. Nor it suggests that men
are somehow ‘better’ than women.
 Ordinal Scale
• Ordinal Scale involves the ranking of items along the continuum of
the characteristic being scaled. In this scale, the items are classified
according to whether they have more or less of a characteristic.
• The main characteristic of the ordinal scale is that the categories have
a logical or ordered relationship. This type of scale permits the
measurement of degrees of difference, (i.e. ‘more’ or ‘less’) but not
the specific amount of differences (i.e. how much ‘more’ or ‘less’).
• This scale is very common in marketing, satisfaction and attitudinal
research. Using ordinal scale data, we can perform statistical analysis
like Median and Mode, but not the Mean.
• For example, a fast food home delivery shop may wish to ask its
customers: How would you rate the service of our staff?
• (1) Excellent • (2) Very Good • (3) Good • (4) Poor • (5) Worst •
 Interval Scale
• Interval Scale is a scale in which the numbers are used to rank attributes
such that numerically equal distances on the scale represent equal distance
in the characteristic being measured.
• An interval scale contains all the information of an ordinal scale, but it also
one allows to compare the difference/distance between attributes. Interval
scales may be either in numeric or semantic formats.
• The interval scales allow the calculation of averages like Mean, Median and
Mode and dispersion like Range and Standard Deviation. For example, the
difference between ‘1’ and ‘2’ is equal to the difference between ‘3’ and
‘4’.
• Further, the difference between ‘2’ and ‘4’ is twice the difference between
‘1’ and ‘2’. Measuring temperature is an example of interval scale.
 Ratio Scale
• Ratio Scale is the highest level of measurement scales. This has the
properties of an interval scale together with a fixed (absolute) zero
point.
• The absolute zero point allows us to construct a meaningful ratio.
Ratio scales permit the researcher to compare both differences in
scores and relative magnitude of scores.
• Examples of ratio scales include weights, lengths and times. For
example, the number of customers of a bank’s ATM in the last three
months is a ratio scale. This is because you can compare this with
previous three months.
• For example, the difference between 10 and 15 minutes is the same
as the difference between 25 and 30 minutes and 30 minutes is twice
as long as 15 minutes
Types of Scaling Techniques
Comparative Scale
Paired Comparison Scale
 Rank Order Scale
• This is another type of comparative scaling technique in which
respondents are presented with several items simultaneously and
asked to rank them in the order of priority.
• This is an ordinal scale that describes the favored and unfavored
objects, but does not reveal the distance between the objects. The
resultant data in rank order is ordinal data.
• This yields better results when direct comparison are required
between the given objects. The major disadvantage of this technique
is that only ordinal data can be generated.
 Constant Sum Scale
• In this scale, the respondents are asked to allocate a constant sum of
units such as points, rupees, or chips among a set of stimulus objects
with respect to some criterion.
• For example, you may wish to determine how important the
attributes of price, fragrance, packaging, cleaning power, and lather of
a detergent are to consumers.
• Respondents might be asked to divide a constant sum to indicate the
relative importance of the attributes. The advantage of this technique
is saving time.
• However, main disadvantages are the respondents may allocate more
or fewer points than those specified. The second problem is
respondents might be confused.
 Q-Sort Scale
• This is a comparative scale that uses a rank order procedure to sort
objects based on similarity with respect to some criterion.
• The important characteristic of this methodology is that it is more
important to make comparisons among different responses of a
respondent than the responses between different respondents.
• Therefore, it is a comparative method of scaling rather than an
absolute rating scale.
• In this method the respondent is given statements in a large number
for describing the characteristics of a product or a large number of
brands of a product.
 Non-comparative scaling

• In non-comparative scaling respondents need only evaluate a single

object.
• Their evaluation is independent of the other object which the
researcher is studying.
• The non-comparative scaling techniques can be further divided into:
• (a)Continuous Rating Scale, and
• (b)Itemized Rating Scale.
 Continuous Rating Scales
• It is very simple and highly useful. In continuous rating scale, the
respondent’s rate the objects by placing a mark at the appropriate
position on a continuous line that runs from one extreme of the
criterion variable to the other.
• Example : Question: How would you rate the TV advertisement as a
guide for buying?
 Itemized Rating Scales
• Itemized rating scale is a scale having numbers or brief descriptions
associated with each category.
• The categories are ordered in terms of scale position and the
respondents are required to select one of the limited number of
categories that best describes the product, brand, company, or
product attribute being rated.
• Itemized rating scales are widely used in marketing research. Itemised
rating scales is further divided into three parts, namely
• (a) Likert scale,
• (b) Semantic Differential Scale, and
• (c) Stapel Scale.
 Likert Scale
• Likert, is extremely popular for measuring attitudes, because, the method
is simple to administer.
• With the Likert scale, the respondents indicate their own attitudes by
checking how strongly they agree or disagree with carefully worded
statements that range from very positive to very negative towards the
attitudinal object.
• Respondents generally choose from five alternatives (say strongly agree,
agree, neither agree nor disagree, disagree, strongly disagree).
• A Likert scale may include a number of items or statements. Disadvantage
of Likert Scale is that it takes longer time to complete than other itemised
rating scales because respondents have to read each statement.
• Despite the above disadvantages, this scale has several advantages. It is
easy to construct, administer and use.
 Semantic Differential Scale
• This is a seven point rating scale with end points associated with
bipolar labels (such as good and bad, complex and simple) that have
semantic meaning.
• It can be used to find whether a respondent has a positive or negative
attitude towards an object. It has been widely used in comparing
brands, products and company images.
• It has also been used to develop advertising and promotion strategies
and in a new product development study.
 Staple Scale

• The Stapel scale was originally developed to measure the direction

and intensity of an attitude simultaneously.
• Modern versions of the Stapel scale place a single adjective as a
substitute for the Semantic differential when it is difficult to create
pairs of bipolar adjectives.
• The modified Stapel scale places a single adjective in the center of an
even number of numerical Values.
 Sampling Design
• Sampling is a process used in statistical analysis in which a
predetermined number of observations are taken from a larger
population. The methodology used to sample from a larger
population depends on the type of analysis being performed but may
include simple random sampling or systematic sampling.
• Sampling design is a mathematical function that gives you the
probability of any given sample being drawn.
• Since sampling is the foundation of nearly every research project, the
study of sampling design is a crucial part of statistics.
• It involves not only learning how to derive the probability functions
which describe a given sampling method but also understanding how
to design a best-fit sampling method for a real life situation.
 Sampling Design
• Population is the collection of the elements which has some or the
other characteristic in common. Number of elements in the
population is the size of the population.
• Sample is the subset of the population. The process of selecting a
sample is known as sampling. Number of elements in the sample is
the sample size.
 Probability and Non- Probability Sampling
• There are lot of sampling techniques which are grouped into two
categories as
• Probability Sampling
• Non- Probability Sampling
• The difference lies between the above two is whether the sample
selection is based on randomization or not. With randomization,
every element gets equal chance to be picked up and to be part of
sample for study.
 Probability Sampling
• This Sampling technique uses randomization to make sure that every
element of the population gets an equal chance to be part of the
selected sample. It’s alternatively known as random sampling.
• Simple Random Sampling: Every element has an equal chance of
getting selected to be the part sample. It is used when we don’t have
any kind of prior information about the target population.
• For example: Random selection of 20 students from class of 50
student. Each student has equal chance of getting selected. Here
probability of selection is 1/50
 Simple Random Sampling
• N = the number of cases in the sampling frame
• n = the number of cases in the sample
• NCn = the number of combinations (subsets) of n from N
• f = n/N = the sampling fraction
• For the sake of the example, let's say you want to select 100 clients to
survey and that there were 1000 clients over the past 12 months. Then, the
sampling fraction is f = n/N = 100/1000 = .10 or 10%. Now, to actually draw
the sample, you have several options. You could print off the list of 1000
clients, tear then into separate strips, put the strips in a hat, mix them up
real good, close your eyes and pull out the first 100.
 Stratified Sampling
• This technique divides the elements of the population into small
subgroups (strata) based on the similarity in such a way that the
elements within the group are homogeneous and heterogeneous
among the other subgroups formed. And then the elements are
randomly selected from each of these strata. We need to have prior
information about the population to create subgroups.
 Cluster Sampling
• Our entire population is divided into clusters or sections and then the
clusters are randomly selected. All the elements of the cluster are
used for sampling. Clusters are identified using details such as age,
gender, location etc. Cluster sampling can be done in following ways:
• Single Stage Cluster Sampling: Entire cluster is selected randomly for
sampling.
 Cluster Sampling
• Two Stage Cluster Sampling
• Here first we randomly select clusters and then from those selected
clusters we randomly select elements for sampling
 Systematic Sampling
• Here the selection of elements is systematic and not random except
the first element.
• Elements of a sample are chosen at regular intervals of population.
• All the elements are put together in a sequence first where each
element has the equal chance of being selected.
• For a sample of size n, we divide our population of size N into
subgroups of k elements.
• We select our first element randomly from the first subgroup of k
elements.
 Systematic Sampling
• To select other elements of sample, perform following:
• We know number of elements in each group is k i.e N/n. So if our first
element is n1 then. Second element is n1+k i.e n2. Third element
n2+k i.e n3 and so on. Taking an example of N=20, n=5. No of
elements in each of the subgroups is N/n i.e 20/5 =4= k. Now,
randomly select first element from the first subgroup. If we select n1=
3, n2 = n1+k = 3+4 = 7, n3 = n2+k = 7+4 = 11
 Multi-Stage Sampling
• Population is divided into multiple clusters and then these clusters are
further divided and grouped into various sub groups (strata) based on
similarity. One or more clusters can be randomly selected from each
stratum. This process continues until the cluster can’t be divided
anymore. For example country can be divided into states, cities, urban
and rural and all the areas with similar characteristics can be merged
together to form a strata.
 Multi-Stage Sampling
• Multistage sampling divides large populations into stages to make the
sampling process more practical. A combination of stratified sampling
or cluster sampling and simple random sampling is usually used.
• Let’s say you wanted to find out which subjects U.S. school children
preferred. A population list — a list of all U.S. schoolchildren– would
be near-impossible to come by, so you cannot take a sample of the
population.
• Instead, you divide the population into states and take a simple
random sample of states. For the next stage, you might take a simple
random sample of schools from within those states. Finally you could
perform simple random sampling on the students within the schools
to get your sample.
• In order to classify multistage sampling as probability sampling, each
stage must involve a probability sampling method.
 Non-Probability Sampling
• It does not rely on randomization. This technique is more reliant on
the researcher’s ability to select elements for a sample. Outcome of
sampling might be biased and makes difficult for all the elements of
population to be part of the sample equally. This type of sampling is
also known as non-random sampling.
• Convenience Sampling
• Purposive Sampling
• Quota Sampling
• Referral /Snowball Sampling
 Convenience Sampling
• Here the samples are selected based on the availability. This method
is used when the availability of sample is rare and also costly. So
based on the convenience samples are selected.
• For example: Researchers prefer this during the initial stages of
survey research, as it’s quick and easy to deliver results.
 Purposive Sampling
• This is based on the intention or the purpose of study. Only those
elements will be selected from the population which suits the best for
the purpose of our study.
• For Example: If we want to understand the thought process of the
people who are interested in pursuing master’s degree then the
selection criteria would be “Are you interested for Masters in..?”
• All the people who respond with a “No” will be excluded from our
sample.
 Judgmental Sampling
• Judgmental sampling, also called purposive sampling or authoritative
sampling, is a non-probability sampling technique in which the
sample members are chosen only on the basis of the researcher’s
knowledge and judgment. As the researcher’s knowledge is
instrumental in creating a sample in this sampling technique, there
are chances that the results obtained will be highly accurate with a
minimum margin of error.
• The process of selecting a sample using judgmental sampling involves
the researchers carefully picking and choosing each individual to be a
part of the sample. The researcher’s knowledge is primary in this
sampling process as the members of the sample are not randomly
chosen.
 Quota Sampling
• Quota sampling means to take a very tailored sample that’s in proportion to some
characteristic or trait of a population. For example, you could divide a population
by the state they live in, income or education level, or sex. The population is
divided into groups (also called strata) and samples are taken from each group to
meet a quota. Care is taken to maintain the correct proportions representative of
the population.
• For example, if your population consists of 45% female and 55% male, your
sample should reflect those percentages. Quota sampling is based on the
researcher’s judgment and is considered a non-probability sampling technique.
• The proportions for each quota must be accurate; this is sometimes difficult or
impossible to calculate. In addition, the researcher has the option to set a quota
higher or lower than the proportion seen in the population. For example, let’s say
the researcher is investigating views on the death penalty and wants to make
sure minorities are included in the survey.
• The population may consist of 3% Native Americans but the researched changes
the quota to 5% to ensure the views of Native Americans are included. The
inclusion of certain minorities has come at the expense of a truly representative
sample.
 Quota Sampling

• The general steps to follow are:

• Divide the population into subgroups. These should be exclusive. For
example, you might divide employees by type of educational degree.
• Figure out the proportion of subgroups to the population. For
example, employees who have a physical science degree might be 1
out of 4.
• Choose your sample size. For example, if you are sampling 10,000
people you might have a quota sample of 100.
• Choose participants, being careful to adhere to the subgroup:
population proportion. For this example, 25% of your sample should
have a physical science degree. The selection process continues until
your quotas are filled.
 Snowball Sampling
• This technique is used in the situations where the population is
completely unknown and rare.
• Therefore we will take the help from the first element which we select
for the population and ask him to recommend other elements who
will fit the description of the sample needed.
• So this referral technique goes on, increasing the size of population
like a snowball.
 Data Collection Methods
• Various methods of collecting data are employed by social scientists.
Here we will discuss the varied dimensions relevant to : data
generation and attempt to arrive at an abstract typology involving
stimuli, responses and setting for data collection. The task of data
collection begins after a research problem has been defined and
research design /plan chalked out.
• PRIMARY DATA : Are those which are collected a fresh and for the first
time and thus happen to be original in character and known as
Primary data.
• SECONDARY DATA : Are those which have been collected by someone
else and which have already been passed through the statistical
process are known as Secondary data.
 Methods of Data Collection
• Primary Data
• OBSERVATION METHOD : Observation method is a method under which
data from the field is collected with the help of observation by the
observer or by personally going to the field.
• In the words of P.V. Young, “Observation may be defined as systematic
viewing, coupled with consideration of seen phenomenon.”
ADVANTAGES:
• Subjective bias eliminated (No bias info)
• Researcher gets the current information
DISADVANTAGES :
• It is expensive method (time requires more)
• Limited information
• Unforeseen factors may interfere with observational task
• Respondents opinion can not be recorded on certain subject
 TYPES OF OBSERVATION
• Structured and Unstructured Observation
• When observation is done by characterizing style of recording the
observed information, standardized conditions of observation ,
definition of the units to be observed , selection of pertinent data of
observation then it is structured observation
• When observation is done without any thought before observation
then it is unstructured observation
 Participant & Non Participant Observation
• When the Observer is member of the group which he is observing
then it is Participant Observation
• In participant observation Researcher can record natural behavior of
group , Researcher can verify the truth of statements given by
informants in the context of questionnaire , Difficult to collect
information.
• Non Participant Observation
• When observer is observing people without giving any information to
them then it is non participant observation
 Controlled & Uncontrolled Observation

• When the observation takes place in natural condition i.e.

uncontrolled observation. It is done to get spontaneous picture of life
and persons

• When observation takes place according to definite pre arranged

plans , with experimental procedure then it is controlled observation
generally done in laboratory under controlled condition.
 INTERVIEW METHOD
• This method of collecting data involves presentation or oral-verbal stimuli
and reply in terms of oral-verbal responses.
• Interview Method is Oral-Verbal communication . Where interviewer asks
questions( which are aimed to get information required for study ) to
respondent.
• There are different type of interviews as follows :
• PERSONAL INTERVIEWS : The interviewer asks questions generally in a face
to face contact to the other person or persons.
• Information at greater depth
• Flexibility of restructuring the Questionnaire
• Interviewer by his skill can come over resistance
• Non Response generally low
• Samples can controlled more effectively
• Personal information can be obtained
 TELEPHONIC INTERVIEWS
• Contacting samples on telephone
• Uncommon method may be used in developed regions
• Flexible compare to mailing method
• Faster than other methods
• Cheaper than personal interview method
• Callbacks are simple and economical also
• High response than mailing method.
• When it is not possible to contact the respondent directly, then interview is
conducted through – Telephone.
• Replies can be recorded without embarrassment to respondents
• Interviewer can explain requirements more easily
• No field staff is required
• Wider distribution of sample is possible
 Types of Interviews
• Structured interviews : in this case, a set of pre- decided questions are there.
• unstructured interviews : in this case, we don’t follow a system of pre-determined
questions.
• focused interviews : attention is focused on the given experience of the
respondent and its possible effects.
• clinical interviews : concerned with broad underlying feelings or motivations or
with the course of individual’s life experience, rather than with the effects of the
specific experience, as in the case of focused interview.
• group interviews : a group of 6 to 8 individuals is interviewed.
• qualitative and quantitative interviews : divided on the basis of subject matter i.e.
whether qualitative or quantitative.
• individual interviews : interviewer meets a single person and interviews him.
• selection interviews : done for the selection of people for certain jobs.
• depth interviews : it deliberately aims to elicit unconscious as well as other types
of material relating especially to personality dynamics and motivations.
 Questionnaire Method
• This method of data collection is quite popular, particularly in case of
big enquiries.
• The questionnaire is mailed to respondents who are expected to read
and understand the questions and write down the reply in the space
meant for the purpose in the questionnaire itself.
• The respondents have to answer the questions on their own.
• Questionnaire is sent to persons with request to answer the
questions and return the questionnaire.
• Questions are printed in definite order , mailed to samples who are
expected to read that questions understand the questions and write
the answers in provided space .
 Essentials of Good Questionnaire
• Short & simple Questions should arranged in logical sequence (From
Easy to difficult one)
• Technical terms should be avoided
• Questions affecting the sentiments of the respondents should
avoided
• Adequate space for answers should be provided in questionnaire
• Provision for uncertainty (do not know, No preference)
• Directions regarding the filling of questionnaire should be given
Physical Appearance - - Quality of paper, color
 SCHEDULE METHOD
• It is one of the important methods for the study of social problems.
• Schedules Like Questionnaires but it filled by enumerator .
• Enumerators are specially appointed for filling questionnaire
• Enumerators explain the aim and objective to respondent and fill the
answers in provided space .
• In the words of Thomas Carson Macormic, “The schedule is nothing
more than a list of questions which it seems necessary to test the
hypothesis .”
 Other Methods Of Data Collection
• Warranty Cards: Post card size cards sent to customers and feedback
collected through asking questions on that card
• Distributor or Store Audits: Audits are done by distributor or
manufacturer’s salesperson. Observation or copying information
about inventory in retail shops. Useful method for knowing market
share ,market size , effect of in store promotion.
• Pantry Audits: From the observation of pantry of customer to know
purchase habit of the people (which product , of what brand etc.)
Questions may be asked at the time of audit
• Consumer Panels: When pantry audit is done at regular basis, Daily
record of consumption of certain customers Or repeatedly
interviewed at the specific periods to know their consumption.
 Other Methods Of Data Collection
• Use of Mechanical Device: Eye Cameras to record eyes focus on
certain sketch. Psycho galvanometer to measure body excitement to
visual stimulus. Motion Picture camera to record movement of body
at the time of purchase. Audiometer concerned to TV. Useful to know
Channel, program preference of people
• Depth Interview: To discover the underlying motives or desires of
samples . To explore needs , feelings of respondents. Skill is required ,
indirect question or projective techniques are used to know behavior
of the respondent.
• Content Analysis: analyzing contents of documentary material as
news paper , books , magazines about certain characteristics to
identify and count
 Other Methods Of Data Collection
• CASE STUDY METHOD: It is essentially an intensive investigation of
the particular unit under consideration. Its important characteristics
are as follows :
• a) the researcher can take one single social unit or more of such units
for his study purpose. b) the selected unit is studied intensively i.e. it
is studied in minute details.
• SURVEY METHOD: One of the common methods of diagnosing and
solving of social problems is that of undertaking surveys.
• Festinger and Kat of the opinion that, “Many research problems
require systematic collection of data from population through the use
of personal interviews or other data gathering devices”.
 PANEL METHOD

• PANEL METHOD:
• In this method, data is collected from the same sample respondents
at the some interval either by mail or by personal interview. This is
used for studies on :
• 1) Expenditure Pattern
• 2) Consumer Behaviour
• 3) Effectiveness of Advertising
• 4) Voting Behaviour and so on
 Secondary Data
Sources of data:
• Publications of Central, state , local government
• Technical and trade journals
• Books, Magazines, Newspaper
• Reports & publications of industry ,bank, stock exchange
• Reports by research scholars, Universities, economist
• Public Records
Factors to be considered before using secondary data
Reliability of data – Who, when , which methods, at what time etc.
Suitability of data – Object ,scope, and nature of original inquiry should be
studied, as if the study was with different objective then that data is not
suitable for current study
Adequacy of data– Level of accuracy
Area differences then data is not adequate for study
 Reliability Test of Instrument
• Reliability is defined as the extent to which an
instrument consistently measures what it is supposed to. A child's
thermometer would be very reliable as a measurement tool while a
personality test would have less reliability.
• Reliability testing provides information about the interrelationships of
items in the scale
• A test is reliable to the extent that whatever it measures, it measures
it consistently. If I were to stand on a scale and the scale read 15
pounds, I might wonder. Suppose I were to step off the scale and
stand on it again, and again it read 15 pounds. The scale is producing
consistent results.
• From a research point of view, the scale seems to be reliable because
whatever it is measuring, it is measuring it consistently. Whether
those consistent results are valid is another question. However, an
instrument cannot be valid if it is not reliable.
 Types of Reliability
• Test-Retest Reliability is the correlation between two successive
measurements with the same test. For example, you can test in the
morning to your pilot sample and then again in the afternoon. The
two sets of data should be highly correlated if the test is reliable. The
pilot sample should theoretically answer the same way if nothing has
changed.
• Test-retest measures the correlation between scores from one
administration of an instrument to another, usually within an interval
of 2 to 3 weeks. Unlike pre-post tests, no treatment occurs between
the first and second administrations of the instrument, in order to
test-retest reliability.
• A similar type of reliability called alternate forms, involves using
slightly different forms or versions of an instrument to see if different
versions yield consistent results.
 Test-Retest Reliability
• Different time frames are used to measure the consistency of items of the
same sample through the same questionnaire.
• The same instrument is given twice to the same group of people. The
reliability is the correlation between the scores on the two instruments. If
the results are consistent over time, the scores should be similar.
• The trick with test-retest reliability is determining how long to wait
between the two administrations. One should wait long enough so the
subjects don’t remember how they responded the first time they
completed the instrument, but not so long that their knowledge of the
material being measured has changed. This may be a couple weeks to a
couple months.
• If one were investigating the reliability of a test measuring mathematics
skills, it would not be wise to wait two months. The subjects probably
would have gained additional mathematics skills during the two months
and thus would have scored differently the second time they completed
the test.
• We would not want their knowledge to have changed between the first
and second testing.
 Inter-observer Reliability
• Different observers are assigned to assess the consistency of the
items of the sample through the same questionnaire
• Researchers try to determine whether two observers are consistent in
their observed estimate for the same sample
• The correlation between ratings of the two observers would provide
the actual estimate of the reliability
• This method is used in pilot study
• For long time survey it should be executed time to time.
 Equivalent-Form

• Two different versions of the instrument are created. We assume

both measure the same thing. The same subjects complete both
instruments during the same time period. The scores on the two
instruments are correlated to calculate the consistency between the
two forms of the instrument.
• Equivalent Forms Reliability is the successive administration of two
parallel forms of the same test. A good example is the SAT. There are
two versions that measure Verbal and Math skills.
• Reliability is measured by evaluating the correlation coefficient
between the two equivalent forms at two different times
 Parallel Forms

• Different survey instrument forms under the same domain at the

same time frame are used to assess the consistency of items
• Two parallel questionnaire forms are created by the researcher from a
large set of question banks that focus on the same construct.
• Reliability is calculated by measuring correlation between the two
parallel survey instrument forms.
 Internal Consistency
• An informal way to test for internal consistency is just to compare the
answers to see if they all agree with each other. In real life, you will likely to
get a wide variety of answers, making it difficult to see if internal
consistency is good or not. A wide variety of statistical tests are available
for internal consistency; one of the most widely used is Cronbach’s Alpha.
• Average inter-item correlation finds the average of all correlations between
pairs of questions.
• Split Half Reliability: all items that measure the same thing are randomly
split into two. The two halves of the test are given to a group of people and
find the correlation between the two. The split-half reliability is the
correlation between the two sets of scores.
• Kuder-Richardson 20: the higher the Kuder-Richardson score (from 0 to 1),
the stronger the relationship between test items. A Score of at least .70 is
considered good reliability.
 Internal Consistency
• Internal consistency reliability looks at the consistency of the score of
individual items on an instrument, with the scores of a set of items, or
subscale, which typically consists of several items to measure a single
construct.
• Cronbach’s alpha is one of the most common methods for checking
internal consistency reliability. Group variability, score reliability, number of
items, sample sizes, and difficulty level of the instrument also can impact
the Cronbach’s alpha value.
• When the items on an instrument are not scored right versus wrong,
Cronbach’s alpha is often used to measure the internal consistency. This is
often the case with attitude instruments that use the Likert scale.
• A computer program such as SPSS is often used to calculate Cronbach’s
alpha. Although Cronbach’s alpha is usually used for scores which fall along
a continuum, it will produce the same results as KR-20 with dichotomous
data (0 or 1).
Cronbach’s Alpha
 Cronbach’s Alpha
• Cronbach’s alpha, α (or coefficient alpha), developed by Lee Cronbach
in 1951, measures reliability, or internal consistency. “Reliability” is
how well a test measures what it should.
• For example, a company might give a job satisfaction survey to their
employees. High reliability means it measures job satisfaction, while
low reliability means it measures something else (or possibly nothing
at all).
• Cronbach’s alpha tests to see if multiple-question Likert scale surveys
are reliable. These questions measure latent variables — hidden or
unobservable variables like: a person’s carefulness, reservation or
openness.
• These are very difficult to measure in real life. Cronbach’s alpha will
tell you if the test you have designed is accurately measuring the
variable of interest.
Cronbach’s Alpha
 Split Half Reliability
• A total score for the odd number questions is correlated with a total
score for the even number questions (although it might be the first
half with the second half). This is often used with dichotomous
variables that are scored 0 for incorrect and 1 for correct.
• Split Half Reliability is when, for example, you have the SAT Math test
and divide the items on it in two parts. If you correlated the first half
of the items with the second half of the items, they should be highly
correlated if they are reliable.
• Split-half testing is a measure of internal consistency — how well the
test components contribute to the construct that’s being measured. It
is most commonly used for multiple choice tests you can theoretically
use it for any type of test—even tests with essay questions.
 Validity
• Validity is the extent to which the scores from a measure represent
the variable they are intended to. But how do researchers make this
judgment? We have already considered one factor that they take into
account—reliability.
• Research validity in surveys relates to the extent at which the survey
measures right elements that need to be measured. In simple terms,
validity refers to how well an instrument as measures what it is
intended to measure.
• Reliability alone is not enough, measures need to be reliable, as well
as, valid. For example, if a weight measuring scale is wrong by 4kg (it
deducts 4 kg of the actual weight), it can be specified as reliable,
because the scale displays the same weight every time we measure a
specific item. However, the scale is not valid because it does not
display the actual weight of the item.
 Face validity
• Face validity, also called logical validity, is a simple form of validity where
you apply a superficial and subjective assessment of whether or not your
study or test measures what it is supposed to measure. You can think of it
as being similar to “face value”, where you just skim the surface in order to
form an opinion.
• It is the easiest form of validity to apply to research. However, it doesn’t
include much (if any at all) in the way of objective measurements.
Therefore, it is often criticized as the weakest form of validity.
• For example, let’s say a researcher’s work indicated that drinking milk
caused cancer. A peer review of the paper by a distinguished biochemist
revealed several shortcomings in the design of the experiment. The
biochemist rejected the paper on face validity, but they were well qualified
to do so. In essence, face validity is weaker for a layperson, and stronger for
an expert in the field.
 Content Validity (Logical or Rational Validity)
• When you create a test or questionnaire for a particular subject, you want
the questions to actually measure what you want them to.
• For example, the Physics exam should cover all topics actually taught to
students and not unrelated material like English or biology.
• This matching between test questions and the content the questions are
supposed to measure is called content validity. If some of the test
questions are measuring something else, this can create bias.
• More formally, that “something” you are trying to measure is called
a construct. A construct can be (almost) anything. Simple constructs
include height, weight and IQ.
• More complicated constructs include: ability to perform well at a certain
job; competency with wide-ranging subject areas like physics or U.S.
history, and ability to evaluate other people’s psychiatric condition.
 Criterion Validity
• Criterion validity (or criterion-related validity) measures how well one
measure predicts an outcome for another measure. A test has this
type of validity if it is useful for predicting performance or behavior in
another situation (past, present, or future). For example:
• A job applicant takes a performance test during the interview process.
If this test accurately predicts how well the employee will perform on
the job, the test is said to have criterion validity.
• A graduate student takes the GRE. The GRE has been shown as an
effective tool (i.e. it has criterion validity) for predicting how well a
student will perform in graduate studies.
• The first measure (in the above examples, the job performance test
and the GRE) is sometimes called the predictor variable or the
estimator. The second measure is called the criterion variable as long
as the measure is known to be a valid tool for predicting outcomes.
 Construct Validity
• When you’re talking about a construct in relation to testing and construct
validity, it has nothing to do with the way a test is designed or constructed.
A construct is something that happens in the brain, like a skill, level of
emotion, ability or proficiency. For example, proficiency in any language is
a construct.
• Construct validity is one way to test the validity of a test; it’s used in
education, the social sciences, and psychology. It demonstrates that the
test is actually measuring the construct it claims it’s measuring. For
example, you might try to find out if an educational program increases
emotional maturity in elementary school age children. Construct validity
would measure if your research is actually measuring emotional maturity.
• It isn’t that easy to measure construct validity–several measures are usually
required to demonstrate it, including pilot studies and clinical trials. One of
the reasons it’s so hard to measure is one of the very reasons it exists: in
the social sciences, there’s a lot of subjectivity and most constructs have no
real unit of measurement. Even those constructs that do have an
acceptable measurement scale (like IQ) are open to debate.
Convergent Validity and Discriminant Validity
• Convergent Validity is a sub-type of construct validity. Construct validity
means that a test designed to measure a particular construct (i.e.
intelligence) is actually measuring that construct. Convergent validity takes
two measures that are supposed to be measuring the same construct and
shows that they are related.
• Conversely, discriminant validity shows that two measures that are not
supposed to be related are in fact, unrelated. Both types of validity are a
requirement for excellent construct validity.
• Let’s say you were researching depression in college students. In order to
measure depression (the construct), you use two measurements: a survey
and participant observation. If the scores from your two measurements are
close enough (i.e. they converge), this demonstrates that they are
measuring the same construct. If they don’t converge, this could indicate
they are measuring different constructs (for example, anger and depression
or self-worth and depression).
 Convergent Validity, Discriminant Validity and
Correlation
• Defining constructs can be a challenge. Therefore, applying
convergent validity and discriminant validity can also be a challenge.
Convergent validity is usually accomplished by demonstrating a
correlation between the two measures, although it’s rare that any
two measures will be perfectly convergent. In the case of discriminant
validity, you could show that there is no correlation at all.
• Correlation is measured by a correlation coefficient, r, on a scale of -1
to 1, where r=-1 is perfect negative correlation, r=1 is perfect positive
correlation, and r=0 is no correlation at all.
• Convergent validity is sometimes claimed if the correlation coefficient
is above .50, although it’s usually recommended at above .70.
 Nomological Validity
• Nomological Validity is a statistical term that refers to a "nonlogical"
necessity or a law of nature.
• It is a form of construct validity that requires a comparison of at least
two constructs and that those constructs have a possible linkage.
• For example, a comparison of human aging with memory loss. Both of
these events occur, and appear to have a correlation without being
directly related to one another.
• It is the extent to which the scale correlates in theoretically predicted
ways with measures of different but related constructs.