UNIT III – SAMPLING METHODS

CONCEPT OF SAMPLING
 Sampling may be defined as the selection of some part of an aggregate or
totality on the basis of which a judgment or inference about the aggregate or
totality is made.
 It is the process of obtaining information about the entire population by
examining only a part of it.
 Sampling is the process of selecting units from a population of interest so
that by studying the sample we may fairly generalize our results back to the
population from which they were chosen
 Sample is the portion of the population which is examined with the view to
estimate the characteristics of the population

REASONS FOR SAMPLING

 The sample can save time
 The sample can save money. Sampling is cheaper than the census survey and
it is obviously more economical
 If assessing the population is impossible, sample is the only option
 Since magnitude of operations involved in a sample survey is small, both the
execution of the fieldwork and the analysis of the results can be carried out
speedily
 A sample survey enables the researcher to collect more detailed information
than would otherwise be possible in a census survey. Also, information of a
more specialized type would be collected
 In sampling, relatively small no. of staff is requires to carry out the survey
 Since the scale of operations involved in a sample survey is small, the
quality of the interviewing, supervision and other related activities can be
better than the quality in the census survey

LIMITATIONS OF SAMPLING
 Misleading Conclusions - the sampling procedures must be correctly
designed and followed otherwise what we call as 'wild sample would crop
 up with misleading results. The sampling error may be larger than expected
if the sampling procedure is improperly designed or incorrectly carried out
 Need for specialized knowledge - Most of the sampling techniques require
the services of sampling experts or statisticians. In social research one needs
to have adequate experience of dealing with and with collecting social data
accurately
 Problematic for Social Sciences - Social scientists are faced with additional
problems in Sampling because of scattered distribution of sample units, non
cooperative nature of respondents, in accessibility to respondents and so on
 Limited scope to know certain population characteristics like population
growth rate, population density etc, census of population at regular intervals
is more appropriate than studying by sampling
 Changeability of units - If the units to be measured are rare and highly
variable a very large sample is required in order to yield enough cases for
achieving statistically reliable information

Essentials of Sampling
Usefulness and reliability of sampling depends on the following features of
sample:

1. Representativeness : The sample selected should fully represent the population

from which it is drawn. This means, all the characteristics or features of the
population should be reflected by the sample. If not, sample conclusions will not
be fully applicable to population. Suppose by talking to five boys in a college of
2000 boys, one cannot come to any conclusion about the college.

2. Adequacy: The size of the sample should be large enough so as to provide

accurate results. Though it is difficult to state what is the ideal size of sample,
Statistically it can be determined. In research, such an approach is used to
determine the sample size so that the results obtained will be accurate and
applicable to population.

3. Randomness : Samples should be selected at random. That is, there should be no

bias in the selection of sample elements and each item in the population should
have equal chance of being selected. Only when the sample is selected at random,
its reliability and representativeness would be achieved.
4. Homogeneity: Any number of samples could be drawn from a population. But
all these samples should have similarity in every respect. That is, suppose a
researcher selects 200 students from a College out of 2000 students in day section,
the sample elements [i.e., students selected] should be from the day section of the
College alone. No student from evening section should be included in the sample.
Similarly, suppose a researcher selects 5000 people from Chennai city as a sample
to study Consumption behavior of the people, then the sample elements should all
be people living in Chennai city. It should not include people who have come to
Chennai city as tourists

SAMPLING TECHNIQUES
 There are different type of sample designs based on two factors (i.e.)
representation basis and the elements selection technique
 On the representation basis, sampling may be probability sampling or non-
probability sampling
 Probability Sampling - It is also known as 'random sampling' or
'choice sampling'. Under this sampling design, every item in the
universe have an equal or known chance of inclusion in the sample
(e.g.) lottery method in which individuals are picked up not
deliberately but by some mechanical process
 Non- probability Sampling - It is also known as 'deliberate sampling'
or 'purposive sampling. In this type, items for the samples are selected
deliberately by the researcher. His choice concerning the items remain
supreme
 On clement selection basis, the sampling may be either unrestricted or
restricted
 Unrestricted sampling - When each sample element is drawn
individually from the population at large, then the sample so drawn is
known as unrestricted sample
 Restricted sampling - remaining all other forms of sampling are
covered under the term restricted sampling

PROBABILITY SAMPLING
 A SIMPLE RANDOM SAMPLING(UNRESTRICTED)
 In the unrestricted probability sampling design, more commonly
known as simple random sampling every element in the population
has a known and equal chance of being selected as a subject
 If there are 1000 elements in the population and if we need a sample
of 100 pieces of paper were dropped in the hat bearing the names of
all the elements and the 100 samples were selected with eyes closed.
The first piece drawn will have/1000 chance of being drawn and the
second piece will have 1/999 chance of being drawn and so on.
  In the current scenario computers are used to generate random
numbers and one does not need to go through the tedious process of
picking out numbers
 Types of simple random sampling are lottery method and table of
random numbers

Simple or Unrestricted Random Sampling is of the following types :

i) Lottery method : In this method all the items in the population are given
numbers and these are written on chits of uniform size. Then these chits are placed
in a bowl or a bag and the required numbers of chits are selected. Even here, when
the chit selected first is replaced before picking the next one, it is called lottery
method with replacement. Suppose the chit selected in the first pick is not selected
and then the second pick is made, we call it as lottery method without replacement.
Of these two the first one is preferred as the probability of the second and the
subsequent chit selected will remain the same. In the second method the
probability of selecting the second or third and subsequent chits will be different,
as there is no replacement of chits already picked

ii) Table of random numbers: In this method, first the size of sample is
determined. Then using random number table, the required number of items is
selected to form the sample. Different Random number tables are available. In
these tables, random numbers are printed in columns and rows Random number
tables are available with two digits, three digits and more number of digits.
Suppose the sample size is 25 out of a total of 200 items. First, a serial number
[two or three or four digits) is assigned to each item. Then using a random number
table, row - wise or column wise, 25 numbers that match with the serial number are
selected. This will constitute the sample. For example, whenever a new car is
introduced in the market, people who are booking for the new car are assigned a
serial number. After the last date for booking is over, the Company will generate
those who would be given the allotment for the month, going by the random
numbers. Once the required numbers are selected, the customers who are assigned
that number are intimated about the allotment.

b) Restricted random sampling :

 As an alternative to simple random sampling design, several complex
probability sampling design can be used
 Efficiency is improved and more information can be obtained for a
given sample size using some of the probability sampling procedures
than the simple random sampling design
  The various complex probability sampling design is systematic
sampling, stratified random sampling, cluster sampling, area sampling
and double sampling

There are three different methods of restricted random sampling. These are
explained below.

i) Stratified random sampling:

 In this method, first the population is divided into various strata i.e.,
segments). Stratum means a layer. Populations from which samples
are to be selected may contain a number of layers. From each layer a
few
samples are selected.
 The items in each segment are homogeneous
 That is each stratum will contain elements which are similar to each
other in various aspects
 Then from each stratum a few elements are selected to constitute the
sample
 While making this selection either same number of items could be
selected from each strata or the number of elements selected may not
be the same for each stratum
 If the same number of elements are selected from each stratum, it is
called as proportionate stratified random sampling and if the number
of items selected is not the same for all the strata it is called as
disproportionate stratified random sampling

Merits:
1. Stratified random sampling has better representativeness.
2. It also gives more accurate information and there would be a better
coverage of the population

Limitations:
1. This method requires lot of care and pre-planning. Unless the different strata
existing in the population is known with certainty, using this method is not
possible

2. Further the basis of segmenting the population should be scientific. In the

example given above, the revenue division of Tamil Nadu state is used as
the basis. Suppose a person wants to select the number of schools in a place
 as the basis, then he should first collect the details of different types of
schools in different places. Data regarding this may not be available. As
there are a number of unrecognized schools existing in so many places.
Therefore, stratified random sampling method is time consuming.

3. Care should be taken to make selection from each stratum random, which
may not be practically possible. Any bias in selection from each stratum will
affect the accuracy of results.

ii) Systematic Random sampling : In this method the sample is formed by

selecting the first unit at random and then selecting the remaining items at evenly
spaced intervals. For example, suppose from 2000 college students we have to
select a sample-of 50 students. Each of these 2000 students are given a serial
number. First we determine the sampling interval [k]. This is obtained by dividing
the size of population by sample size (2000 / 50). We get the sampling interval (k),
of 40 Then from serial number 0001 to 0040 we select at random a serial number.
Suppose we have selected the student with the serial number 15, then with this we
add the size of k, (here it is 50), to select the second student. That is, 15+50 65.
So the second student selected bears the serial number 65. Adding size of k with
this serial number, we select the third student with the serial number 115 and the
next one selected will have the serial number 165 and so on. In this manner, we
select 50 students who constitute the sample.

Merits:
1. It is very convenient and simple to adopt
2. The time and cost involved are relatively less
3. With a large population, this method of sampling is easy to use.
4. Random selection of items is ensured, once the sampling interval is
determined
5. Sampling interval is determined scientifically depending upon the size of
Sample desired

Limitations :
1. It is less representative, as once the first item is selected at
random, subsequent items are all lying at uniform interval. So the selected
items may lack complete representativeness.
2. This method requires correct understanding of the
methodology as otherwise, the sample selected will not be correct.
3. The first item selected should be strictly at random. If there is
any bias in this first stage, this will influence the items selected at
subsequent stages.

iii) Cluster sampling:

 Groups or chunks of elements that ideally would have heterogeneity
among the members within each group are chosen for study in cluster
sampling
 When several groups with intra group heterogeneity and intergroup
homogeneity are found then a random sampling of the clusters can
ideally be done and information gathered from each of the members in
randomly chosen clusters
 Ad Hoc organization committees drawn from various departments to
offer inputs to the company president to enable him to make decisions
on product development, budget allocation, marketing strategies are
good examples of different clusters
 Cluster sampling involves grouping the population and then selecting
the groups or the clusters rather than individual elements for inclusion
in the sample
 For e.g. a departmental store may like to sample its credit card
holders. If it has I5000 customers and if it want to have the sample
size as 450 then 15000 customers can be grouped into 100 clusters of
150 each. Three clusters can then be selected randomly
 For example, suppose we have to select 1000 farmers from Tamil
Nadu. Then in the first stage, we will divide the state into district,
from among which we will select two or three districts at random in
which agricultural operations are predominant. Then in the second
stage, each selected district will be divided into different Taluks from
which a few taluks from each selected district will be selected at
random. Only taluks where agricultural occupation / operations are
predominant are selected. Then from each taluk selected, a few
panchayat unions with agricultural operations will be selected. Each
panchayat union consists of a number of panchayats, and so a few will
be selected based on the predominance of agricultural operations.
From each panchayat consisting of a number of villages, a few will be
selected where agricultural operations are performed in large scale.
Then from these villages, the required number of farmer (1000) is
selected. Since the sampling is done at various stages, it is called
multi-stage. It is also called cluster sampling because, in each stage
 the attempt is to focus only those items Which has the desired
characteristic. In the above example, since the object is to select 1000
farmers. In each stage, units with predominant agricultural operations
alone are considered. In this manner the focus is only on items which
possess the desired characteristics.

 SINGLE STAGE CLUSTER SAMPLING

 In this method population is divided into convenient clusters,
randomly choosing the required number of clusters as sample subjects
and then investigating all the elements in each of the randomly chosen
clusters

 MULTISTAGE CLUSTER SAMPLING

 Cluster sampling can be carried out in several stages and it is known
as multistage cluster Sampling.
 The samples are selected at different stages and the population is first
divided into different stages
 Few items are selected at random on the basis of the specific feature
or characteristic. From these in the second stage a few elements are
selected at random possessing the characteristic and so on to finally
make the necessary selection of samples.
 All the samples selected at random will possess the common
characteristic or will be homogeneous in some basis
 If 1000 farmers are to be selected from Tamilnadu, first the states are
divided into districts, selected districts will be divided into Taluks,
selected Taluks will be divided into Panchayat unions, Panchayat
Unions will be divided into villages and then farmers will be selected

 AREA SAMPLING
 The area sampling design constitutes geographic clusters
 When the research pertains to populations within identical
geographical areas such as done countries, city blocks or particular
boundaries within a locality area sampling can be done.
 Area sampling is therefore a form of cluster sampling within an area
 Location plans for retail stores, advertisements specially focused on
local population could use an area sampling design
  DOUBLE SAMPLING
 This method is resorted when further information is needed from a
subset of the group from which some information has already been
collected for the same study
 A sample design where initially a sample is used in a study to collect
some preliminary information of interest and later a subsample of this
primary sample is used to examine the matter in a more detailed
manner it is called double sampling
 A structured interview might reveal that a subgroup of the respondents
have more insight into the problems of the organization and these
respondents are interviewed again by asking some additional
questions

Merits: of cluster sampling

1. It is highly flexible
2. It ensures better representativeness
3. Results and conclusions based on the sample will hold good for the
population
4. This type of sampling is very useful either for formulating policy or
evaluating an implemented policy.

Limitations: of cluster sampling

1. In practice this method is found to be less
accurate compared to other meth because any bias at any stage will get
accumulated.

2. Unless a person is fully aware of the various

stages into which the popular can be divided, he cannot be effective in
selecting the required number samples.

3. The characteristic or feature to be present

with samples at all stages may no. fulfilled in all cases. Suppose in a study is
about the effectiveness of pollution control policy, it should be decided in
first stage which type of pollution studied (viz., air, water, noise, etc). These
types of pollution are very common in all places. Then selecting a few
samples at random from each stage will cumbersome.

4. The bias of the person selecting the sample

will get reflected in the process. For example, in the case of a study on
 pollution, the degree of pollution differ from place to place. Then the places
above a certain level of pollution
alone may have to be selected. That means, data regarding the level
pollution of various types, should be available. In the absence of this, select
will not be strictly random.

2. Non-random Sampling or Non-probability Sampling:

 NON PROBABILITY SAMPLING
 In non-probability sampling design, the elements in the population do
not have any probabilities attached to their being chosen as sample
subjects. This means that the findings from the study of the sample
cannot be confidentially generalized to the population
 Non random or non-probability sampling refers to the sampling
process in which the samples are selected for a specific purpose with a
pre-determined basis of selection .The reliability of conclusions based
on this type of sampling is less .
 The various non probability sampling methods are convenience
sampling. judgment sampling and quota sampling(purposive sampling
methods)

a) Judgment Sampling:
In this method, the sample selection is purely based on the judgment of the
investigator or the researcher. This is because, the researcher may lack information
regarding the population from which he has to collect the sample. Population
characteristics or qualities may not be known, but sample has to be selected. In
such instances, judgment sampling method is used. The investigator on the field is
allowed to select any item of his choice to constitute the sample. Once the sample
Size is determined, the investigator is free to select any item on the field. For
example, suppose 100 boys are to be selected from a college with 1000 boys. If
nothing is known about the students in this college, then the investigator may visit
the college and choose the first 100 boys he meets. Or he may select 100 boys all
belonging to III Year. Or he might select 25 boys from Commerce course, 25 from
Science courses, 25 boys from Arts courses and 25 from Fine arts courses. Hence,
when only the sample size is known, the investigator uses his discretion and selects
the sample.

The strength of this method is that the sample elements are selected by the
investigator on the spot using his understanding of the population. So the samples
may fairly represent the population. But if the investigator may be biased, this type
of sampling may not be fully representing the population. Further, there is a need
to train investigator to do this job correctly.

b) Convenience Sampling or CHUNK :

This method of sampling involves selecting the sample elements using some
convenient method without going through the rigour of sampling method. The
researcher may make use of any convenient base to select the required number of
samples. For example, suppose 100 car owners are to be selected. Then we may
collect from the RTOs other the list of car owners and then make a selection of 100
from that to form the sample. But unless the list at the RTO's office is up to date,
the sample selected will be wrong. Further, if an investigator is biased, the sample
selected may not be random.

c) Quota Sampling :
In this method, the sample size is determined first and then quota is fixed for
various categories of population, which is followed while selecting the sample.
Suppose we want to select 100 students, then we might say that the sample should
be according to the quota given below : Boys 50%, Girls 50% Then among the
boys, 20% college students, 40% plus two students, 30% high school students and
10% elementary school students. A different or the same quota may be fixed for
the girls.
In this method the quota has to be determined in advance and intimated to
the investigator. The quota for each segment of the population may be fixed at
random or with a specific basis. Normally such a sampling method does ensure
representativeness of the population.

 D) SNOWBALL SAMPLING
 Snowball sampling uses recommendations to find people with the
specific range of skills that has been determined as being useful.
 An individual or a group receives information from different places
through a mutual intermediary
 This is referred to metaphorically as Snowball sampling house as
more relationships are built through mutual association more
connections can be made through the new relationships and a plethora
of information can be shared and collected, much like a snowball that
rolls and increase in size as it collects more snow.
 Snowball sampling is a useful tool for building networks and
increasing the number of participants. However, the success of this
technique depends greatly on the initial contacts and connections
made.
SAMPLING ERRORS
 While using sampling, errors are committed. These errors are broadly
classified a sampling errors and non-sampling errors.
 Sampling errors arise due to draw inferences about the population on the
basis of few observations. That is when the sample size is not a true
representative of the population, any conclusion drawn on the basis of
sample will not be applicable to the population
 Such errors may be due to several factors. It may be due to biased errors and
non-biased errors

Biased errors - It is understood as the interference of the investigator's likes and

dislikes in the process of sampling. For e.g., if the investigator has to collect data
from a specific group of people he may collect data from unrelated group also.

FAULTY PROCESS OF SELECTION - This refers to a situation when the

investigator does not apply the randomness in his choice or selection of the sample
elements from the population

FAULTY COLLECTION OF INFORMATION - Adoption of faulty method of

collecting information may cause errors. For e.g., suppose the population or the
scope of the survey is not clear. Then this might lead to collection of information
from sample elements not relevant for the study

FAULTY METHOD OF ANALYSIS - This is a most frequently committed

mistake on the part of the researcher. When the data collection is completed, the
researcher embarks on data analysis. Before this the data has to be classified and
tabulated. If any mistake is committed in this stage subsequent analysis will yield
wrong results

 UNBIASED ERRORS
 These errors are caused due to chances not strictly due to any bias on
the part of the investigator
 Sometimes the findings from the selected sample may be different
from other elements not included in the sample

 NON-SAMPLING ERRORS
 Non-sampling errors are those errors which are not due to any
sampling process
  Investigators may collect data without using the complete schedules
or proper measurement
 Faulty method of interview or observation may also contribute to non
sampling errors
 Use of untrained or unskilled investigators only causes more
confusion rather than carrying out the work properly. Such
investigators would report incomplete or irrelevant data
 There are instances when the organizer of the survey does not plan for
close supervision and control over investigators in the field. As a
result coverage of respondents will not be complete
 Mistakes committed in data processing is also a source of non-
sampling errors
 Interpretation of data requires enormous experience and skill. Wrong
interpretation of results will result in wrong interpretation of outcome
 The total sampling error is a combination of both sampling error and
non-sampling error. To minimize the sampling error if we increase the
sample size non-sampling error is bound to increase. Effective steps
should be taken to minimize the non-sampling errors.

Sample Size
One of the most important issues to be settled while using sampling method is to
determine the size of sample. More often than not, researchers commit mistakes in
deciding the sample size. There is a thumb rule, which says that to satisfy
statistical requirement, the size of the sample should be a minimum of 30 and
above. In statistics any sample with 30 and more elements is considered large
sample. Less than 30 elements in a sample constitute only small sample. By
definition this might appear to be an easy way out to determine the sample size.
But it should be noted that there are several other considerations or factors which
influence the sample size. These are discussed hereunder.

1. The size of the population : Depending upon the size of population, the size of
sample has to be decided. If the population is very small (say for example only 50],
then the sample size could also be small. But, it should be remembered that larger
the size of population, larger should be the sample size to achieve
representativeness and accuracy.

2. The resources available: What amount of time and financial resources are
available to the researcher will determine the size of sample. With sufficient time
and large volume of funds available, the sample size could be large, otherwise it
should be small.

3. The extent of accuracy desired: One of the requirements of data analysis is the
accuracy level. There is no choice about the level of accuracy that one wants to
achieve or maintain. But while dealing with large population, due to constraints on
resources, sampling has to be adopted. In that case, the level of accuracy that is
desired must be spelt out. Suppose, the choice is for achieving cent per cent
accuracy, then sampling itself cannot be thought of. Alternatively, if the accuracy
desired is 95% then sample size should be large. Any level of accuracy less than
this [95%) may require only small sample size.

4. Nature of population : The similarities and dissimilarities identified with

population itself may affect the sample size. If the population contain a lot of
heterogeneous sub population [i.e., small segments of population with different
features or characteristics], then large sample size is required. For example, if in a
Computer training institute, sample is to be selected drawing from students
undergoing different courses, then the sample size should be large. Alternatively
suppose from a Commerce college a sample is to be selected, a small size is
sufficient as there is no dissimilarity in the population

5. Method of sampling adopted : Several sampling methods have been elaborated

in the previous section of this topic. Depending upon the method of sampling used,
the size of sample will be decided

6. Nature of respondents : Success or failure of a sample survey depends

ultimately on the response of the informants. So the nature of respondents will
influence the sample size. Suppose in a survey on the opinion of a policy of
liberalisation, introduced by the Government, if the respondents are literate, the
size of sample could be smaller. If the respondents are illiterate or less literate, the
size of sample should be large
 UNIT III
DATA COLLECTION
NATURE OF DATA
Data refers to information or facts. Often, researchers understand by data only
numerical figure. It also includes descriptive facts, non-numerical information,
qualitative and quantitative information. In a research if the data are available, the
research is half - complete.

 PRIMARY DATA - Primary Data are those which are collected afresh and
for the very first time and thus happens to be original in character.
 SECONDARY DATA - Secondary Data are those which are already
collected by someone else and which have been passed through the
statistical process.
 The methods of collecting primary and secondary data differ since primary
data are to be originally collected, while in case of secondary data the nature
of data collection work is merely that of compilation

PRIMARY SOURCES OF DATA

 Primary sources of data are individuals, focus groups, panel of respondents
generally set up by the researcher and from whom opinion may be sought
on specific issues from time to time.
 FOCUS GROUPS
 Focus groups consists primarily of 8 to 10 members with a moderator
leading the discussion for about 2 hours on a particular topic, concept or
product
 Members are generally chosen on the basis of their expertise in the topic on
which information is sought (e.g.) computer specialists may discuss matters
related to computers
 The focus sessions are aimed at obtaining respondent's impressions ,
interpretations, opinions as the members talk about the event, concept,
product or service
 The moderator plays a vital role in steering the discussion in a manner that
would draw out the information sought and keeping the members on track
 The unstructured and spontaneous responses are expected to reflect
the genuine opinions, ideas and feelings of the members about the
topic under discussion.
  Focus groups are relatively inexpensive and can provide fairly
dependable data within a short time frame

THE NATURE OF DATA OBTAINED THROUGH FOCUS

GROUPS
 The data obtained is qualitative and not quantitative.
 It is the least expensive of all the data collection methods.
 The members are not selected scientifically to reflect the opinion of the
people at large.
 When exploratory information is collected as a basis for further scientific
research, focus groups serve as an important function (E.g.) the value of
focus groups in exploring the concept of "intellectual property".
 Focus groups have been credited with enlightening investigators as to why
certain products are not doing well, why certain advertising strategies are
effective, why specific management techniques do not work etc

PANELS
 Panels like focus groups are another source of primary information for
research purposes
 Focus groups meet for a one time group sessions, panels meet more than
once
 When the effects of certain interventions or changes are to be studied over a
period of time ,panel studies are very useful
 Individuals are randomly chosen to serve as panel members
 For e.g., if the effects of a proposed ad for a certain brand of coffee is to be
assessed quickly, the panel members can be exposed to that ad and their
intentions of purchasing that brand can be assessed. A few months later, the
product manager might think about introducing a change in the flavor of the
same effect and explore its effects on the panel.
 Thus, a continuing set of experts serves as the sample base. Such expert
members composed the panel, and research that uses them is called panel
study.
 Nielsen TV index is based on the television viewing patterns of the pencil

METHODS OF PRIMARY DATA COLLECTION

SURVEYS
  Survey research is one of the most important areas of measurement in
applied social research. The dictionary meaning of survey is: "Survey is a
technique for gathering information from a large number of users" |Brehob,
20011.
 Surveys are usually conducted in case of descriptive research. Survey type
research usually have larger samples.
 Surveys are concerned with describing, recording, analyzing and
interpreting conditions that either exist or existed.
 A “survey" can be anything from a short paper-and-pencil feedback form to
an intensive interview.
 A survey is a data collection tool used to gather information about
individuals. Surveys are commonly used in psychology research to collect
self-report data from study participants.
 A survey can be administered in a couple of different ways. In one method
known as a structured interview, the researcher asks each participant the
questions. In the other method known as a questionnaire, the participant fills
out the survey on his or her own.
 Surveys are generally standardized to ensure that they have reliability and
validity. Standardization is also important so that the results can be
generalized to the larger population.

ADVANTAGES OF SURVEY METHOD

 Surveys allow researchers to collect a large amount of data in a relatively
short period of time.
 Surveys are less expensive than many other data collection techniques.
 Surveys can be created quickly and administered easily.
 Surveys can be used to collect information on a wide range of things,
including personal facts, attitudes, past behaviors and opinions.

DISADVANTAGES OF SURVEY METHOD

 Poor survey construction and administration can undermine otherwise well
designed studies.
 The answer choices provided on a survey may not be an accurate reflection
of how the participants truly feel.
 While random sampling is generally used to select participants, response
rates can bias the results of a survey.
SURVEY TECHNIQUES - Interview method, Questionnaire method, Schedule
 INTERVIEWS
 Interview is a conversation between two or more people where question is
asked by the interviewer to obtain information from the interviewer
 The interview method of collecting data involves preparation of oral-verbal
stimuli and reply in terms of oral-verbal responses
 This method can be used through personal interviews and if possible trough
telephone interviews
 Interview a prominent method of data collection may be defined as a two
way systematic conversation between an investigator and an informant,
initiated for obtaining information relevant to a specific study
 It involves not only conversation, but also learning from the respondent's
gestures, facial expressions and pauses and his environment.

Types of Interview:
Interview may be broadly classified as
1. Direct interviews and 2. Indirect interview.
In both these types different approaches may be followed like: structure interview,
unstructured interview, focused interview, non-directive interview and telephonic
interview. These types of interview are discussed hereunder.

Direct Interview:
In this type of interview, the interviewer and the interviewee meet personally either
with prior appointment or not. This type of interview ma further be classified as
structured interview, unstructured interview, focused interview, clinical interview
and non-directive interview. Usually when this technique is adopted, the
interviewer may brief the respondent about the purpose of interview and its scope
in advance. This enables the respondents to be read with necessary details or data.
For example, suppose the Chairman of ISRO is t be interviewed. Then an
appointment must be obtained and the subject matter interview or the purpose of
the interview should be stated in advance. This will enable the Chairman to collect
the necessary data in advance so as to give authentic information at the time of
interview .But there are occasions when the respondent is contacted and his
opinion collected. In such cases there is n possibility for briefing him about the
interview. For example, television crew like SUN TV] meet the people coming out
a theatre screening a new film an ask them about the film. The response is simply
the opinion of the audience an there is no advance intimation given.

(A) Structured Interview:

In this type of interview the person collecting information decides advance the
nature, scope, questions to be asked, the persons to be contacted etc., in advance.
At the time of interview no deviation is made from the questions to be asked or
scope or the persons. For example: It is usual for Journalist to interview the
Finance Minister after the presentation of Budget. In such occasions, the Journalist
should be well prepared and decide in advance the questions to be asked, the
details to be quoted, the instances to be recalled, etc. Sometimes even the questions
to be asked and other details are to be submitted to the authorities concerned,
before conducting the interview. Similarly during the college re-opening season,
the Principals of various colleges are regarded the demand for admission, number
of applications received, popularity of various course among the students etc
Unless the interviewer decides the questions in advance, the Principals may not
have time to reply questions off-hand by the interviewer.

The most important advantages of such structured interview are:

 The interviewer is well prepared and so the interview is conducted in a
focused manner.
 As much details as possible could be collected about the subject matter
interview, as the interviewer decides in advance the depth of interview.
 Time of both the interviewer and the respondents could be saved.
 This is the only type of interview possible when the respondents are VIPs.
 There is no scope for irrelevant matter to find a place in the course of
interview.
 If the respondent is informed in advance, he could prepare necessary
details so that the outcome is reliable.

But this method of interview has the following limitations:

 Since the subject matter is decided in advance there is no scope for
elaborating or extending the interview.
 Sometimes the respondents may manage to give well rehearsed replies
which would fail to bring out the real information .
 There is a need for the interviewer to plan the interview properly and so if
the plan is not perfect, the interview findings may not be complete.
 There is some scope for the interviewer to be biased while preparing the
questions to be raised.
 There is also little scope for exercising the creative nature of the
interviewer.

(B) Unstructured Interview:

In this type of interview, interview is conducted on the spot without any
preparations or advance information to the respondent. For example, suppose an
organization producing a new health drink wants to know the opinion of the
people directly. Then it might send trained field investigators who meet people at
random and offer them a cup of that new drink . After they drink, their opinion is
asked and the responses are noted down or recorded. As such interviews take place
with people not informed in advance, except the location, nothing can be decided
by the organization conducting such type of interview. So the investigators raise
questions with the respondents and records the answers. Such interviews are used
when opinion poll is conducted. For example, during election time, the TV
channels would meet people moving around and ask them about their opinion
about different parties and the one to which they would vote. Similarly after the
budget is presented in the Parliament, public opinion is collected on the
announcements in the budget through unstructured interview.
Merits:
1. The interviewer could plan his interview depending upon the response of the
informant and possibly collect additional information.
2. The scope for bias on the part of the interviewer or the respondents is less.
3. The real opinion of the respondent could be obtained through such interview.
4. In certain circumstances, this is the only type of interview possible.
5. Such interviews will be usually very short and specific and so not much of time
is wasted.
Demerits :
1. The interviewer has to be very much alert to obtain the specific response.
2. Sometimes the respondent may answer the questions without understanding
them, as there is no time available for explaining the questions.
3. It is possible that irrelevant respondents are contacted and irrelevant responses
are obtained.
4. The interviewer may intelligently the questions suggestive to obtain the desired
response. (For example: an interviewer collecting the opinion about a film may
ask: Don't you think that the hero could have done better? Don't you feel that the
music in this film are bad? Don't you think that this film will flop ?]

(C) Focused Interview :

This type of interview is unstructured by nature. In this type of interview the
object of the interviewer is to focus the attention of the respondent on a specific
issue or point. The interviewer has the freedom to plan the interview and conduct it
the way he wants it. The question sequence, wording of questions, etc., are all
decided by the interviewer on the spot. For example suppose a detective is
questioning a person regarding a crime committed in an area .The detective has to
be very much experienced to make the person interviewed to answer only about the
crime and nothing else.

(D) Non-directive Interview:

This is again unstructured type of interview. In this type, the interviewer
encourages the respondents to say whatever he likes and feels on a subject matter.
There may not be much of questioning taking place. The respondent is free to
express his views or opinions without any direction from the interviewer. For
example: suppose in a college students are on strike. Then an interviewer may
encourage different students to say whatever they feel about the reasons for the
strike . He may not intervene when the students are stating the reasons. Through
such a process more facts may come to light, than when the interview guides the
respondents.

(E) Telephonic Interview:

This is basically a type of direct interview and but there is no scope for physical
presence of both the parties to the interview. Such interviews are used when the
informant and the interviewer are geographically separated (i.e. a person in India
interviewing a person in USA). Since the interview has to be very much focused,
the interviewer should prepare in advance the questions to be raised. A well
prepared interview will bring to light lot of information. But the problems in this
type of interview are: a) the respondent should be accessible by phone , b) there is
not much time available for giving any clarification, c) if there is disturbance in the
telephone line, then the information given may not be clear, d) it is also costly.

Merits of interview as a method of data collection :

1. Interview enables personal contact with which factual information could be
obtained.
2. The interviewer can guide the respondents to understand the questions a suitably
rephrase or modify the questions.
3. The non-response in this category of data collection is low.
4. Spontaneous reply of the respondents can be obtained which would truly reflect
their opinion.
5. Interviewer has the flexibility to handle the interview to collect relevant
information.
6. The interviewer can combine observation with interview so that a lot of
additional information about the environment, nature, behavior and attitude of the
respondent could also be noted.
7. The interviewer can be persuasive to obtain the response of the respondent while
this may not be possible in the case of questionnaire method of data collection.
8. The interviewer can adopt himself better by using the language with which he
can reach the respondents better and the educational level of the respondent.
9. It is also possible to obtain personal information which will not be revealed
through questionnaire.

Demerits of interview as a method of data collection :

1. This method presupposes the existence of rapport between the respondent and
the interviewer. In case there is no rapport, the interview cannot be held at all
2. It is a costly method of data collection, as the interviewers should be trained,
oriented and supported.
3. The time taken for covering a large sample of respondents is more than what it is
under questionnaire method.
4. It is possible for a respondent to conceal his real opinion or views and so
genuine data may not be available.
5. The interviewer may also be biased and thereby bias may influence, the
interview outcome
6 Interview method requires an elaborate organizational arrangement.
7. Sometimes this method cannot be followed as it would require fixing up
appointment, specifying the questions that are to be answered, duration of
Interview, the person interviewing the organizational background. The purpose of
interview, etc; Inspite of providing all these information, it may not be possible to
get an appointment to conduct the interview.

How to make interview successful

If the interview should be successfully conducted, the following points are to be
taken into account.
1. The interviewer should be carefully selected.
2. The interviewer should be trained properly.
3. Different methods of obtaining the response from the informants have to be
explored and the interviewer should be trained in all these aspects.
4. Unless the interviewer is experienced he would not be able to conduct the
interview properly. But without conducting interviews he cannot be
experienced .So care should be taken while selecting this method of data
collection.
5. Honesty and integrity of the interviewer determines the outcome of the
interview. So the qualities of the interviewer should be objectively studied.
6. The interviewer must first create a rapport with the respondent and ensure
presence of cordial atmosphere to conduct the interview.
 7. The interviewer should be fully equipped to clarify any questions raised by
the informant.
8. Qualities like courteousness, politeness, friendly, conversational,
unbiasedness are all necessary to make the interview successful.
The interviewer should be alert and intelligent with presence of mind to keep the
interview focused on the subject matter

QUESTIONNAIRE METHOD
QUESTIONNAIRES
 A questionnaire is a research instrument consisting of a series of questions to
be asked from the respondents and thereby gathering the desired information
from respondents. It also contains a suitable space where the answers can be
recorded.
 The term questionnaire usually refers to a self-administered process where
the respondent himself reads the questions and records the answers without
the assistance of the interviewer.
 A questionnaire is a method of obtaining specific information about a
defined problem so that the data after analysis and interpretation results in a
specific solution to the problem.
 The success of collecting data through the questionnaire method largely
depends on the proper design of the questionnaire.
 This is a specialized job and requires high degree of skill, experience,
thorough knowledge about the research topic, ability to frame questions and
a high degree of patience.
 Questionnaires have advantages over some other types of surveys in that
they are cheap, do not require as much effort from the researcher as verbal or
telephone surveys, and often have standardized answers that make it simple
to compile data.
 Questionnaires are also sharply limited by the fact that respondents must be
able to read the questions and respond to them.

TYPES OF QUESTIONNAIRE
 Structured Questionnaire
 Structured questionnaires are those questionnaires in which there
definite, concrete and predetermined questions. The questions are
presented with exactly the same wording and in the same order to all
respondents.
  Such questionnaires may also have fixed alternative questions in
which the responses of the informants are limited to the stated
alternatives. The respondents own words are held to the minimum.
 Structured questionnaires are simple to administer and relatively
inexpensive to analyse .
 Unstructured Questionnaire
 The interviewer is provided with the general guide on the type of
information to be obtained, but the exact question formulation is
largely his own responsibility and the replies are to be taken in the
respondent's own words as possible.
 In some situations tape recorders may be used.

 Open ended Questions - An open-ended question asks the respondent to

formulate his own answer. Often difficult to analyse and hence should be
avoided in the questionnaire to the extent possible.
 Close ended Questions - A close-ended question offers the respondent to
pick an answer from a given number of options. The response options for a
closed-ended question should be exhaustive and mutually exclusive
Respondents' answers are limited to a fixed set of responses. Most scales are
closed ended. Other types of closed ended questions include:
 Dichotomous Questions Yes/no questions - The respondent answers
with a "yes" or a "no"
 Multiple choice - The respondent has several options from which to
choose. Alternative answers will be listed.
 Scaled questions - Responses are graded on a continuum (example:
rate the appearance of the product on a scale from preferred
appearance). Examples of types of scales include the Likert scale. 1 to
10, with 10 being the most semantic differential scale and rank-order
scale (See scale for a complete list of scaling techniques.)

GUIDELINES FOR QUESTIONNAIRE

Sound questionnaire design focuses on three areas.
 The first relates to the wording of questions.
 The second refers to the planning of issues of how the variables will be
categorized, scaled and coded after the receipt of responses.
 The third pertains to the general appearance of the questionnaire

 PRINCIPLES OF WORDING
 CONTENT & PURPOSE OF THE QUESTIONS- The nature of the
 variables tapped - subjective feelings or objective facts - will determine what
kind of questions will be asked.
 If the variables tapped are of subjective in nature (satisfaction,
involvement) where respondent's beliefs, attitudes and perceptions are
to be measured, the questions should tap the elements and dimensions
of the concept.

 If objective variables like age and educational level of respondents are

tapped, a single direct question would be appropriate.

 Language and wording of the questionnaire - It should be based on the level

of understanding of the respondents. The choice of words usually depends
on the educational level, usage of terms in various cultures. If the questions
are not easily understood or interpreted in a different way by the respondent
the researcher would obtain wrong answers to the questions.

TYPES & FORMS OF QUESTIONS

OPEN ENDED VERSUS CLOSE ENDED QUESTION:
 Open ended questions (e.g.) State the things that are challenging and
interesting in the job, shat is that they like about the supervisor?.
 Close ended questions gives 10 to 15 specs that might seem
challenging or interesting and ask the respondents to rank the first five
in their order of preference.

POSITIVELY & NEGATIVELY WORDED QUESTIONS:

 Instead of phrasing all questions positively it is advisable to include
some negative worded questions as well, so that the tendency in
respondents to mechanically circle the points towards one end of the
scale is minimized.
 (E.g.) if the respondent has circled 5 for a positively worded question
such as I feel I have been able to accomplish a number of different
things in my job", he cannot circle number 5 again for a negatively
worded question like "I do not feel I ma very effective in my job".
 The use of double negatives and excessive use of words not and only
should be avoided.
 It is better to say that the rich need no help" than to say Only the rich
do not need help

DOUBLE-BARRELED QUESTIONS:
  A question that lends itself to different possible responses to its sub
parts is called a double- barreled question.
 Such questions should be avoided and two or more separate questions
should be asked instead. (e.g.) Do you think that there is good market
for the product and that it will sell well? could bring yes response to
the first part and no response to the second part.
 Therefore it is better to ask two questions like (1) Do you think that
there is a good market for the product? (2) Do you think the product
will sell well?

AMBIGUOUS QUESTIONS :
 Even questions that are not double barreled might be ambiguously
worded and the respondent may not be sure what exactly they mean
 (E.g.) To what extent you say that you are happy? The respondents
may be confused whether the question refers to their workplace or at
home or in general. The respondents may not provide a correct
answer to the question.

RECALL-DEPENDENT QUESTIONS:
 Some questions might respondents to recall experiences from the past
that are hazy in their memory. Answers to such questions may have
bias
 (E.g.) employee with 30 years of experience if he is asked to state
when he first started working in a particular department and for how
long will not be able to recollect and may give biased answers. The
best source is therefore personal records.

LEADING QUESTIONS:
 Questions should not be phrased in such a way that they lead the
respondents to give the answers that the researcher would like or
want them to give.
 (E.g.) Do you think that in these days of escalating cost of living
employees should be given good pay rises?. By asking such a
question the respondents are pressured to say “yes”.
 To what extent do you think that employees should be given higher
pay rises?

LOADED QUESTIONS :
  Questions become loaded when they are phrased in an emotionally
charged manner. An example of such a loaded question is asking
employees " To what extent do you think management is likely to be
vindictive if the Union decided to go on strike?. The words “strike”
and “vindictive” are emotionally charged terms, polarizing
management and unions.

SOCIAL DESIRABILITY :
 Questions should not be worded in such a way that they elicit socially
desirable responses. For e.g., a question such as Do you think that
older people should be laid off?" would elicit a response of “no"
mainly because society would frown on a person who says that
elderly people should be fired even if they are capable of performing
the jobs satisfactorily .

LENGTH OF QUESTIONS:
 Short questions are preferred to long one. As a rule of thumb a
question or a statement in the questionnaire should not exceed 20
words

SEQUENCING OF QUESTIONS:
 The sequencing of questions should be such that the respondents are
led from the questions of a general nature to those that are more
specific and from questions that are relatively easy to answer to those
that are progressively more difficult. This funnel approach facilitates
the easy and smooth progress of the respondent.

CLASSIFICATION DATA OR PERSONAL INFORMATION:

 It elicits demographic information from the respondent such as age,
educational background, marital status and income. Unless absolutely
necessary it is best not to ask for the name of the respondent.
 PRINCIPLES OF MEASUREMENT
 The data that is collected should be appropriate for the testing of
hypothesis.
 Scales and scaling techniques are used - interval and ratio scales are
used preferred to nominal or ordinal scales.
 Goodness of data is assessed through tests of validity and reliability.
 VALIDITY - It establishes how well a technique, instrument or process
measures a particular concept
  RELIABILITY - Indicates how stably and consistently the instrument taps
the variable.

 GENERAL APPEARANCE OR GETUP OF THE QUESTIONNAIRE

 A good introduction.
 Organizing questions, giving instruction and guidance and good alignment-
demographic information or personal questions can be asked at the end
rather than in the beginning.
 Information on income and other sensitive personal data- need to explain
how it is going to contribute to research and ensure that it will be kept
confidential.
 Open ended questions at the end - End up with an expression of sincere
thanks.
 Concluding the questionnaire - It should end up with a courteous note and
reminding the respondents to ensure that all questions are answered.
 Pre testing of structured questions - It is done to ensure that the respondent
has no problem in the measurement and wording of questions.

VALIDATION OF QUESTIONNAIRE
 Validation" is also the process by which any data collection instrument,
including questionnaires, is assessed for its dependability.
 Validating questionnaires is somewhat challenging as they usually evaluate
subjective measures, which means they can be influenced by a range of
factors that are hard to control.
 When validating a questionnaire it is important that a sample is used that is
representative of the population in which the instrument is to be used.
 There are no general criteria for the required sample size in a validation
study. A sample size of at least 50-100 participants is generally
recommended. However, certain methods require larger numbers of
participants.
 The time interval between assessments is important for determining test
retest reliability. This interval should not be too brief in order to prevent
participants remembering what they previously answered, and should not be
too long either, as participants' scores may have actually changed.
 It is important to establish a priori hypothesis when determining validity and
responsiveness, for instance, expected correlations with other questionnaires
or anticipated differences in scores between certain subgroups. These
hypotheses should be as specific as possible.
 Validation involves establishing that the instrument produces data that are
reliable and true. There are a number of ways to define this, some of which
outlined below.
 VALIDITY: the degree to which a questionnaire reflects reality. There are a
number of different facets to validity.
 INTERNAL VALIDITY: the degree in which questions within an
instrument agree with each other. i.e. that a subject will respond to similar
questions in similar way.
 STATISTICAL VALIDITY: this is related to internal validity, and assesses
whether the differences in the questionnaire results between patient groups
can appropriately be subjected to statistical tests of significance.
 CONTENT VALIDATION: It often refers to face validity. Face validity is
determined by comparing the questionnaire with other similar questionnaire
surveys. Face validity was also determined through pre testing such as the
initial pilot study.
 SAMPLING VALIDITY: It is another component of validation. A large
sample size can ensure low sampling errors and high sampling validity.
 EXTERNAL VALIDITY: the ability to make generalizations about a
population beyond that of the sample tested.
 LONGITUDINAL VALIDITY: whether a questionnaire returns the same
results in a given population over time, assuming all else remains equal.
 LINGUISTIC VALIDITY: whether the wording of the questionnaire is
understood in the same way by everyone who completes it.
 EMPIRICAL VALIDITY: It examines the survey results by comparison
with other studies. The aim is to check consistency with previous results.
Empirical validation of the questionnaire reliability often involves two
techniques
 Test - Retest Techniques : It determines stability of measured
indicators
 Construct Validity : It is a scoc to determine internal consistency-
reliability, measured by the Cronbach alpha.

SCHEDULE
 Schedule is a device in social research, which is most frequently used in
collecting field data especially where the survey method is employed. It is
used in indirect interview.
 It contains questions and blank tables which are to be filled in by the
investigators themselves after getting information from the respondents.
 Outwardly schedule and questionnaire appear to be the same but there is
difference between the two. Schedule is used in direct interview and direct
observation and is filled in by the research work himself .
 Schedule is the name usually applied to a set of questions which are asked
and filled in by an interviewer in a face-to-face situation with another
person Goode and Hatt

DIFFERENCE BETWEEN QUESTIONNAIRE AND

SCHEDULES

BASIS OF QUESTIONNAIRE SCHEDULE

DIFFERENCE
Usage Respondent himself records the Researcher/Enumerator records
answers obtained. the answer obtained

Cost Relatively cheaper as it is sent Costlier, as the investigator has

by mail to the targeted to be appointed, trained and
respondents meets every informant at the
latter’s place.

Coverage Wide coverage possible, as it Relatively limited coverage, as

can be sent to any place by post the investigator is more focused
and obtain details personally.

Degree of response Less, as all the respondents, do Relatively good, as the

not respond. investigator is more focused
and obtain details personally.

Quality of response Not good, as the respondent Relatively better as the

answers the questions the way investigator guides the
it is understood. respondents in understanding
the questions in right context.
Identify of respondent It is not known clearly who It is clearly known, as the
answered the questionnaire and enumerator himself elicits the
this in turn might affect information. So the accuracy of
accuracy of information information is more.
obtained.
Time taken for reply It cannot be established, as the It is possible to plan the enquiry
respondent may reply at his and depute the investigators
 convenience. accordingly and collect
information within a targeted
time.
Personal contact It is completely absent and to It is absolutely possible and so
that extent there is no scope for the quality of response is better.
giving any clarification to The investigator can help the
respondents respondent to understand the
questions clearly.
Pre-condition for use The respondent should be The literacy status of the
literate and cooperative respondent is not a limitation.
The investigator can explain the
question and obtain the
response.
Sample coverage It is possible to cover a wide This is not possible, as the
range of sample elements, as investigator has to personally
the questionnaire is only sent contact each respondent.
by post.
Accuracy of information It is not likely to be high, as it Relatively accuracy is better in
depends on the structure of the this method, as the investigator
questionnaire itself. can determine the accuracy on
the field and adopt appropriate
methods to ensure accuracy.
Presentation requirement Questionnaire should be No such requirements are a
designed properly and made condition.
attractive to encourage the
respondents to fill it
Scope for application of other This is not possible, as the There is a lot scope for the
methods of data collection questionnaire is sent to the investigator to apply
respondent. observation method or
interview method of data
collection, along with the use of
schedules.
Field control and monitoring This is not possible as the There is good scope for
questionnaire is filled by the controlling, editing and
respondent himself monitoring information on the
field itself.
Bias in information collected There is no way to test the If the investigator is trained and
extent of bias of the experienced, then there is very
information given by the little scope for bias in
respondent. information content.

Use of Schedules:
Whenever a researcher uses schedule to collect data, the following steps should be
taken.

1. The researcher should prepare the list of respondents to be contacted or the area
where they can be contacted.
2. Depending on requirement, investigators should be selected.
3. The investigators should be explained the purpose of the survey, their job,
responsibilities, accuracy desired, importance of answers recorded, the need to be
clear in recording details, etc.,
4. The investigators should be trained with the schedule.
5. Necessary instructions to the investigators to deal with different types of
problems [like non- availability of respondent, non-cooperative respondent, etc) on
field should be given.
6. Sufficient arrangement for field control, monitoring and supervision should be
made.
7. Method of follow up of non-response should be determined in advance.
8. The investigators selected should be honest, sincere, hard working, patient and
take all efforts to collect the details.
9. Time frame for completing the data collection should be clearly spelt out.
10. Periodical review of the filled up schedules would help to reframe the
questions or change the sequence or initiate corrective action.

OBSERVATION METHOD
 It is the most common method used in studies related to behavioral sciences.
 Observation becomes a scientific tool and the method of data collection for
the researcher when it serves a formulated research purpose, is
systematically planned and recorded and is subjected to checks on validity
and reliability.
 Under this method, the information is sought by investigator's own direct
observation without asking from the respondent.
 Observation as a method of data collection is used very frequently,
whenever collection of data through other methods is difficult For example,
it is not always possible to conduct interviews with every person to collect
required information. Similarly, using questionnaire or schedule for data
collection is not free from limitations, especially when the response to
questionnaire is very poor. In such occasions observation is more useful for
collecting data. There are occasions when no other method can be adopted
for data collection. For instance, suppose a scholar wants to study the life
style of a hill tribe. It is certainly not possible to use a questionnaire or
 schedule or conduct interview. Only alternative available is observation as
the respondents would not reply any question orally or in written.
 . Observation may be defined as, "sensible application of sense organs in
understanding less explained or unexplained phenomena."

Types of Observation:
1. Structured observation : When observation takes place strictly in accordance
with a plan or a design prepared in advance, it is called structured observation. In
such a type, the observer decides what to observe, what to focus on, what type of
information or activity should be given importance who are all to be observed,
what conditions are to be fulfilled to carry out observation, etc. in advance. He
sticks to these decisions when he observes.
Advantages:
a) filtering what is relevant and focusing on it,
b) avoiding waste of time
c) studying only the target group
d) Minimizing the bias of the observer and
e) Eliminating any scope for vagueness.
Disadvantages:
a) Unless a person is well trained he cannot be effective in undertaking
structured observation,
b) It is possible that vital aspects are missed, as they were not conceived at
the time of designing the observation.
c) By limiting the independence of the observer, crucial things might be left
out from being observed.
2. Unstructured observation: In this type of observation, there is no advance
designing of what, how, when, who, etc., of observation. The observer is given the
freedom to decide on the spot, to observe everything that is relevant. For example,
while observing the life style of a hill tribe in their place, the observer may be able
to observe several interesting things like how they discuss their plans, how they
entertain themselves, how they train the youngsters, how they settle quarrels, who
takes decision, etc. Some these may not be observed if structured observation is
adopted. The main strength of the unstructured observation is that at the time of
observation everything is taken note of and the researcher then segregates the
related and relevant details. Of course, one important quality required of the
observer is that he should be well trained and experienced.

3. Participant observation : In this method, the observer is very much present

in the midst of what is observed. For example, suppose a researcher is studying the
life style of a hill tribe, then he might understand the life style of the tribe better
only when he stays with them. By being present on the spot, he would be able to
continuously observe and note everything that is happening around him. But he
may not interfere with anything that is happening. He is a participant in the sense,
he is physically present on the spot to observe and not influencing the activities.
Similarly a journalist may be present on the site where an earthquake had
happened. He might only take photograph or photographs what he sees apart from
noting several other actions of people on the spot, but not directly or indirectly
participate in anything.
Merits:
1. The observer will not miss anything which is relevant,
2. There is every scope for him to clarify things which he cannot understand,
3. He can interact with people to get more information.
4. There is no need to depend upon hearsay or reported information.
Demerits :
1. An inexperienced observer may not know what is relevant and what is not
relevant,
2. He tends to focus more on things of interest to him, than what is relevant,
3. There is lot of scope for his bias to intervene in his interpretation of what
is observed,
4. The conduct or behavior or reaction of the target audience may be
influenced by his presence.

4. Non-participant observation : This is a method in which the observer remain

detached from whatever is happening around and does not involve himself in any
activities taking place. He is present only to observe and not to take part in the
activities. Sometimes he may even remain anonymous. That is, the target audience
does not know his presence at all. For example, the plain clothes men policemen
not in uniform) are deputed on observation duty whenever a processing takes place
or whenever any important political personality participate in the public meeting or
a place where a murder is committed. The object of such action is only to notice
what is happening not to be involved in what is happening. The most important
strength of this method of observation is that the observer would collect first hand
information without being noticed or influenced by any one. If the observer is
honest and sincere, then, the data collected through such observation is very
valuable.

5. Controlled observation : This is a slightly modified version of unstructured

observation. In this case, the observer performs his work in an environment or
situation, which is very much planned or designed or set. For example, sometimes
to test the effectiveness and alertness of airport security system, a mock event [like
hijacking or fire accident is carried out. Then how the security staff reacts to such
mock event observed. Based on this the weaknesses in the system are noticed and
steps taken to eliminate them.

6. Uncontrolled observation: This method is a modified version of unstructured

observation. No attempt is made to intervene the naturalness of the environment or
situation. The observer is at freedom to observe whatever is taking place around
him in the natural set up. For example, an animal lover may like to watch the
conduct and behavior of the animals in their natural habitat. Their behavior is
controlled in a zoo or a sanctuary but they are free in a forest. Some of the serials
shown in Discovery channel are filmed in the natural setting where animals live.
This helps to understand the natural behavior of animals.

Merits of observation method of data collection:

1. If observation is done correctly, the scope for bias is very much minimized.

2. Through observation, the current scenario in which anything is happening is

noticed and explained. There is no interpretation of how things would have
happened in the past or will happen in future, etc.

3. As there is no need to get any reply or details from the respondents, observation
does not require any cooperation of the respondents.

4. This is a fairly reliable method, provided the observer is well experienced,

trained and sincere.

5. Whenever respondents are illiterate or incapable of answering any question, [due

to language barrier or cultural background, etc), observation is the only method of
data collection available.

Limitations of observation :
1. This is a relatively costly method of data collection, because the observer
has to be present on the spot to observe whatever is happening . Further training an
observer is the additional cost to be incurred.

2. The scope for the bias of the observer interfering in what is observed and
understood is high.
3. It could be noticed that what is observed may bring out only part of the facts,
while data collected through questionnaire or interview ensure better coverage.

4. Sometimes, it may not be possible to observe what is targeted. This may be due
to the difficulty in reaching such people or spot.

5. There is a lot of scope for the observer to get distracted or influenced by

unexpected factors which would affect the accuracy of information collected.

6. A very important limitation is that only the observer can effectively establish
link among whatever he has observed to give a meaningful interpretation. Based on
his report nobody else can give satisfactory interpretation. Therefore, the ability to
relate things and interpret them intelligently is a quality expected of an observer.

How to make Observation Successful :

1. First the researcher should have a clear grasp of what he should observe and the
purpose or objectives of such observation

2. The person should be trained in adopting observation method of data collection.

3. The person should avoid any of his personal likes and dislikes intervene in the
process of observation.

4. Unless the observer is alert and intelligent he might ignore important things.

5. The observer should be able to convince his target audience the need and
importance of what is observed.
6. Unless an observer is able to relate various things seen or heard or felt, he may
not be able to give a satisfactory explanation for what is observed. So he should be
a person of analytical and critical nature.

Before concluding, it should be noted that observation alone may not be useful in
collecting data. If it is combined with other methods of data collection like
questionnaire / schedule method or interview method, it would help to make data
collection comprehensive.

Prerequisites for using Questionnaire in the Process of Data Collection:

Every researcher should keep in consideration the following points while using
questionnaire for data collection.
1. The scope of the survey should be clearly determined in advance. This will help
to determine the segment of informants or respondents from whom the information
should be collected
2. The purpose of the survey must be established and stated in the questionnaire
3. The researcher should prepare the draft questionnaire and revise it until it is fit
for the purpose of enquiry.
4. Follow up arrangement after despatching the questionnaire should be planned in
advance.
5. Maintenance of list of respondents, to whom the questionnaire is sent, is
necessary
6. Whether to use structured or unstructured questionnaire is an importan decision
to be taken.
7. Time frame for different activities connected with the questionnaire like
preparation of questionnaire, its finalization, printing, collecting list of respondents
and their addresses, despatch and follow up, etc.

Mechanics of Questionnaire Construction Questionnaire or Features of a

good questionnaire:
The following are the points to be given importance while designing a
questionnaire:

1. Questionnaire should be printed / cyclostyled / Xeroxed

2. The first part of the questionnaire should specify the object or purpose for which
the information is required.
3. An assurance to the respondent that the information furnished would be kept
confidentially must be given.
4. Some introduction about the person / organization who is collecting the
information is to be given. Sometimes, this is given as a letter enclosed with the
questionnaire,
5. Questions should be constructed using simple language and technical jargon,
terms, concepts should all be avoided.
6. Questions should never be lengthy. It is wiser not to combine a number of
questions in one question itself.
7. Each question should be specific and clear.
8 Personal questions on wealth, habits, etc. could be avoided.
9. Questions should be given in a sequence. [For example, Question relating to
marital status should precede the question about the number of children]
10. Questions should not require any referencing before replying.
11. Questions should not force the respondent to recall from his memory anything
to answer.
12. Questions needing computation/ calculation / consultation should be avoided
13 Questions on sentiment/ belief/ faith should be avoided
14. Repetition of question should be eliminated.
15. In case of any instruction is required for filling up the questionnaire, such
instructions should be given separately specifying the question number and the
related instructions. For example, the Application form for University
Examination, is given with instructions sheet regarding fees to be paid, mode of
payment, subject code, etc.
16 Sufficient space should be given for answering questions
17. The questionnaire should be made attractive, as otherwise, the respondents may
not be motivated to answer
18. If any diagramme or map is used then it should be printed clearly
19. Questions, which, cross check the response, could be built in to the
questionnaire
20. Instructions regarding how to return the filled up questionnaire must be given.
It is desirable that a self-addressed sufficiently stamped envelope is sent along with
the questionnaire to enable the respondents to send the filled up questionnaire.

Pre-testing & Questionnaire (or) Pilot study

It is often suggested that before a questionnaire is finalised, it should be field-
tested. That is, after the questionnaire is drafted, to decide whether it is
comprehensive or not, it is used with a few respondents. Their responses are
studied to determine the need for restructuring the questionnaire, re-sequencing the
questions, addition or deletion of questions, giving more instructions for filling up,
etc., can also be decided. Further, the pilot study will bring to light the weaknesses
of the questionnaire. Based on the pre-test necessary modifications in the
questionnaire can be made and then it could be released for use.
2. Secondary Data:
It has been already explained that secondary data refers to use of information
already collected and published or unpublished. Such a source is used to save time
and cost in compiling the data relating to the past. Further there is no possibility of
collecting any data of the past for the first time. So this source is used for
collecting the historical data. There are several methods of collecting the data and
these are discussed below.

a) Book : This refers to the published documents like books. The data
contained in standard books published in the past give very valuable
 information. But there are occasions when data published by different books
differ, causing confusion among the people compiling data.
b) Periodicals or journals: This is one of the very valuable source of
information. While books may deal with historical information, periodicals
contain articles and abstracts which provide the latest information. The
current thinking on any aspect is brought out through such publications.
c) Research thesis and dissertations: This is another useful source of
secondary data . But while using this source, the scholar should be careful to
study the objectives of the thesis being referred. It should also be
remembered that thesis submitted in the distant past may be used only for
understanding the relationship but not for replication.
d) Bibliographies: These are alphabetically arranged list of useful publications
with details about the year of publication, author, title, etc. This may serve as
a source of information to locate and access the information relevant to the
work being done.
e) Foot notes: At the end of each page of any published material, foot notes are
given. These notes would throw light on the source of information. By
tracing this source, original information and additional facts may be
available.
f) Encyclopedia: This is a publication where every useful information is
presented with authority, supported by diagrammes and facts. This will give
an authentic base for any fact being used in the research study. Several
standard encyclopedia are available and the scholar may refer them for
reliable information.
g) Statistical data source : Several organization publish at regular intervals
compiled statistical data on various aspects. For example, Statistical Hand
Book, United Nations Statistical year book, Demographic year book, Census
publications, etc., compile, classify and present codified statistical
information on various aspects. Use of authentic source of statistical data
would add to the quality of the research work.
h) Directories and Year Books: This is another source of secondary data in
which specific and focused information is available. For example, in
Kothari's Directory of Industries give reliable data industry-wise in India
every year. Year books are published by various agencies giving details
about the current status of various things. Examples : Manorama Year Book,
India - an Year Book, etc

But the problems in using the secondary data source are

1. Data reliability: This is one of the basic problems. The reliability or authenticity
of the data published has to be checked. Unfortunately, even among the official
sources, differences are found in data provided. So while using secondary data the
following questions relating to reliability are to be raised : Who publish the data ?
What is the source of information for the publisher ? Is the data up to date? How
were the data compiled using scientific method or not? What is the level of
accuracy claimed by the publisher and what is the accuracy level desired ? etc

2. Suitability of the data: Sometimes the data may be available, but it may not be
suit the purpose of the study on hand. For example, RBI bulletin published data
regarding Foreign Investment. Before 1997, no break up of the Foreign investment
used to be given. But after 1997, the portfolio component and the Direct
investment component of the Foreign investment is given. A scholar working on
the Foreign Direct Investment will feel handicapped in the absence of specific data.
Though data are available, they are not suitable for the study.

3. Adequacy of data : Sometimes, a researcher may require weekly data of foreign

direct investment. Though data regarding foreign direct investment is available, it
is certainly not available week wise. So data adequacy is not met. On the other
hand, Price quoted in Indian stock exchanges for various scrips are available on a
daily basis. This could be used for undertaking any study requiring daily data.

4. Continuity of data: This another problem using secondary data. For example, the
format used for providing some data may not be consistently followed by the
source. Depending upon the page constraints or availability of material, the data
presentation in a format is decided. So frequent change in the format would only
add to confusion to the people using the data from such sources.

Selection of Appropriate Method of Data Collection:

Having discussed various aspects about compilation of data for research, the
question to be answered is 'Which method of data collection should be adopted?
There is no standard answer for this question. The answer depends on a number of
factors, which are discussed below:
1. Nature, scope and object of the data collection: Elsewhere it was pointed out
that if the objectives of the study are clear, the type of data to be collected
could be easily determined. If the research topic is of current nature like
Impact of earthquake in Gujarat. Then primary data is the automatic choice.
Suppose the topic is the pattern of Foreign trade in India. To get a clear
 picture over the past few decades, historical data (i.e., secondary data]
should be used.

2. Budget constraints: With liberal availability of funds, primary data could be

the choice. Otherwise, secondary data is to be collected.

3. Availability of Time: The time frame fixed for the research work will
directly influence the choice between primary and secondary data. If
sufficient time is available, the researcher could probe into the past with
secondary data and capture the present using primary data.

4. Degree of accuracy desired: A very important condition is the level of

accuracy of the data collected. In case of compilation of data regarding the
deviation from the standard measurements in a work shop, the data should
be cent per cent accurate. Similarly the data regarding the patient condition
explained through various parameters, should be very accurate .On the other
hand, data required for a social research on Poverty, even 95 % accuracy is
acceptable. So greater the level of accuracy wanted, primary data should be
selected.

5. Period of study : A study based on historical data require secondary data

source while the study on the patient status in a hospital require primary data.

Other methods

d) Feedback form: In the case of some of the consumer goods, the supplier or the
manufacturer send the product along with a pre-paid reply cover in which
questions on the product and its usage are raised and the customer is requested to
fill it up and send. Based on this the first hand information about the product from
the consuming public is obtained.

e) Sales force opinion: On several occasions, the manufacturers or distributors

collect information about the movement of the product or market size, market
share, purchasing pattern, etc. through the sales force on the field. The sales men or
representatives visit the distributor or the retailer's shop to note down the details of
stock movement availability of items,etc., which give valuable information.

f) Panty audit : In this method, the investigators stay at the consuming point and
observe the purchasing behavior or the people. From this very valuable
information like the price response, quality consciousness, response to prize
incentive schemes, who takes buying decision, credit facility required, etc;All these
will influence the marketing strategy of the organization concerned.

g) Consumer panels : The consumer panel refers to an arrangement with select

consumers to maintain details of their consumption behavior in their diaries.
Based on these recorded information, useful first hand information is collected
about the product and behavior of the consuming public.

h) Collection through mechanical devices: There are several shopping

establishments where hidden video cameras are positioned at vantage points. This
are used for observing the public inside the shop. Apart from helping to eliminate
pilferage and theft, they provide very useful information on the consumers and
their preferences of products.

i)Projective techniques : This technique is adopted to study the consumers through

various methods like recalling advertisement theme, story completion tests,
quizzes, thematic apperception tests, etc. Through this technique it is possible to
compile information to be used as the basis for projecting the demand for the
product at different points of time.

j) Content analysis: In this method, the investigator would listen through various
audio visual records to obtain the required information. Of course, in this process,
what is already recorded by somebody for some purpose is used to cull out useful
information.