MODULE 3

SAMPLING AND DATA

COLLECTION

NAVYA NINAN
SAMPLING

Meaning of Sampling
Sampling is the process of obtaining relevant
information and making inferences about a population
by analysing a small group of people within the
population for the purpose of a research.

Population
Population is the collection of the elements on which
you are required to analyze and draw a conclusion.
The population includes all the items under
consideration for the particular case study and is
usually very large. Population is generally denoted by
the Greek letter Sigma ( σ)
Sample: A portion of the population which is analysed during a study. It represents all the features or
characteristics of the entire population.

Sampling unit: One item of a sample

Sampling frame: A list of elements from which a sample may be drawn; also called as the working
population

Sampling design: A plan for obtaining a sample out of a given population

Ways in which information can

be obtained for sampling

Census Sample
survey survey

Sample size: The total number of observations that form a sample. An ideal size must be:
• optimum
• representative
• reliable

Sampling error: arise as we study only a small portion of the entire population
Need for Sampling

1. Economy of time.
2. Economy of money.
3. True detailed knowledge.
4. Utility in experimental study.
5. It has reliability because it is based on probability theory.
 Assumptions of sampling
1. Homogeneity amidst complexity:
Social phenomenon is very complex in nature and every unit appears to be different from
another.
But at the same time they also possess similarities in many respects.
It is, therefore, assumed that there is the possibility of such representative types in the whole
population that makes sampling possible.

2. Possibility of Representative Selection:

Sampling has its origin in the mathematical theory of probability and law of statistical
regularity.
The law of statistical regularity lays down that a group of objects chosen at random from a
large group tend to possess the characteristics of that large group (universe)

3. Absolute accuracy not essential

But relative or significant accuracy i.e. needed in case of large scale observations.
Because it is practically impossible to achieve because of errors in measurement, collection
of data , its analysis, interpretation.
Essentials of an Ideal Sample

•Homogeneity: The units included in sample must be as likeness

with other units.

•Adequacy: A sample having 10% of the whole data is adequate.

•Independence: Every unit should be free to be included in the

sample.

•Representativeness: An ideal sample must be such that it

represents the whole data adequately.
Advantages of Sampling

1. It has a greater adaptability.

2. It is an economical technique.
3. It has high speed for generalization.
4. It has greater precision and accuracy in the observation
5. This technique has great accuracy.
6. It has a greater speed in conducting a research work.
7. It has a greater scope in the field of research.
8. It reduces the cost of observation or data collection.
Disadvantages of Sampling

1.Scope of biasness.(Less accuracy)

2.Problem of representative sample-Difficulty in selecting a truly
representative sample.
3.Need of eligible researchers.
4.Instability of sample subjects or changeability of units i.e. in
heterogeneous population.
Characteristics of a good sample
1. A good sample is the true representative of the population corresponding to its
properties.
2. The population is known as aggregate of certain properties and sample is called
sub-aggregate of the universe.
3. A good sample is free from bias; the sample does not permit prejudices, the
learning and pre-conception, imaginations of the investigator to influence its choice.
4. A good sample is an objective one; it refers objectivity in selecting procedure or
absence of subjective elements from the situation.
5. A good sample maintains accuracy .It yields an accurate estimates or statistics
and does not involve errors.
6. A good sample is comprehensive in nature. This feature of a closely linked with
true-representativeness. Comprehensiveness is a quality of a sample which is
controlled by specific purpose of the investigation. A sample may be comprehensive
in traits but may not be a good representative of the population.
7. A good sample has the practicability for research.
TYPES OF SAMPLING DESIGNS/
METHODS OF SAMPLING
 PROBABILITY METHOD NON-PROBABILITY METHOD

It is a method of sampling which gives the probability that a In the absence of any idea of probability the method of
sample is representative of population. sampling is known as non-probability sampling.

Probability sampling is generally used in fundamental It is generally used in action researches in which one studies a
research in which the purpose is to generalize the results. class without any generalization purpose.

It refers from the sample as well as the population. There is no idea of population.

Every individual of the population has equal probability to be There is no probability of selecting any individual.
taken into the sample.

It may be representative of the population. It has free distribution.

Its observations (data) are used for the inferential purpose. The observations are not used for generalization purpose.
Inferential or parametric statistics are used.
Non-inferential or non-parametric statistics are used.
There is a risk of drawing conclusion. There is no risk for drawing conclusions.
It is based on Law of probability sampling i.e. Law of Statistical
Regularity and Law of Inertia of the Large Sample. It is not based on law of probability sampling.
 Sampling methods

Probability Sampling Non-probability Sampling

Incidental/
Random Systematic Stratified Multi -stage Cluster Judgment Quota Purposive Snowball
accidental
Sampling Sampling Sampling Sampling Sampling Sampling Sampling Sampling Sampling Sampling
PROBABILITY SAMPLING
METHODS
 Probability Sampling Methods

(1) Simple Random Sampling

It is one in which each element of the population has an equal and

independent chance of being included in the sample i.e. a sample
selected by randomization method is known as simple random
sample and this technique is simple randomizing.

Randomization is done by using the following techniques:

(a) Tossing a coin
(b) Lottery method
(c) Tippett’s table method
(d) Throwing a dice
(d) Blind folded method
Merits of Randomization:
1. It requires the minimum knowledge of population.
2. It is free from subjectivity and free from personal error.
3. It provides appropriate data for one’s purpose.
4. The observations of the sample can be used for inferential
purpose.

Demerits of Randomization:
1. It cannot ensure the representativeness of a sample.
2. It does not use the knowledge about the population.
3. Its inferential accuracy depends upon the size of the sample.
(2) Systematic Sampling

•Systematic sampling is an improvement over the simple random sampling.

•This method requires the complete information about the population.
•There should be a list of information of all the individuals of the population in
any systematic way.
Merits:
1. This is a simple method of selecting a sample.
2. It reduces the field cost.
3. Inferential statistics may be used.
4. Sample may be comprehensive and representative of population.
5. Observations of the sample may be used for drawing conclusions and
generalizations.

Demerits:
1. This is not free from error, since there is subjectivity due to different
ways of systematic list by different individuals.
2. Knowledge of population is essential.
3. Information of each individual is essential.
4. This method can’t ensure the representativeness.
5. There is a risk in drawing conclusions from the observations of the
sample.
(3) Stratified Sampling

•Simple random sampling is the most appropriate when the entire population from which the
sample is taken is homogeneous.
•Stratified sampling techniques are generally followed when the population is heterogeneous
and where it is possible to divide it into certain homogeneous sub-populations, which are
called strata.
•The strata differ from one another but each is homogeneous within itself.
•The units are selected at random from each of these strata.
•The number of units selected from different strata may vary according to their relative
importance in the population.
•The sample, which is the aggregate of the sampled units of each of the stratum, is called a
stratified sample and the technique of drawing this sample is known as stratified sampling.

Allocation of Sample in Different Strata

•For management purposes the most effective utilization of resources is achieved if the
variance of the estimator is minimized for a fixed budget or the cost of sampling is minimized
for a fixed variance of the estimator.
•Keeping in view the stratum size, the variability within stratum and the cost per observation
the techniques of proportional allocation and optimum allocation are commonly used.
(a) Proportional Allocation:

•In this procedure the number of sampling units ni allocated to the i-th stratum is proportional to the
number of units in the population.

•Proportional allocation is an efficient and suitable design when the cost of selecting a unit is equal
for each stratum and there is no difference in within stratum variance.
(b) Optimum Allocation:

Let Ci be the cost of sampling one unit from the i-th stratum having variance σi2 . Assuming σi2
to be known, ni is given by

Thus, the sample size would larger if

i) the stratum size is larger
ii) stratum variance is larger
iii) The sampling cost in the stratum is lower
Merits:
(i) It is a good representative of the population.
(ii) It is an improvement over the earlier technique of sampling.
(iii) It is an objective method of sampling.
(iv) Observations can be used for inferential purpose.

Demerits:
(i) Serious disadvantage of this method is that it is difficult for the researcher to decide
the relevant criterion for stratification.
(ii) Only one criterion can be used for stratification, but generally it seems more than
one criterion relevant for stratification.
(iii) It is costly and time consuming method.
(iv) Selected samples may be representative with reference to the used criterion but
not for the other.
(v) There is a risk of generalization.
(4) Cluster Sampling

To select the intact group as a whole is known as a cluster sampling.

In cluster sampling the sample units contain groups of element (cluster)
instead of individual members or items in the population.

Rather than listing all elementary school children in a given city and
randomly selecting 15 % of these students for the sample, a researcher lists
all of the elementary schools in the city, selects at random 15 % of these
clusters of units, and uses all of the children in the selected schools as the
sample.
Merits:

(i) It may be a good representative of the population.

(ii) It is an easy method.
(iii) It is an economical method.
(iv) It is practicable and highly applicable in education.
(v) Observations can be used for inferential purpose.

Demerits:

(i) Cluster sampling is not free from errors.

(ii) It is not comprehensive (all inclusive).
(5) Multi Stage Sampling

This sample is more comprehensive and representative of the population.

In this type of sampling primary sample units are inclusive groups and
secondary units are sub-groups within these ultimate units to be selected
which belong to one and only one group.

Stages of a population are usually available within a group or population,

whenever stratification is done by the researcher.

The individuals are selected from different stages for constituting the multi
stage sampling.
Merits:
(i) It is a good representative of the population.
(ii) Multistage sampling is an improvement over the earlier methods.
(iii) It is an objective procedure of sampling.
(iv) The observations from multi stage sample may be used for
inferential purpose.

Demerits:
(i) It is a difficult and complex method of sampling.
(ii) It involves errors when we consider the primary stages.
(iii) It is again a subjective technique of sampling.
NON-PROBABILITY
SAMPLING METHODS
(1) Incidental or Accidental Sampling

The term incidental or accidental applied to those samples that are taken
because they are most frequently available i.e. this refers to the groups
which are used as samples of a population because they are readily
available or because the researcher is unable to employ more acceptable
sampling methods.

Merits:
(i) It is very easy method of sampling.
(ii) It is frequently used method in behavioural sciences.
(iii) It reduces the time, money and energy i.e. it is an economical method.

Demerits:
(i) It is not representative of the population.
(ii) It is not free from errors.
(iii) Parametric statistics cannot be used.
(2) Judgment Sampling

This involves the selection of a group from the population on the basis of available
information assuming as if they are representative of the entire population.
Here group may also be selected on the basis of intuition or on the basis of the criterion
deemed to be self-evident.
Generally investigator should take the judgment sample so this sampling is highly risky.

Merits:
(i) Knowledge of investigator can be best used in this technique of sampling.
(ii) This method of sampling is economical.

Demerits:
(i) This technique is objective.
(ii) It is not free from errors.
(iii) It includes uncontrolled variation.
(iv) Inferential statistics cannot be used for the observation of this sampling, so
generalization is not possible.
(3) Purposive Sampling

The purposive sampling is selected by some arbitrary method because it is known to be

representative of the total population, or it is known that it will produce well matched groups.
The idea is to pick out the sample in relation to criterion which are considered important for
the particular study.
This method is appropriate when the study places special emphasis upon the control of
certain specific variables.

Merits:
(i) Use the best available knowledge concerning the sample subjects.
(ii) Better control of significant variables.
(iii) Sample groups data can be easily matched.
(iv) Homogeneity of subjects used in the sample.

Demerits:
(i) Reliability of the criterion is questionable.
(ii) Knowledge of population is essential.
(iii) Errors in classifying sampling subjects.
(iv) Inability to utilize the inferential parametric statistics.
(v) Inability to make generalization concerning total population.
(4) Quota Sampling

This combines both judgment sampling and probability sampling: on the basis of
judgment or assumption or the previous knowledge, the proportion of population falling
into each category is decided.
Thereafter a quota of cases to be drawn is fixed and the observer is allowed to sample
as he likes.
Quota sampling is very arbitrary and likely to figure in municipal surveys.

Merits:
(i) It is an improvement over the judgment sampling.
(ii) It is an easy sampling technique.
(iii) It is not frequently used in social surveys.

Demerits:
(i) It is not a representative sample.
(ii) It is not free from errors.
(iii) It has the influence of regional , geographical and social factors.
(5) Snowball Sampling

The term; snow ball sampling’ has been used to describe a sampling procedure in which the
sample goes on becoming bigger and bigger as the observation or study proceeds.
The term snowball stems from the analogy of a snowball sample which would allow
computation of estimates of sampling error and use of statistical test of significance.

For example, an opinion survey is to be conducted on smokers of a particular brand of

cigarette. At the first stage, we may pick up a few people who are known to us or can be
identified to be the smokers of that brand. At the time of interviewing them, we may obtain
the names of other persons known to the first stage subjects. Thus the subjects go on
serving an informant for the identification of more subjects and the sample goes on
increasing.

Merit:
Snowball sampling which is generally considered to be non-probabilistic can be
converted into probabilistic by selecting subjects randomly within each stage.
Demerits:
Sampling errors may creep in.
METHODS OF DATA
COLLECTION
What is data collection?
 It is the process by which the researcher collects the information needed to answer
the research problem
 The task of data collection begins after a research problem has been defined and
research design chalked out.

While collecting the data, the researcher must decide:

 Which data to collect?

 How to collect the Data?
 Who will collect the Data?
 When to collect the Data?
The selection of a method for collecting information depends upon

 Resources available
 Credibility
 Analysis and reporting
 Skill of the evaluator
 METHODS OF DATA COLLECTION

PRIMARY SECONDARY

Primary data are those Secondary data are those

which are collected for which have already been
the first time and are collected by someone else
original in character. and which have through
some statistical analysis.
Primary data collection methods

Primary Data may be collected through:

 Experiments
 Surveys (sample surveys or census surveys)
 Interviews
 Observation
 Questionnaires
 Schedules
 1. Observation
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.”
Steps in an effective observation

Determine what needs to be observed

Select participants (Random/Selected)

Conduct the observation - (venue, duration, recording

materials, take photographs )

Compile, Analyze and Interpret the collected data

 CLASSIFICATION OF OBSERVATION

Structured Controlled
Unstructured Uncontrolled
Observation Observation
Observation Observation
When the When
observation is When it takes Participant Non-Participant When the observation
place without Observation observation takes place
characterized by a Observation takes place in according to
careful definition of the above
When the natural pre arranged
the units to be characteristics When observer is
observer is condition i.e., plans, with
observed, the style observing experimental
member of the uncontrolled
of recording the people without procedure then
group which observation. It
observed giving any it is controlled
he/she is is done to get
information, information to observation
observing then spontaneous
standardized them then it is generally done
it is Participant picture of life
conditions of Non-Participant in laboratory
Observation. and persons. under
observation and the Observation.
selection of related controlled
condition.
data of observation.
Advantages of Observation

 Produces Large quantities of data.

 All data obtained from observations are usable.
 The observation technique can be stopped or begun at any time.
 Relative Inexpensive

Disadvantages of observation

 Interviewing selected subjects may provide more information, economically, than

waiting for the spontaneous occurrence of the situation.
 It is expensive method
 Limited information.
 Extensive Training is needed
2. Interview

 The Interview Method of collecting data involves presentation of oral-verbal stimuli and reply
in terms of oral- verbal responses.
 Interviewer asks questions (which are aimed to get information required for study) to
respondent.
Steps in an effective interview
Prepare the interview schedule

Select subjects/ key respondents

Conduct the interview

Analyse and interpret the data collected from the

interview
 CLASSIFICATION

 Structured Interviews : A set of predefined questions are asked.

 Unstructured Interviews : In this case, the questions are not pre-determined
 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 an individual’s life experience.
 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 selection of people for certain Jobs.
Advantages

 More information at greater depth can be obtained

 Resistance may be overcome by a skilled interviewer
 Personal information can be obtained

Disadvantages

 It is an expensive Method
 Interviewer bias
 Respondent bias
 Time consuming
3. Questionnaires
 A Questionnaire is sent ( by post or by mail ) to the persons concerned with a request
to answer the questions and return the Questionnaire.
 A Questionnaire consists of a number of questions printed in a definite order on a
form.
Steps in an effective questionnaire

Prepare questions
(Formulate & choose types of questions, order them, write instructions, make copies)

Select your respondents

Random/Selected

Administer the questionnaire

(date, venue, time )

Tabulate, analyze and interpreted data collected

 CLASSIFICATION

Open-ended questions Close-ended or fixed alternative questions

This gives the respondents the ability to This allows the respondents to choose
respond in their own words. one of the given alternatives.

Essentials of Good Questionnaire

 Should be short and simple
 Follow a sequence of questions from easy to difficult one
 Technical terms should be avoided
 Should provide adequate space for answers in questionnaire

 Directions regarding the filling of questionnaire should be given Physical Appearance – Quality of
paper, Color
 Sequence must be clear
Advantages
 Low cost –even when the universe is large and is widespread
 Free from interviewer bias
 Respondents have adequate time to think through the answers.
 Respondents who are not easily approachable, can also be reached
conveniently.
 Large samples can be used.

Disadvantages
 Time consuming
 The respondents need to be educated and cooperative
 This method is slow
 Possibility of unclear replies
4. Schedules

 Very similar to Questionnaire method

 The main difference is that a schedule is filled by the enumerator who is specially
appointed for the purpose.
 Enumerator goes to the respondents, asks them the questions from the Questionnaire
in the order listed, and records the responses in the space provided.
 Enumerator must be trained in administering the schedule.