Module 3

Sampling
Sampling: Concepts- Types of Sampling - Probability Sampling – simple random sampling,
systematic sampling, stratified random sampling, cluster sampling -Non Probability Sampling–
convenience sampling- judgemental sampling, snowball sampling- quota sampling – Errors in
sampling.

Sampling – Meaning
 A sample is a subgroup of the population selected for participation in the study. Sample
characteristics, called statistics, are then used to make inferences about the population
parameters.
 The process of selecting sample for the purpose of research study is called sampling.

Concepts
Sampling is the process by which inference is made to the whole by examining a part.
a) Population
The collection of all units of a specified type in a given region at a particular point or period of time
is termed as a population or universe. Thus, one may consider a population of persons, families,
farms, cattle in a region or a population of trees or birds in a forest or a population of fish in a tank
etc. depending on the nature of data required.
b) Sampling Unit
Elementary units or group of such units which besides being clearly defined, identifiable and
observable, are convenient for purpose of sampling are called sampling units. For instance, in a
family budget enquiry, usually a family is considered as the sampling unit since it is found to be
convenient for sampling and for ascertaining the required information. In a crop survey, a farm or a
group of farms owned or operated by a household may be considered as the sampling unit.
c) Sampling Frame
A list of all the sampling units belonging to the population to be studied with their identification
particulars or a map showing the boundaries of the sampling units is known as sampling frame.
Examples of a frame are a list of farms and a list of suitable area segments like villages in India or
counties in the United States. The frame should be up to date and free from errors of omission and
duplication of sampling units.
d) Sampling and Non-sampling error
The error arising due to drawing inferences about the population on the basis of observations on a
part (sample) of it is termed sampling error. The sampling error is non-existent in a complete
enumeration survey since the whole population is surveyed.
The errors other than sampling errors such as those arising through non-response, in-
completeness and inaccuracy of response are termed non-sampling errors and are likely to be more
wide-spread and important in a complete enumeration survey than in a sample survey. Non-
sampling errors arise due to various causes right from the beginning stage when the survey is
planned and designed to the final stage when the data are processed and analyzed.
Distinction between Census and Sampling
 A census involves a complete enumeration of the elements of a population. A sample, on the
other hand, is a subgroup of the population selected for participation in the study.
When is a Census Appropriate?
1. A census is appropriate if the size of population is small. For eg. A researcher may be
interested in contacting firms in iron and steel industry. These industries are limited in
number, so a census will be suitable.
2. Sometimes, the researcher is interested in gathering information from every individual. Eg.
Quality of food served in a mess.
When is Sample Appropriate?
1. When the size of population is large.
2. When time and cost are the main considerations in research.
3. If the population is homogeneous.
4. Circumstances when a census is not possible. Eg. Reactions to global advertising by a
company.
Characteristics of a good sample design
 True representative of the whole population.
 Appropriate sample size
 Sample should be chosen properly by appropriate sampling technique.
 A perfect mix of all the population elements.
Types of sampling

sampling

non-
probability
probability
sampling
sampling

probability
sampling

simle random systematic stratified cluster

sampling sampling sampling sampling
 non-
probability
sampling

convenience judgement snowball quota

sampling sampling sampling sampling

 Probability sampling – Every unit in the population has equal chances for being selected
as a sample unit. The sampling units are selected by chance and no biasness is involved,
 Non probability sampling – The units in the population have unequal or negligible
chances for being selected as a sample unit. Sampling relies on the personal judgment of the
researcher rather than chance to select sample elements. The researcher can arbitrarily or
consciously decide what elements to include in the sample.

Probability sampling Non probability sampling

Every individual has a known and equal chance It is associated with an individual being selected
of being selected
Refer to both sample as well as population. Sample frame is not developed
Sampling frame is used
Parametric tests are mostly used Non-parametric tests are preferred
A sample is more representative of population Nothing definite can be said about the
characteristics representativeness of non-probability sampling

Classification of Sampling Techniques

1. Probability Sampling Techniques
 Simple Random Sampling: a simple random sample is defined as one in which each
element of the population has an equal and independent chance of being selected. Each
element in the population has a known and equal probability of selection. This implies that
every element is selected independently of every other element. The sample is drawn by a
random procedure from a sampling frame. It can be drawn through either of the 2
procedures
Lottery system – Take a population containing four departmental stores: A,B, C & D.
Suppose we need to pick a sample of two stores from the population. We write down all
possible combinations AB, AC, AD, BC, BD, CD on pieces of papers and fold the pieces. Put
them in a box. Mix them and pull one at random.
Random number tables
  Stratified Random Sampling – It is a two-step process:
1. Population to be sampled is divided into groups or strata. The strata should be mutually
exclusive and collectively exhaustive, i.e. every population element should be assigned to
assigned to one and only one stratum and no population elements should be omitted. Strata
are more or less equal on some characteristics.
2. Elements are selected from each stratum by a random procedure.
It may be noted that stratification does not mean absence of randomness. All that it means is that
the population is first divided in to certain strata and then a simple random sample is selected with
in each stratum of the population.
Stratified sampling is of two types:
1. Proportionate stratified Sampling –
2. Disproportionate stratified Sampling –
Proportionate stratified Sampling
The number of sampling units drawn from each stratum is in proportion to the population size of
that stratum.
Ex- in a college there are total 2500 students out of which 1500 are girls and 1000 are boys. If a
sample of 100 is to be chosen, then the number of girls should be 60 and boys should be 40.

Disproportionate stratified Sampling

The number of sampling units drawn from each stratum is based on analytical consideration, but
not in proportion to the size of the population of that stratum.
Ex- in a college there are total 2500 students out of which 1500 are girls and 1000 are boys. If a
sample of 100 is to be chosen, then the number of girls should be 50 and boys should be 50.

 Systematic Sampling – is chosen by selecting a random starting point and then picking
every nth element in succession from the sampling frame. There are three steps:
1. Sampling interval n is determined by the following formula:
n = No. of units in the population / No. of units desired in the sample
2. One unit between the first and nth unit in the population list is randomly chosen.
3. Add nth unit to the randomly chosen number.
Example – Consider 1000 households from which we want to select 50 units.
Calculate K = 1000/50 = 20
To select the first unit, we randomly pick one number between 1 to 20, say 17. So our
sample begins with 17, 37, 57 …… Only the first item is randomly selected and rest are
systematically selected.

 Cluster Sampling –
Instead of selecting individual units from the population, entire groups or cluster are selected at
random.
The following steps are followed:
1. The population is divided into mutually exclusive and collectively exhaustive clusters.
2. A simple random sample of few clusters is selected. For each selected cluster, either all the
elements are included in the sample or a sample of elements is drawn probabilistically.
 3. All the units in the selected cluster are studied.
4. Suppose a business firm, engaged in the manufacture of sports goods is interested to know
the changing patterns of family expenditures for recreation in a metropolitan city.
5. It may divide the total area of interest into as number of smaller area or blocks . A number
of these blocks can then be selected by using random numbers.
6. It can then collect the requisite information from all samples of the families residing in
these blocks.
Stratified Sampling Cluster Sampling

Population is divided into a few subgroups Population is divided into many subgroups,
each having many elements each having a few elements
Homogeneity with in the subgroups and Heterogeneity within subgroups and
Heterogeneity between subgroups Homogeneity between subgroups.
Elements are randomly selected from within Few subgroups are randomly selected and then
each subgroup all elements within those subgroups are
covered in the study

Advantages of Probability Sampling

 It is unbiased.
 Quantification is possible in probability sampling.
 Less knowledge of universe is sufficient.
Disadvantages of Probability Sampling
 It takes time.
 It is costly.
More resources are required to design and execute than in non-probability design

2. Probability Sampling Techniques

 Convenience sampling: in this the researcher has the freedom of choosing any respondent
based on his convenience. Respondents become a part of the sample because they happen
to be at the right place in the right time.
Examples:

1) Use of students, church groups and members of social organizations,

2) Mall respondents,

3) Department stores,

4). People on street interviews.

 Least expensive and least time-consuming of all sampling techniques.

 Selection bias and samples are not representative of any definable population
 Judgement sampling: It is a form of convenience sampling in which the population
elements are selected based on the judgment of the researcher. The researcher exercising
judgment or expertise, chooses the elements to be included in the sample, because he or she
believes that they are representative of the population of interest or are otherwise
appropriate.
Common examples of judgmental sampling include
1) Test markets selected to determine the potential of a new product,
2) Purchase engineers selected in industrial marketing research because they are
considered to be representative of the company
 Snowball sampling: An initial group of respondents is selected, usually at random. After
being interviewed, these respondents are asked to identify others who belong to the target
population of interest. Subsequent respondents are selected based on the opinion or
referrals provided by the initial respondents. This process may be carried out in waves by
obtaining referrals from referrals, thus leading to a snowballing effect.
Ex: 1. Special census groups such as Unmarried males under 35
2. College students bring in more students on the consumption of Pepsi.

 Quota sampling: It involves the fixation of certain quotas, which are to be fulfilled by the
interviewers. It involves two stages:
1. The first stage consists of developing control categories, or quotas of population elements. To
develop these quotas, the researcher lists relevant control characteristics and determines the
distribution of these characteristics in the target population. The control characteristics include
gender, age and race.

2. In the second stage, Sample elements are selected based on convenience or judgment.

Ex: Suppose 200, 000 students are appearing for a competitive examination. We need to select
1% of them based on quota sampling. The classification of quota may be as follows:

Category Quota
General Merit 1000

Sport 200
NRI 100
OBC 400
SC/ST 300
Steps in Sampling Design Process

Define the target population

Determine the sampling frame

Specify the sampling unit

Selection of sampling method

Determine the sample size

Execute the sampling process

1. Define the target population – The target population is the collection of elements or
objects that possess the information sought by the researcher and about which inferences
are to be made. The target population should be defined in terms of elements, sampling
units, extent and time.
An element is the object about which or from which the information is desired.
A sampling unit is an element or a unit containing the element, that is available for selection at
some stage of the sampling process.
Suppose that company wanted to assess consumer response to new line of soft drink and wanted to
sample males over 18 years of age. Here the sampling unit would be households and all males
over 18 in each selected household would be population element.
Extent refers to the geographical boundaries, and the time factor is the time period under
consideration.
For eg., For a study of Departmental Store:
Elements : male or female head of the household responsible for most of the shopping at
Departmental stores
Sampling units : households
Extent : Bangalore City
Time : 2011
2. Determine the Sampling Frame : A sampling frame is a representation of the elements of
the target population. It consists of a list or set of directions for identifying the target
population.
 Examples of a sampling frame include the telephone directory, an association directory
listing the firms in an industry, a mailing list purchased from an organization, a city
directory or a map.
Ex: You want to learn about scooter owners in a city. The RTO will be the frame which
provides you names, addresses and the types of vehicles possessed.
3. Specify the Sampling Unit – Individuals who are to be contacted are the sampling units. If
retailers are to be contacted in a locality, they are the sampling units.
4. Selection of sampling method – The researcher must decide whether to use Bayesian or
traditional sampling approach, to sample with or without replacement, and to use non
probability or probability sampling.
In probability sampling technique, sampling units are selected by chance. There is no biasness
involved at the time of selecting the sample and each element is getting a fair chance to be a part of
the sample.
In non- probability sampling technique, the sample is selected based on personal judgment of
the researcher and not chance. Thus some biasness is involved.
5. Determine the sample size – Sample size refers to the number of elements to be included
in the study. The sample size depends upon the type of study that is being conducted. If it is
an exploratory research, the sample size will be generally small and for descriptive
research, the sample size will be large. The sample size also depends on the resources
available with the company. It depends on the accuracy required in the study and the
permissible errors allowed
6. Execute the sampling process – A detailed specification of the sampling design decisions
with respect to the population, sampling frame, sampling unit, sampling technique and
sample size are to be implemented. If households are the sampling unit, an operational
definition whether household includes husband or wife or both, and procedure should be
specified if household is not available whether to call back or eliminate it from the sample.

Errors in sampling

total error

non-sampling
sampling error
error

non-response
biased error unbiased error responce error
error

Researcher Interviewer Respondent

error error error
The research project can get affected by errors arising due to various reasons. The errors in the
sampling procedure can be classified as sampling error and non-sampling errors.

Sampling errors

The errors which are due to sampling and of which the average magnitude can be determined are
called sampling errors. The extent of sampling error depends on factors like the nature of the
universe; the techniques of sampling etc. sampling errors can be biased or unbiased.

a. Biased error arise due to any bias or prejudice of the researcher in selecting the
sample. Ex: use of convenience sampling technique introduces bias in the result. Bias
may arise due to any of the following 3 reasons
i. Faulty process of selection: it can be due to
1. Use of non-probability sampling techniques
2. Substitution of an item in the place of one chosen in the random sample
3. Non-response is another bias
4. Using biased questions
ii. Bias due to faulty collection of data: an inadequate sampling frame, a wrongly
defined population, wrongly defined sampling unit.
iii. Bias due to faulty analysis: choosing methods of analysis on convenience basis
rather than on suitability basis lead to bias.
b. Unbiased error: also called as random sampling error are due to chance difference
between the members of the population included in the sample and those not included.
o These are unavoidable errors which may be purely due to selecting an individual or
object randomly who may be high, low or average in the trait under consideration.
o Biased error can be reduced by increasing the size of the sample.

Non-sampling errors

Arise due to reasons other than sampling, like error in scales, instruments, data collection, editing,
coding or tabulation. These errors would occur in sampling as well as census survey.

These errors are of 2 types. That is response error and non-response error.

a. Response error: these errors occur when the respondent give inaccurate answers or their
answers are not recorded properly. Response error can be accounted to 3 sources.
i. Researcher error: a researcher can introduce a error by recording wrong
information that does not suit the purpose. They may use a faulty scale of
measurement, define the population wrongly, develop an incorrect sampling frame
or use inappropriate statistical procedures.
ii. Interviewer error: these errors occur when the interviewer select respondents
other than those specified in the sampling design. They may ask questions in the
wrong manner and further introduce errors due to faulty hearing, interpreting and
recording the respondents answer.
iii. Respondent error. Such error occurs due to respondents activities. One reason
could be that the respondent may be unable to provide correct answers because of
 any reasons like lack of knowledge, fatigue, shyness etc. respondents may also
deliberately provide wrong answers to cover embarrassing questions or provide
socially correct answers.
b. Non-response error: they arise when some of the respondents do not respond. The
general impact of non-response is that it alters the size and composition of original sample.
Non-response can be due to failure in locating the respondents or their unwillingness to
respond or because they lack the information desired. These errors tend to introduce bias
in the research result.

Minimization of Sampling Errors

 The only way to guarantee the minimization of sampling error is to choose the appropriate
sample size. As the sample keeps on increasing the sampling error decreases.

 Increasing the sample size does decrease sampling error , but it may also increase non
sampling error by increasing interview errors