100% found this document useful (1 vote)
26 views12 pages

MKT Res IINew

The document provides an overview of marketing research focusing on sampling methods, including definitions of population, census, and sampling. It outlines the advantages and disadvantages of both census and sampling methods, details the steps involved in sampling design, and describes various types of sampling techniques, including probability and non-probability sampling. Key considerations for effective sampling design are also highlighted, emphasizing the importance of representative samples and budget constraints.

Uploaded by

Abdul Khan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
100% found this document useful (1 vote)
26 views12 pages

MKT Res IINew

The document provides an overview of marketing research focusing on sampling methods, including definitions of population, census, and sampling. It outlines the advantages and disadvantages of both census and sampling methods, details the steps involved in sampling design, and describes various types of sampling techniques, including probability and non-probability sampling. Key considerations for effective sampling design are also highlighted, emphasizing the importance of representative samples and budget constraints.

Uploaded by

Abdul Khan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 12

MARKETING RESEARCH

Unit II

Sampling

Population
Population is a group of people (thing) which are having one or more similar characteristics.
Population is the total collection of elements about which we wish to make some inferences.

Population Element
A population Element is the subject on which the measurement is being taken.
It is the UNIT OF STUDY.

Census
A Census is when we collect data from all the elements in a population.

Advantages of Census Method


The advantages of Census Method are as follows:
 Information can be obtained from each and every unit of population and
 The research results are achieved with greater accuracy.

Conditions of Census Method


The conditions of Census Method are as follows:
 Census Method is feasible when the population is small and
 Census Method is necessary when the elements are quite different from each other.

Disadvantages of Census Method


The advantages of Census Method are as follows:
 Very costly,
 Time consuming and
 Requires lot of effort and energy.

Sampling
A sample is when we collect data by selecting some of the elements in population.
Sampling can be seen in our Day to Day Activity. For example when a House-Wife has to
check whether a Pot of Rice which she is cooking is ready or not, she picks few rice grains
and examines them. On the basis of these few rice grains she takes a decision whether the
whole of rice is cooked or not. So this is a sampling.

Advantages of sampling method


The advantages of Sampling Method are as follows:
 Reduction in cost
Sampling Method is having economic advantage because collection of information is from
selected units of population.
 Greater accuracy of results
Sampling Method is having greater accuracy of results because the sampling process has
better interviewing, better supervision and better processing with complete coverage. The
other reason can be that there are trained and experienced experts engaged in collecting
information from smaller number of units of population.
 Greater Speed of Data Collection
Sampling Method has greater speed of execution because it reduces the time between the
recognition of need for information and availability of that Information. This is due to smaller
number of units of population.
 Greater Depth of Information
Sampling Method provides more insight of limited units of population leading to more study of
that unit.
 Preservation of Units
Sampling Method can keep units of population stored for re-use purpose.

Sampling Design within the research process


A Sample Design is a definite plan for obtaining a sample from a given population. A sample
Design refers to the technique or the procedure the researcher would adopt in selecting
items for the sample. A sample Design lays down the number of items to be included in the
sample i.e. the size of the Sample. A sample Design is determined before the data are
collected.

Steps in Sampling Design


While developing a Sampling Design the researcher must keep in mind the following points:

1. Management-Research Question
Researcher makes several decisions when designing a sample. The sampling decisions flows
from two decisions made in the formation of Management – Research Question i.e. the nature
of the management question and the investigative questions which evolve from the research
question.
2. Type of Universe
The first step in developing any sample design is to clearly understand the type of universe.
The universe can be finite or in-finite.
In finite universe the number of items is certain like:
(a) Population of a city or
(b) Numbers of workers in a factory
In in-finite universe the number of items is not certain i.e. we do not have any idea about the
total number of items like:
(a) Number of stars in the sky,
(b) Number of hairs on head or

3. Define relevant population


The next step in the process of the sampling design is to define the relevant population i.e. to
decide and to choose the type of the population for the research study. It means to know the
characteristics of the population so that it can be easier for the researcher to have its
research. The population can be in the form of school teachers, college teachers or all the
teachers.

4. Sampling Unit
The second step is to decide about the sampling unit which is to be done before selecting the
sample. The sampling unit can be an individual or social unit like family, club and school or
construction unit like flat and house or geographical unit like village, district and state.
Researcher has to select one or more units for his study.

5. Source List
The source list is also known as ‘Sampling Frame’ from which sample is to be drawn.
If the universe is finite then it contains the name of all the items of the universe. If source list
is not available then the researcher has to prepare it. Source list should be comprehensive,
correct, reliable and appropriate. Source list should be the representative of the population.

6. Size of the Sample


The size refers to the number of the items to be selected from the universe for making a
sample. This is sometimes the major problem for the researchers. The size of the sample
should neither be too large nor too small but it should be optimum. The optimum sample is
one, which fulfills the requirements of efficiency, representativeness, reliability and flexibility.

7. Budgetary Constraint
Budgetary constraint means to know the available budget for the activity of the research. In
determining the sample design, the cost has major impact relating to the size of the sample
as well as on the type of the sample.

8. Sampling Procedure
Finally the researcher must decide the type of sample he will use i.e. he must decide about
the technique to be used in selecting the items for the sample.

9. Sampling Method
The sampling method means to know the type of the sampling to be taken for the research
study. The type of the sampling can be random sampling or non random sampling.

10. Draw the sample


Draw the sample means to know choose the sample by using any one sampling method and
by using any one technique in that method.
Sampling design within the research process

MANAGEMENT RESEARCH QUESTION

TYPE OF UNIVERSE

DEFINE RELEVANT POPULATION

SAMPLING UNIT

SOURCE LIST

SIZE OF SAMPLE

BUDGETARY CONSTRAINT

SAMPLING PROCEDURE

SAMPLING METHOD

RANDOM NON RANDOM


SAMPLING SAMPLING

DRAW
SAMPLE

Characteristics of a Good Sample Design


 S.D. must be a true representative of the population.
 S.D. must be according to the funds available for the research study.
 S.D. must be with small sampling error.
 S.D. must be such so that the systematic bias can be controlled in a better way.
(Systematic bias results from errors in the sampling procedures)
 S.D. must be such so that the results of the sample can be used in general with a level
of confidence.
Types of sampling

Sampling

I II
Probability Non-Probability
(Random) (Non-Random)
Sample Sample

A B A B C
Simple Complex Convenience Purposive Snow Ball
Random Random Sample Sample Sample
Sample Sample

i ii
Deliberate\ Judgment
Systematic Stratified Cluster Double Quota Sample
Random Random Sample Sample
Sample
Sample Sample
I. Random (Probability) Sample
Random Sample is also called as probability sample. Probability sample is the sample in
which each element /member of population has a known, chance of being selected. The
probability sample can be classified as: Simple random sampling and Complex random
sampling.

(A) Simple Random Sample


Simple random sample is applicable when population is small, homogenous and readily
available. Simple random sample means where each population element / member has
an equal and known chance of being selected in the sample. Let us assume that there
are 2,500 teachers in the college\university and through simple random sample we have
to choose 250 teachers for the study. In this method we will select sample members by
assigning each teacher a number on chit. The total number of teachers which will be
given numbers will be the size of population i.e. 2500 and we will choose 250 teachers
randomly equal to sample size. The choosen sampling unit will again be placed for the
sampling process.
There are two terms to be remembered in simple random sampling:
WR= With replacement i.e. an element may appear multiple times in the sample
WOR= Without replacement i.e. an element may not appear multiple times in the sample.
Dis-advantages
1. It is not applicable for large population.
2. It does not form divisions of the population.
3. It chooses the sample unit again and again which has been choosen earlier.

(B) Complex Random Sample


Complex Random Sample is more efficient sample with a smaller sample size.
Complex Random Sample is of following types:

(i) Systematic Random Sample


Systematic random sampling means each population element / member has
known chance of being selected into the sample but not an equal one. Let’s take
the same example of 2,500 teachers in an organization and a sample of 250 is to
be used.
Forumla
Population Size N 2500
= = =10
Sample Size n 250
It means that out of 10 we have to select 1. Then we randomly select a digit between 1
and 10 like 7. Then we will select 7 th, 17th, 27th ........ 2497th item to make a sample of 250.
Gap of 10 after every member selected is sampling interval.
Advantages
1. Convenient to adopt than simple random sample.
2. Sample is evenly spread over entire population.
Dis-advantage
Every 10th element/member selected may not be the actual representative which
creates bias.

(ii) Stratified Random Sample


In Stratified random sample the total population is divided into various exclusive
sub-populations or into various strata on the basis of age, gender, income, education
or religion. For example university students can be divided on the basis of their course,
classes
or gender. After the population is divided into strata then each stratum can be treated as
independent population. Then simple random sampling or any sampling technique can be
taken within each stratum.
Advantages
1. Stratified Random Sample is a combination of number of smaller samples.
Stratification is considered to be ideal when each stratum is homogeneous internally
and heterogeneous with other strata.
2. Stratified Random Sample is more efficient than simple random sample.
3. Stratified Random Sample is useful when one wishes to draw some conclusions about
activities in different classes of students.
Dis-advantage
1. Sampling frame for each stratum is to be prepared separately.
2. Multiple stratums can cause complications.

Stratified Random Sample can of following types: (i) Proportionate Stratified Random Sample
and (ii) Dis-proportionate Random Stratified Sample.

1. Proportionate Stratified Random Sample


In Proportionate Stratified Sample, number of elements in sample of one stratum is
proportionate to the no. of elements in sample of other stratum i.e. if we take 10% for number
of elements in sample of one stratum then same % will be taken no. of elements in sample of
other stratum.
2. Dis-Proportionate Stratified Sample
In Dis-proportionate Stratified Sample, number of elements in sample of one stratum is not
proportionate to the number of elements in sample of other stratum. This type of sampling is
used when we have to take large number of sample from one stratum and fewer number of
sample from other stratum.

(iii) Cluster Sample


A sampling strategy where the population of interest is divided into representative "clusters" of
individuals, among whom a random selection of subjects is drawn. Cluster sampling can be of
following two types:

(i) Area Sampling


Area Sampling means when clusters happen to be some geographic sub-divisions in terms of
colony or house-hold. For example let randomly select the city of Lucknow from the state of
Uttar Pradesh of the country India. If by chance there is no up-to-date list available then
cluster sample becomes important. Let’s assume that the sampling unit is house-hold and the
sample size is 250 house-holds. Then let’s divide the whole Lucknow City in 50 clusters on
the basis of colony, where there is heterogeneity within clusters and homogeneity between
clusters because of similar residential characteristics. Then we give numbers to 50 clusters
from 0 to 49. Then we choose 6 clusters randomly which can be 7, 18,25,28,38 and 45. Then
we can choose 250 Households from 6 clusters by taking equal number of household from
each 6 clusters i.e. 42 house-holds.

(ii) Multi-stage sampling


Multi-stage sampling is the development of cluster sampling. Let us take the example where
the government people want to know the performance of the universities of India. Multi-stage
sampling means when in the first stage we select large sampling unit such as our country.
Then we may select randomly certain district as clusters and interview all the universities in
the chosen cluster of districts. This means two-stage sampling design. If instead of taking a
census of all the universities within the clusters of the district, we select randomly certain
clusters of district and then again randomly select clusters of cities and then interview with all
the universities. This means three-stage sampling design. Then again going for further
classification for forming clusters is called as multi-stage sampling design.
Advantages
1. Economically more efficient then simple random i.e. lower Cost / sample.
2. Easy to do with source list (population list)
Dis-advantage
Ineffective statistical efficiency due to sub-groups being homogeneous rather than
heterogeneous.

(iv) Double Sample


Double Sample is also known as Multiple/Sequential Sample. Double sampling means when
data is collected on the basis of two samples. Multiple sampling means when the data is
collected on the basis of more than two samples but the number of samples is certain and
decided in advance. Sequential sampling means when the data is collected on the basis of
more than two samples but the number of samples is un-certain and not decided in advance.
This means in sequential sampling one can go on taking samples one after another as long
as one desires to go.

II. Non- Random (Non-Probability) Sample


Non-random sample is based on the concept of non probability selection (arbitrary).
It does not follow controlled procedure but is dependent on researcher’s wish. We should use
non probability sample then to probability sample because:
 Non-random sampling can be performed more easily than random sampling.
 Non-random sampling can meet the research objectives without the formal exercise as
random sampling.
Non-random sampling can be of following types:

(i) Convenience Sample


Convenience sample is a sample, which is chosen on the basis of convenience of the
researcher. Convenience sample is ‘take them where you find them’. Convenience sample is
unrestricted. Convenience sample is a sample where the researchers have the freedom to
chose or not to chose, so the name convenience. For example if the researcher is from
Lucknow city and the researcher chooses the sample unit from Lucknow then it is called as
Convenience sample. The researcher can choose the samples as friends, neighbours or
relatives depending upon their convenience.
Convenience sample is also called as accidental sampling. Here the researcher cannot
measure the sampling error. Convenience sample is generally used in exploratory research
design.
(ii) Purposive Sample
Purposive sample is the sample where the researcher purposively chooses the
sampling unit from the population. Purposive sample is the sample where the
researcher chooses the sampling unit on certain criteria. Purposive sample are of
following types:

(a) Deliberate Sample \Quota Sample


Deliberate sample\ quota sample means where the researcher chooses the sampling
unit having some characteristics of the population thought to be relevant. There is a
difference with convenience sampling as there was not deliberate choosing but
choosing according to convenience.

Deliberate sample\ quota sample is similar to stratified random sample. Deliberate


sample\ quota sample is the sample in which total population is divided into various
strata (groups) on the basis of age, gender, income, education or religion.

(b) Judgment Sample


Judgment sample is the sample where the researcher selects the sample members
according to some criteria i.e. knowledge. This means only those members for the
sample will be choosen who have knowledge related with the subject of the study. For
example civil engineer for civil task, marketing person for marketing task and heart
surgeon for heart study.

(iii) Snow Ball Sample


Snow Ball Sample is the sample where the researcher collects the sample unit through
some reference. Snow- ball sample has found importance in recent years where
respondents are difficult to identify and are best located through referral networks.
Snow ball sampling is also called as referral sampling or chain sampling. The name of
snow ball given because the sample group rolls as snow ball.

Types of sample design


The basis of types of sample design can be as follows:
 Finite universe or Infinite universe which means the universe is countable or un-
countable.
 Sampling unit is an individual or an organization.
 Sampling frame is bigger or smaller.
 The size of sample is larger or smaller.
 The technique of sampling is random sampling or non random sampling.
 The topic selected for the study.
 The field of the study.

Sample size
 Sample size means the No. of Elements of Population which can be the True
Representative of the Total Population.
 Sample size must be Large otherwise it will not represent the Total Population.
 Sample size must be proportionate to the size of Total Population from which it is
drawn.
Principles which Influence the sample size
1. The Greater the variance between the population, the larger the sample size.
2. The Greater the feeling of Estimation to be precise, the larger the sample, size.
3. The Greater the Confidence level in Estimation, the larger the sample size.
4. The Greater the No. of Sub-groups, the larger the Sample Size.
5. The Narrower the Interval Range, the larger the sample.
 Researcher can never be 100% certain for a sample reflecting its population. They
must decide about how much precision they need.
Precision is measured by 
1. The Interval Range in which they find the Estimate
and
2. The degree of confidence they wish to have in that Estimate.
 The size of the sample needed can be affected by the size of the population. The
Sample size should be 5% or more of the population.

Determining the sample size


The sample size can be determined as follows:
SZ\T
S=Preliminary SD of the universe
Z=Number of standard errors
T=Errors to be tolerated

The sample size can also be determined as follows:


Enter your choices in a calculator below to find the sample size you need or the confidence
interval you have. Leave the Population box blank, if the population is very large or unknown.

Determine Sample Size

Confidence Level: 95% 99%

Confidence Interval:

Population:

Sample size needed:

Find Confidence Interval

Confidence Level: 95% 99%

Sample Size:

Population:
Percentage:

Confidence Interval:

The confidence interval (also called margin of error) is the plus-or-minus figure usually
reported in newspaper or television opinion poll results. For example, if you use a confidence
interval of 4 and 47% percent of your sample picks an answer you can be "sure" that if you
had asked the question of the entire relevant population between 43% (47-4) and 51% (47+4)
would have picked that answer.

The confidence level tells you how sure you can be. It is expressed as a percentage and
represents how often the true percentage of the population who would pick an answer lies
within the confidence interval. The 95% confidence level means you can be 95% certain; the
99% confidence level means you can be 99% certain. Most researchers use the 95%
confidence level.

When you put the confidence level and the confidence interval together, you can say that you
are 95% sure that the true percentage of the population is between 43% and 51%. The wider
the confidence interval you are willing to accept, the more certain you can be that the whole
population answers would be within that range.

For example, if you asked a sample of 1000 people in a city which brand of cola they
preferred, and 60% said Brand A, you can be very certain that between 40 and 80% of all the
people in the city actually do prefer that brand, but you cannot be so sure that between 59
and 61% of the people in the city prefer the brand.

Limitation of sampling
The limitation of sampling is as follows:
 There is no appropriate sample size for any population.
 The technique of sampling selected may not be appropriate.
 The criteria adopted for any technique may not correct as per the suggested design.
 The members selected for the sampling may not be true representative of the population.
 The sampling frame may not be appropriate frame for any study.
 The information collected or stored may not be true.
 The mis-understanding of the topic.
 The lack of knowledge of the researcher.

You might also like