Sampling
Design, process and techniques
Some definitions
Population
The aggregate of all the elements, sharing
some common act of characteristics, that
comprises the universe for the purpose of
the business research problem.
Census
A complete enumeration of the elements of
a population or study
Some definitions
Sample
A subgroup of the elements of the
population selected for participation in the
study.
Representative sample
A sample that is similar in all respects to the
target population.
The Sampling Design Process
Define
Define the
theTarget
Target
Population
Population
Determine
Determinethe
the
sample
samplesize
size
Determine
Determinethe
the
sampling
samplingframe
frame
Execute
Executethe
the
sampling
samplingprocess
process
Select
Selectaa sampling
sampling
technique
technique
Defining the target population
Target Population is a collection of
elements or objects that possess the
information sought by the researcher
about which inferences are to be made. It
must be defined in terms of elements,
sampling units, extent and time.
Elements are objects that possess the
information sought by the researcher and
about which inferences are to be made.
Defining the target population
Sampling unit is the basic unit containing
the elements of the population to be
sampled
Extent refers to the geographical
boundaries.
Time factor refers to the time period
under consideration
Determine the sampling frame
A sampling frame is the representation of
the target population. It consists of a list
or a set of directions for identifying the
target population.
Telephone book, association directory
that lists firms in an industry, a city
directory or a map etc., can be used as a
sampling frame based on the situation.
Determine the sampling frame
Though it maybe possible to compile a
list of the elements of the target
population, the list might include certain
elements that do not fit the description of
the sample elements correctly or might
omit certain elements that fit with the
description of the sample elements. This
leads to the Frame Error.
Select a sampling technique
The most important decision about the
choice of sampling technique is whether
to use probability or non probability
sampling.
If the sampling element is different from
that of the sampling unit it is necessary
to specify how elements have to be
selected within the unit.
Determine the sample size
Determining the sample size is complex and
involves several qualitative and quantitative
considerations
Qualitative considerations include
The importance of the decision
The nature of the research
The number of variables
The nature of analysis
Sample sizes used in similar studies
Resource constraints
Execute the sampling process
All the decisions taken in the earlier
stages are carefully executed in this
step.
A classification of the techniques
Sampling Techniques
Non - Probability Probability
Convenience Simple Random
Judgment Systematic
Quota Stratified
Snowball Cluster
Non-Probability sampling
Sampling techniques that do not use
chance selection procedures. Rather,
they rely on the personal judgment of the
researcher.
Convenience Sampling
It attempts to obtain a sample of
convenient elements. The selection of
sampling units is left primarily to the
researcher.
Examples are Tear-out questionnaires in
magazines, people on the street
interviews, Mall-Intercept interviews
without qualifying the respondents
Convenience Sampling
Advantages
It is the least expensive and the least time
consuming technique of sampling.
The sampling units are accessible, easy to
measure and cooperative.
Limitations
Non-representative hence results cannot be
generalized.
Not useful for descriptive and causal research
Judgmental Sampling
This is a form of convenience sampling
in which the population elements are
purposively selected based on the
judgment of the researcher.
Test-markets selected to determine the
potential of a new product, departmental
stores selected to test a new
merchandising display system.
Judgmental Sampling
Advantages
Low cost, convenient and quick
Useful if broad population inferences are not
required.
Limitations
Results are not generalizable.
It is subjective and its value depends on the
expertise of the researcher.
Quota Sampling
It is a two-stage restricted judgmental
sampling.
Stage 1:Developing control characteristics
Identifying control characteristics based on
judgment
Determining the distribution of such characteristics
in the target population
Setting up quotas such that the composition of the
sample is the same as the composition of target
population
Quota Sampling
Stage 2: Selecting sample elements
based on convenience or on judgment,
the only condition being that the sample
elements fit the control characteristics.
Quota Sampling
Control Char. Population Composition Sample Composition
Percentage Percentage Number
Gender
Male 48 48 480
Female 52 52 520
Age
18-30 27 27 270
31-45 39 39 390
45-60 16 16 160
Over 60 18 18 180
100 100 1000
Snowball Sampling
A technique in which initial group of
respondents is selected randomly.
Subsequent respondents are selected
based on the referrals or information
provided by the initial respondents. This
process may be carried out in waves by
obtaining referrals from referrals.
Snowball Sampling
Advantages
The likelihood of finding those sample
elements that have the desired
characteristics of the population increases
significantly because of referrals
It also results in relatively low sampling
variance and costs.
Probability sampling techniques
A sampling technique in which each
element of the population has a fixed
probabilistic chance of being selected for
the sample.
Simple Random Sampling (SRS)
A technique in which each element in the
population has a known and equal
probability of selection. Every element is
selected independently of every other
element and the sample is drawn by a
random procedure from a sampling
frame.
Simple Random Sampling (SRS)
Compile
Compileaa Generate
Generate‘n’‘n’(sample
(samplesize)
size)
sampling
samplingFrame
Frame random
random numbers
numbersbetween
between
11and
andNN(Population
(Populationsize)
size)
using
usingaacomputer
computerroutine
routine
Assign or
or aarandom
random number
numbertable
table
Assignaanumber
number
between
between11totoNN
(Population
(PopulationSize)
Size) Choose
Choosethethesample
sample
to
toeach
each sample
sample elements
elementsfrom
fromthe
thesample
sample
element
element frame
framethat
thatcorrespond
correspondtoto
the
therandom
randomnumbers
numbers
generated
generatedusing
usingthe
thetable
table
Simple Random Sampling (SRS)
Advantages
Easily understood
Sample results maybe projected to the
target population.
Most statistical inferential procedures
assume that the data have been collected
by using simple random sampling
procedures
Simple Random Sampling (SRS)
Limitations
It is often difficult to construct a sampling
frame that will permit a simple random
sample to be drawn.
May result in samples that are large and
spread over a wide geography making the
data collection effort costly.
May not result in a representative sample
Systematic Sampling
A technique in which the sample is
chosen by selecting a random starting
point and then picking every i th element
in succession from the sampling frame.
The sampling interval, i is determined by
dividing the population size N by the
sample size n and rounding it to the
nearest integer.
Systematic Sampling
The researcher here assumes that the
population elements are sorted in some
respect, preferably based on a
characteristic that is desirable by the
researcher.
The representativeness of the sample
increases if the elements are sorted
based on a preferred characteristic.
Systematic Sampling
Compile
Compileaa Determine
Determinethe thesampling
sampling
sampling
samplingFrame
Frame interval
intervalii== N/n
N/nand
andround
rounditit
to
tothe
thenearest
nearestinteger
integer
Assign
Assignaanumber
number Select
Select aarandom
randomnumber
number ,,
from
from11totoNN r,r, between
between11and
andi.i.
(population
(populationsize)
size)
to
toeach
each sample
sample Starting
Startingfrom
from that
thatnumber
number
element
element choose
chooseevery
everyiith
thelement
element
in
inthe
thesampling
sampling frame
frametill
tillnn
elements
elementsarearechosen.
chosen.
Systematic Sampling
Advantages
In case of large sampling frames significant
time as well as money can be saved in
selecting the sample elements.
When information on a desired
characteristic is available the
representativeness of the sample becomes
more compared to that of SRS.
Stratified Sampling
It is a two-step process in which the
population is partitioned into sub
populations or strata. Elements are then
selected from each stratum by a random
procedure.
Stratified Sampling
Select
Select aasuitable
suitablesampling
sampling In
Ineach
eachstratum
stratum number
number
frame
frame the
theelements
elementsfrom
from 11to
toNNhh
Select
Selectthe
thestratification
stratification
variable Determine
Determinethe
the sample
sample
variable(s)
(s) and
andthe
the
number size
sizeof
ofeach
eachstratum
stratum
numberof of strata
strataHH
Divide
Dividethethepopulation
populationinto
into In
Ineach
eachstratum,
stratum,select
selectaa
HHstrata
strataand
and assign
assignthe
the simple
simplerandom
randomsample
sampleofof
sample
sampleelements
elements to
toone
one size
sizennhh
of
ofthe
theHHStrata
Strata
Cluster Sampling
It is a technique in which the target population
is divided into mutually exclusive and
collectively exhaustive subpopulations called
clusters.
Then, a random sample of clusters is selected
based on a probability sampling technique
such as SRS.
Either all the elements are included in the
sample or a sample of elements is drawn from
each cluster probabilistically
Cluster Sampling
If all the elements of a cluster are
included then, it is called one-stage
cluster sampling.
If a probabilistic method is used to select
sample elements from within each
cluster then, it is called two-stage cluster
sampling.
Cluster Sampling
The objective of cluster sampling is to
increase sampling efficiency by
decreasing costs.
Area sampling is a form of cluster
sampling in which the clusters consists
of geographic areas.
Strengths and Weaknesses of basic
sampling techniques
Technique Strengths Weaknesses
Non-probability
Convenience Least expensive, least time Selection bias, sample not
consuming, most representative, not
convenient recommended for descriptive
and causal research
Judgmental Low cost, convenient, not Does not allow
time consuming generalization, subjective
Quota Sample can be controlled Selection bias, no assurance
for certain characteristics of representativeness
Snowball Can estimate rare Difficult to construct sampling
characteristics frame, expensive, lower
precision, no assurance of
representativeness.
Strengths and Weaknesses of basic
sampling techniques
Technique Strengths Weaknesses
Probability
SRS Easily understood, results Difficult to construct sampling
projectable frame, expensive, lower
precision, no assurance of
representativeness
Systematic Can increase Can decrease
representativeness, easier representativeness
to implement than SRS
Stratified Includes all important Difficult to select relevant
subpopulations, precision stratification variables, not
feasible to stratify on many
variables, expensive
Cluster Easy to implement, cost Imprecise, difficult to compute
effective and interpret results
Calculating the Sample size
Steps Means Proportions
Specify the level of D = ± 5.00 D = p-π = ± 0.05
precision
Specify the confidence CL = 95% CL = 95%
level
Determine the Z value Z value is 1.96 Z value is 1.96
associated with the CL
Determine the standard Estimate σ (=55) Estimate π (=0.64)
deviation of the σ2 = ∑(Xi – X)2/(n-1) π 2 = p(1-p)/n
population where i = 1 to n
Determine the sample n = σ2 z2 / D2 n = π (1- π) z2 / D2
size using the formula
for standard error
