Types of Sampling

SAMPLING
By: Chukwuebuka Ejeckam
Preston Healthcare Consulting
Friday, 20th January 2017
2/9/2017 1

Outline
Definition of Concept
Definition of Terms
Why Sample
Sampling Technique
Considerations in Sampling
2/9/2017 2

Definitions
A sample can be thought of as a model of a
larger population.
In research terms a sample is a group of people,
objects, or items that are taken from a larger
population for measurement. The sample should
be representative of the population to ensure
that we can generalise the findings from the
research sample to the population as a whole.
 A sample is usually a subunit within the
universe- the universe consists of all the
members of a distinct group. The universe or
population is also the total collection of units
from which a sample can be selected.
Sampling is a process used in statistical analysis
in which a predetermined number of
observations are taken from a larger population
2/9/2017 3

Definitions Cont’d
2/9/2017 4

Definition of Some Terms
Respondent: A person or subject from whom
information/data is gathered in an interview
survey or questionnaire survey
Case: A more general term that may be used
to describe the unit studied, regardless of the
type of study or type of unit being studied.
Population/Universe- consist of all members
of a group. The population is also the total
collection of units from which you select your
sample.
Census- A survey of the entire universe (
gives real estimate not sample estimate)
Sampling Units- are the elements into which a
population is divided.
Sampling Interval: the nth unit of sample in a
stratified technique. Derived by dividing the
population by the desired sample size.
2/9/2017 5

Why do we Sample
 Enables research/ surveys to be done more quickly/ timely
 Less expensive and often more accurate than large CENSUS ( survey of the entire population)
Given limited research budgets and large population sizes, there is no alternative to sampling.
Sampling also allows for minimal damage or lost
Sample data can also be used to validate census data
2/9/2017 6

Sampling Technique – Probability
Sampling
Probability Sampling - in this technique, each element of the larger population or universe
has a KNOWN, NON-ZERO probability of being selected.
This is achieved through random selection of units for the sample from a list or sampling
frame- which guards against introduction of bias into the sample by researcher and against
other types of systematic bias.
 Sampling Frame contains the list of all possible/probable or eligible subjects that can be
selected or sampled.
 Probability sampling maximizes external validity or generalizability of the result of the study.
 Probability Sampling is the recommended gold- standard in most scientific research
endeavors. It engenders OBJECTIVITY.
2/9/2017 8

Simple Random Sampling
In Simple Random Sampling, each element
of the larger population is assigned a unique
ID number, and a table of random numbers or
a lottery technique is used to select elements,
one at a time, until the desired sample size is
reached.
Simple random sampling is usually reserved
for use with relatively small populations with
an easy-to-use sampling frame ( very tedious
when drawing large samples).
Bias is avoided because the person drawing
the sample does not manipulate the lottery or
random number table to select certain
individuals.
2/9/2017 9

Systematic Sampling
Systematic sampling is a type of probability
sampling method in which sample members
from a larger population are selected according
to a random starting point and a fixed periodic
interval.
In this approach, the estimated number of
elements in the larger population is divided by
the desired sample size to yield a SAMPLNG
INTERVAL, n). The sample is then drawn by
listing the population in an arbitrary order and
selecting every nth case, starting with a
randomly selected number between 1 & n.
 This is less time consuming and easier to
implement.
Systematic sampling is useful when the units in
your sampling frame are not numbered or when
the sampling frame consists of very long list.
2/9/2017 10

Stratified Sampling
Populations often consist of strata or groups
that are different from each other and that
consist of very different sizes.
Stratified Sampling ensures that all relevant
strata of the population are represented in the
sample.
Stratification treats each stratum as a
separate population- arranging the sampling
frame first in strata before either a simple
random technique or a systematic approach is
used to draw the sample.
One can draw either a proportionate or
disproportionate stratified sample.
2/9/2017 11

Disproportionate Vs. Proportionate
Stratified Samples
2/9/2017 12

Cluster Sampling
In Cluster Sampling, samples are selected in
two or more stages.
A cluster is a group of sampling units rather an
individual unit
It is mainly used when it is not possible to get
an adequate sampling frame for the individuals
or unit you wish to study or when a SR technique
would result in a list of individuals so dispersed
that it would be too costly to visit each one.
When only two phases are involved , it is called
TWO-Stage Cluster Sampling but when more
than two phases are involved, it is called MULTI-
Stage Cluster Sampling.
With extremely large populations, Multi-stage
cluster sampling is the ideal.
2/9/2017 13

Sampling Technique:Non-Probability
Sampling
Non-probability sampling involves a technique where
samples are gathered in a process that does not give all
the individuals in the population equal chances of being
selected.
A core characteristic of non-probability sampling
techniques is that samples are selected based on the
subjective judgement of the researcher, rather than
random selection (i.e., probabilistic methods), which is
the cornerstone of probability sampling techniques
Because subjective Judgement of the researchers plays a
key role in selecting the sample,almost always,
nonprobability sampling tend to over-select some
population elements and under-select others.
 Nonprobability sampling procedures are not valid for
obtaining a sample that is truly representative of a larger
population – the external validity of intervention studies
that employ nonprobability sampling technique depends
on replication of the study results in different
populations/enviroments.
2/9/2017 14

Convenience Sampling
Convenience sampling is a non-probability
sampling technique where subjects are selected
because of their convenient accessibility and
proximity to the researcher.
Convenience Sampling involves the selection of
samples from whatever cases/subjects or
respondents that happens to be available at a
given place or time.
Also known as Incidental/Accidental,
Opportunity or Grab Sampling.
Snow- ball Sampling is a special type of
convenience sampling where individuals or
persons that have agreed or showed up to be
interviewed in the study serially recommend
their acquaintances.
2/9/2017 15

Purposive Sampling
Purposive sampling, also known as judgmental,
selective or subjective sampling, is a type of non-
probability sampling technique.
In this non-probability approach, samples consist
of units deliberately selected to provide specific
information about a population.
Purposive samples are commonly used in
qualitative operation research studies (FGD with
adolescent girls on a sanitary pad brand that is
most appealing ).
Quota sampling is a type/variation of the
purposive sampling method.
2/9/2017 16

Basic Considerations
Sample Size
Universe Size & Mix ( Homogeneity vs.
Heterogeneity)
Related Resources (Time, cost, personnel,
etc.)
Accesibility
2/9/2017 17

‘’ for education is the progressive discovery of
our ignorance, for the MORE I know; that is
the MORE I know that I know NOTHING”
Confucius
2/9/2017 18

Wow…..,what an audience you all have
been…………………………
Thank you……………….
Obrigado…………………
Je vous remercie……..
Gracias…………………..
Danke…………….
Ndewo,Daluu…………Deeje
Na Gode………………...
Ese…………………………
Ahiya…………………….
Sosongo, Nobe…………………
Nago………………….
2/9/2017 19

Types of Sampling

More Related Content

What's hot (20)

Similar to Types of Sampling (20)

More from Preston Healthcare Consulting (20)

Recently uploaded (20)

Types of Sampling