SAMPLING DESIGNS IN OPERATIONAL

HEALTH RESEARCH
Dr. Syed Irfan Ali

Basic/
applied

Quantita
tive

Research

Empirical
/theoreti
cal

Qualitati
ve

Biomedi
cal

Health
research
triangle

Health
research

RESEARCH
A delegate search/
investigation/
experimentation for
discovery/ interpretation of
knowledge
Defined goal/ purpose
Observation/ theory

Behavio
ural

Changes at celluar level

Environment causing cellular
changes
Interactions reflecting the KAB of
individual in society

Measurem Organize, order

ent
observation
Of
variable
Estimation
Of
parameter
s

Population
parameters estimated
by statistical methods

The extent to which

chance may account
Hypothesi
s
for observation
testing

HEALTH
RESEARCH
Health research basically is
a quantitative type of
research & it has three basic
components

SAMPLE
Definition of sample and

population

Census and sampling

Parameters and statistics

Basis of sampling error

 Less resources
More accuracy less non sampling error
Only method in case of infinite population
Advantages

Disadvantag
es

Sampling error
Bias

Universe or population
Target population
Sample frame
Sample population
Sample design
Sampling units

TYPES OF ERROR IN SAMPLING

Sampling error
Faulty selection of the sample

Substitution
Faulty demarcation of

sampling unit
Error due to improper choice

of the statistics for estimating

the population parameters

Non sampling error

Faulty planning and

definitions
Response errors
Non-response
Compiling errors

Publication errors

TYPES OF SAMPLING DESIGN

Probability sampling

Non probability sampling

Simple Random Sampling

Convenience or haphazard sampling

Complex Random Sampling (mixed

Purposive / Deliberate sampling

sampling) Designs

Judgment Sampling

Stratified Sampling

Quota Sampling

Cluster Sampling

Snowball sampling

Area Sampling
Systematic Sampling
Multistage Sampling
Sequential Sampling

PROBABILITY SAMPLING
Subjects of the sample are chosen based on known

probabilities.

Advantages of probability samplingI.

The population of interest is clear (because it must be identified before

sampling from it.)

II.

Possible sources of bias are removed, such as self-selection and interviewer

selection effects.

III. The general size of the sampling error can be estimated.

SIMPLE RANDOM
SAMPLING

why

Simplest and easiest, requiring minimum prior knowledge

Free of classification error. Easy collection & interpretation
Each element & sample has an equal probability of getting selected

Element
chosen
randomly
by
random
tables.
basic
With replacement- used in infinite population
Types With out replacement.

Disad Useful for a relatively small sample

vantag
Sample frame is a pre requisite
es

From a sample
frame

Randomly
select elements

The selected
elements form
the sample

SYSTEMIC
SAMPLING

 Decide on sample size: n

Divide population of N individuals into groups of

k individuals: k = N/n
Randomly select one individual from the 1st group.
Select every k-th individual thereafter.
Advantage:

N = 12

I.

n=4

The sample usually will be easier to identify than it would be if

simple random sampling were used.

II.

Time and labour is relatively small.

III. It yields accurate results if the population is large and

homogenous.

k=3

STRATIFIED
SAMPLING

population

strata

strata

strata

strata

 Subpopulation in an overall population might vary

A weighted mean is obtained
why

basic

Types

Based on common characters divided into strata

Mutually exclusive and collectively exhaustive
Less difference with in and greater difference between the strata
Proportionate- basic stress is on representation of subgroups
Disproportionate- stresses on the validity

 Takes into account various sub groups

Increased precision/ validity/ reduced sampling error
More convenient & lower cost
Advantages
Difficult to identify and justify subgroups representing
population. Prior information of the characteristic is
needed
Disadvantag Separate sampling frame required for each strata
es

From a
population

Based on an
attribute divide
into strata

Select elements
from strata by
randomization

CLUSTER
SAMPLING

why

basic

Large population size

Sampling frame not present
Less resources required
There are 2 sampling units PSUs & SSUs. PSUs are selected
randomly, from 1 PSUs all SSUs are selected

Multistage cluster- some not all SSUs are selected randomly

Types

Disad Very high error for error to be low Most of the variations should
vanta
be within the groups not between them or use design having large
ges
number of PSUs with small number of SSUs.

naturally
occurring groups
in a population

Select the PSUs

or Clusters
Randomly

Select all the

SSUs from the
selected PSUs

STRATIFICATION VS. CLUSTERING

Clustering

Stratification

1. Divide population into

1.

Divide population into groups

different from each other: sexes,
races, ages

2.

Sample randomly from each group

3.

Less error compared to simple

random

4.

More expensive

5.

obtain stratification information

before sampling

comparable groups: schools, cities

2. Randomly sample some of the

groups
3. More error compared to simple

random
4. Reduces costs to sample

5. only some areas or organizations

MULTI STAGE SAMPLING

Complex form of cluster sampling in which two or more levels of units

are embedded one in the other.

This technique, is essentially the process of taking random samples of

preceding random samples.

It banks on multiple randomizations

Multistage sampling used frequently when a complete list of all

members of the population does not exists or is inappropriate.

Moreover, by avoiding the use of all sample units in all selected

clusters, multistage sampling avoids the large unnecessary, costs

associated with traditional cluster sampling.

MULTIPHASE SAMPLING
Part of the information collected from whole sample & part

from subsample.
In Tb survey cough in all cases Phase I
X Ray chest in MT +ve cases Phase II

Sputum examination in X Ray +ve cases - Phase III

Survey by such procedure is less costly, less laborious &

more purposeful

NON PROBABILITY SAMPLING

Any sampling method where some elements of population have no

chance of selection (these are sometimes referred to as 'out of

coverage'/'under covered'), or where the probability of selection
can't be accurately determined.
It involves the selection of elements based on assumptions regarding

the population of interest, which forms the criteria for selection.

Hence, because the selection of elements is nonrandom,

nonprobability sampling not allows the estimation of sampling

errors.

QUOTA SAMPLING
The population is first segmented into mutually exclusive sub-

groups, just as in stratified sampling.

Then judgment used to select subjects or units from each segment

based on a specified proportion.

For example, an interviewer may be told to sample 200 females and

300 males between the age of 45 and 60.

In quota sampling the selection of the sample is non-random.

CONVENIENCE SAMPLING
Sometimes known as grab or opportunity sampling or accidental or

haphazard sampling.
A type of nonprobability sampling which involves the sample being

drawn from that part of the population which is close to hand. That is,
readily available and convenient.
This type of sampling is most useful for pilot testing.

PURPOSIVE OR JUDGEMENTAL SAMPLING

The researcher chooses the sample based on who they think would

be appropriate for the study. This is used primarily when there is a

limited number of people that have expertise in the area being
researched

SNOW BALL SAMPLING

Find a few people that are relevant to your topic.
Ask them to refer you to more of them.

SAMPLING DESIGN & ITS ASPECTSpopulatio

n

Type of
sample

Sampling unit

Sampling frame
Sample size

resources

Parameter at
study

CHARECTERS OF A GOOD SAMPLE DESIGN

True representative
Has all characteristics that are present in population
Sampling error should be small
Bias is minimal

Economically viable
Results can be applied to the universe in general with a reasonable

level of confidence or reliability

Optimum size (adequately large)

IN A NUT SHELL
Probability Sampling

- Simple Random Selection at Random

- Systematic Selecting every nth case
- Stratified Sampling w/n groups of Populn

- Cluster Surveying whole clusters of P/n

- Multistage Sub samples from large smpl

 Non- Probability Sampling

- Accidental Sampling those most convnt
- Voluntary Sample is self selected
- Purposive Handpicking typical cases

- Quota Sampling w/n groups of Ppln

- Snowball building sample thru informnts

REFERENCES
Parks Text book of preventive and social medicine- K.Park
Sampling: Design and Analysis Sharon L. Lohr
Fundamentals of Biostatistics Bernard Rosner
Principals and practice of biostatistics Dr J B Dixit

HEALTH RESEARCH METHODOLOGY A Guide for Training in

Research Methods-WORLD HEALTH ORGANIZATION

TextBook of Public Health and Community Medicine Chief Editor

RajVir Bhalwar