0% found this document useful (0 votes)
15 views43 pages

Sampling

1. Sampling involves selecting a subset of individuals from a population to estimate characteristics of the whole population. 2. There are two main types of sampling: probability/random sampling, where all individuals have an equal chance of selection and results can be generalized; and non-probability sampling, where results cannot be generalized. 3. Common probability sampling methods include simple random sampling, systematic random sampling, stratified random sampling, and cluster random sampling. Non-probability methods include purposive and quota sampling.

Uploaded by

Abdallah Reda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
15 views43 pages

Sampling

1. Sampling involves selecting a subset of individuals from a population to estimate characteristics of the whole population. 2. There are two main types of sampling: probability/random sampling, where all individuals have an equal chance of selection and results can be generalized; and non-probability sampling, where results cannot be generalized. 3. Common probability sampling methods include simple random sampling, systematic random sampling, stratified random sampling, and cluster random sampling. Non-probability methods include purposive and quota sampling.

Uploaded by

Abdallah Reda
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 43

Sampling

Statistical Section
Public Health Department
Cairo University
Research Question
(What is the problem?)
Phase I:
Goal (broad & main objective) Planning
Specific Objectives (precise &
concise)
Protocol
Writing Study Design
Process (How are we going to work?)
(All the 4
research
Sampling
phases
(Target population, size & technique)
Should
be considered
) Study Tools &Variables
(Clear definitions and Valid standardized
tools)

Ethical Considerations
(Informed consent)

Phase II:
Field Work & Data Collection Implementatio
(Quality Control & Monitoring) n

Data Management & Analysis Phase III:


(Data entry, cleaning, analysis and Data
interpretation) management

Phase IV:
Writing Up Communicatin
(Publication and presentation) g Results
Research Question
(What is the problem?)
Phase I:
Goal (broad & main objective) Planning
Specific Objectives (precise &
concise)
Protocol
Writing Study Design
Process (How are we going to work?)
(All the 4
research
phases Sampling
Should )
be considered
) Study Tools &Variables
(Clear definitions and Valid standardized
tools)

Ethical Considerations
(Informed consent)

Phase II:
Field Work & Data Collection Implementatio
(Quality Control & Monitoring) n

Data Management & Analysis Phase III:


(Data entry, cleaning, analysis and Data
interpretation) management

Phase IV:
Writing Up Communicatin
(Publication and presentation) g Results
Study population

The entire population (100%) sample in case -1


of having small number of cases understudy
.(small village)
A sample if the study populations and places -2
or service points are large in number, it is
necessary to select a sample of less than
100% to represent them
Study setting

• The study setting refers to the place from


which, data will be collected. It could be
from a certain clinic in the hospital, village
(community), urban area (community),…etc.
Within those settings, we have to select the
study population.
Sample definition

• Sampling is the selection of a subset of individuals from


within a population to estimate the characteristics of
whole population
Advantages of sampling

• Save time, money and effort


• Improve research accuracy
Who do you want
The
to
population
generalize to?

What population accessibl


can e
You get access populatio
How to?
can n
The
you get sampling
access to type
them
Who you will The
select sample
in your study?
Sample type

Probability or random samples : They are -1


representative of the study population so you
can generalize their results to population
Non probability samples : They aren’t -2
representative of the study population so you
cannot generalize their results to population
Probability or random sample

The sample is selected to represent the entire


population understudy, so that the information
obtained from the sample will be very similar to
the information that would be obtained from a
study of the entire population i.e. sample results
can be generalized to study population
Probability or random sample

Randomization
• All units must be known and made available for
sampling
• All units must have an equal chance to appear in
the sample.
UNITS

Healthy

Frank Disease

Early Disease
Difficult detection

POPULATION
UNITS

Healthy

Frank Disease Sample 1


Early Disease
Difficult detection

Sample 2

POPULATION
Types of random sample

• Simple random sample


• Systematic random sample
• Stratified random sample
• Cluster random sample
• Multi-stage random sample
TYPES OF SAMPLES

Community Hospital based Exposure based


based
Cluster
Simple Rando
Random m

Stratified Multistag
Random e
Systematic
Random
Random
SIMPLE RANDOM SAMPLE-1

Each element in the population has an


equal probability (chance) of being
selected for the sample
Assign numbers
then
random selection
SIMPLE RANDOM SAMPLE

➢ Methods used
• Lottery method

• Dice

• Tables of random numbers


• Computer programmes.
SIMPLE RANDOM SAMPLE

• Advantage:
1. Easy & Simple
2. Reasonable to generalize the result to
population
• Disadvantage:
1. Not suitable for large population
2. No good representation of sub groups
SYSTEMATIC RANDOM-2
SAMPLING

An easy sampling procedure if:


▪ You have a complete list of all units.
▪ The sample size is relatively large.
SYSTEMATIC RANDOM
Method: SAMPLING
▪ Determine population size e.g. N = 100
▪ Determine Sample size e.g. n = 20
▪ Determine Systematic sampling interval
e.g. I = N/n [100/20 = 5]
▪ Select a random number R from 1 to 5 e.g. R =
4
▪ Use the interval to identify sampled units
e.g. R + I = 4 + 5 = 9 then 9 + 5 = 14 etc……
1 Ahmed
2 Amal
3 Bahgat 96 Waleed
4 Bothina 97 Yehia
5 Dalia 98 Yousef
6 Emad 99 Zaky
7 Faiez 100 Zeinab
8 Gehad
9 Hoda
10 Ibraheem Sample units are:
11 Ismaiel 4, 9, 14, 19……99.
12 Kamelia 4 (first random)
13 Kamal
4+5=9
14 Lobna
9+5=14
15 Labib
14+5=19
.
94+5=99
CLUSTER RANDOM-3
SAMPLING
▪ In real life, it is sometimes very difficult to know all
units in a community.
▪ It is easier to identify units (individuals) in their
natural groupings [Clusters].
• Instead of giving equal chance for every unit, we
will give an equal chance to every Cluster to be
selected in the sample.
POPULATION CLUSTERS

▪Governorates (27)
▪Cities
▪Villages
▪Schools
▪Houses
Sampled
Clusters

POPULATION
CLUSTER (Area) RANDOM
SAMPLING
• Advantage
1. Easy, simple
2. Convenient
• Disadvantage
1. May be no representation of subgroups
STRATIFIED RANDOM-4|
SAMPLING
Strata – is a group of people who
share a common characteristic.

Examples of strata– Gender, Marital


status, Student IQ.
STRATIFIED RANDOM
SAMPLING

▪ The study population is divided into


different strata (Hypothetical Groups).
▪ The size of the sample in each stratum is
proportional to the size of the stratum
(proportional allocation).
Females

Males

POPULATION
Random Ordering
19

14

4
Stratification
19
Stratum 2
Females

14

9
Stratum 1
Males

4
Multistage random sample

• The most sophisticated


• In research with complex population
distribution e.g. national surveys as Egyptian
demographic health survey. It is done by
combining sampling methods
TYPES OF SAMPLES

Probability
Non probability
(random)
Cluster
Simple Rando
Random m

Stratified Multistag
Random e
Systematic
Random
Random
Non-Probability samples

• Does not involve random selection and are not


representative to study population.
• There are many types e.g.:
i- Purposive sample
ii-Quota sample
iii-Snow ball sample
Purposive sample

• We sample subjects with a purpose in mind


tied to a purpose of research
• We take every patient who meets the
selection criteria over a specified time interval
or number of patients
Quota sample

• You select people non-randomly according to


some fixed quota
• E.g. if you know the population has 40%
women and 60% men, and that you want a
total sample size of 100, you will continue
sampling until you get those percentages and
then you will stop.
Snow ball sample

• You begin by identifying someone who meets


the criteria for inclusion in your study. You
then ask them to recommend others who they
may know to also meet the criteria.
• It is useful when you are trying to reach
populations that are inaccessible or hard to
find, e.g. AIDS patients, homeless persons
Sample size determination

1. Importance of the study


2. Variables of the study
3. Magnitude of the problem
4. Availability of facilities
5. Statistical analysis and power
? ANY QUESTIONS

You might also like