Research

Sampling Design
Group 3 : Dorilag, Ang, Ganza, Fran, Padernal, Reyes
 Outlline:
Sampling Design
Advantages of Sampling Design
Sampling in Public Health
Definition of Terms
Characteristic of Good Sampling Design
Basic Sampling Design
Non- Probability Sampling
Probability Sampling

Group 3 : Dorilag, Ang, Ganza, Fran, Padernal, Reyes

Sampling Design:
Sampling:
selection of a population's
representative subset
or some individuals in a population
who will serve as
the entire populace
 What are the advantages of sampling?

1 3
Cheaper
2 4
Best Quality Ethical
considerations
Faster Feasibility
Uses of sampling in public health
Determining a population's state of health
Examining the elements that affect health
Assessing the success of health interventions
Evaluating particular elements in the
management of health services
Assessing the completeness and dependability
of record systems like the hospital records and
the vital registration system
 Definition of Terms
Population The entire group that you want to draw conclusions about

2 Types of Target Population: the group whom representative

population information is desired.
Sampling Population: population to which sample will
actually be taken.
Elementary Unit
or Element An object or area on which a measurement can be taken

Sampling Unit Any of the elements selected from a population to make up a sample

Sampling Collection of all sampling units.

Frame
Characteristics of a good sampling design:
1. Representative Sample - A good sample design should
ensure that the sample is representative of the population.
The sample should accurately reflect the characteristics of
the population, such as age, gender, income, and education.

2. Adequate Sample Size

A good sample design should have an adequate sample size to
ensure that the research findings are reliable and accurate

3. Random Sampling
Random sampling is a crucial aspect of a good sample design.
Random sampling ensures that every member of the population
has an equal chance of being selected for the sample.
Characteristics of a good sampling design:
4. Practical and feasible
The sampling design should be sufficiently simple and straight
forward so it can be carried out as planned

5. Economy and efficiency of the sampling design

It must give the most information at the smallest cost
 Basic Sampling Design
Non- Probability Sampling
a sampling technique in which the researcher selects
samples based on the subjective judgment of the
researcher rather than random selection. It is a less
stringent method.
This sampling method's drawback is the potential for
bias. A bias is a greater probability that a particular type
or class of sample units or elements will be included in
the chosen sample.
This sampling type's conclusion is only valid for the
sample itself.
 Examples of Non Probability Sampling
Judgement Or Purposive Sampling
❖ Selection of samples is based on expert’s subjective
judgement or a pre-specified criterion
A type of non-probability sampling. This means that the
selection of the sample is not based on chance. Instead,
the researcher selects participants for the study based
on specific criteria that are predetermined by the
researcher.

Accidental Or Haphazard
❖ when selection is by whatever is available or whatever
items comes on hand
Quota Sampling
❖ Interviewers keep on interviewing in a given place until
quota is met

For example, a cigarette company wants to find out what age

group prefers what brand of cigarettes in a particular city.
They apply survey quota on the age groups of 21-30, 31-40, 41-
50, and 51+. From this information, the researcher gauges the
smoking trend among the population of the city.

Snowball Technique
❖ Selection is based on earlier subjects until sample size is
met.
a non-probability sampling method where new units are
recruited by other units to form part of the sample. Snowball
sampling can be a useful way to conduct research about
people with specific traits who might otherwise be difficult to
identify (e.g., people with a rare disease).
 Probability Sampling
❖ A design based on the concept of random selection
❖ A procedure that assures that all the elements in
the population are given an equal chance of being
selected as a sample unit

.
❖ Population has a known no zero chance
❖ Allows extrapolation from small, highly
representative
sample, to larger population.
❖ Partiality and biases are reduced or controlled
 Cross-sectional surveys:
SIMPLE RANDOM SAMPLING
♦ Selecting individuals from a sampling frame such that ♦ Every element in the population has an equal chance of
each individual has a fixed and determinate probability of being
selection. ♦ included in the sample.

Done by: Each element has an equal

chance of being selected
Procedure

◦ Drawing Lots – Steps: ◦ Example: 1. Prepare the sampling frame

◦ Make a list of the elements ◦ Random selection of 2. Decide on the size of the
and number them. households in barangay sample
◦ Write the number on small ◦ Population size (N)= 500, 3. Select the required number of
piece of paper and roll. Sample size (n)=100 subjects at random
◦ Pick one rolled paper under ◦ Assign unique number (1 to using a table of random numbers
you can complete the 500) or computer-generated
◦ estimated sample size. ◦ Select HHs using random list of random numbers
◦ Use table of Random digits numbers (n = 100)
 SYSTEMATIC SAMPLING WITH RANDOM START

♦ A method selecting a sample from a population ♦ Steps:

◦ Determine the sampling interval
by taking
the
♦ kth units from an ordered population, from the
K= 𝑁/𝑛 ; K= 𝑆𝑖𝑧𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑃𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛/𝑆𝑎𝑚𝑝𝑙𝑒 s𝑖𝑧e
◦
◦
example: K= 30/15 = 2
first unit Select random any number from
1-K.
that is selected at random ◦
♦ K is called the sampling interval, and it is derived ◦
Then start from there.
From there take every k until you can have all the sample
by units desired.
dividing ◦ Example:
♦ the total population by the desired sample size. 1. Get 10 household from the population of 80
♦
♦ To use this technique an ordered list of population ♦
k=N/n
k=80/10
elements is required. ♦ k=8
♦ Sequential selection of individuals, conceptually ◦ Therefore 1 household shall be selected for every 8
household in the population.
separated on the lists by an interval of selection ◦ 2. Systematic sampling with random start.
◦ Choose from 1-80 using fish bowl method of where to
start number 1.
 STRATIFIED RANDOM SAMPLING
♦ It is the process of selecting a random sample from strata
or subgroups into which population has beensubdivided.
♦ Steps:
◦ Classify into strata orsubgroups
◦ Determine sample size by:
▪ stratum sample size = stratum size x desired size population size
♦ Note to be done for each group
◦ With the sub-sample size, select the sample from each
stratum using SRS or Systematic sampling with random
start.
◦ Example:
◦ Total Farmers =75
◦ Estimated sample size = 30
♦ Breakdown
◦ Rice farmers = 30 30/75x30=12
◦ Sugar cane farmers = 20 8
◦ Vegetable farmers = 10 4
◦ Cut flower growers = 1 5 6
Total 30
CLUSTER SAMPLING SELECTION
♦ Selection is done by sample of groups or cluster of
elements.

♦ Clusters are usually exclusive sub - populations which

♦ together comprise a population.
♦ Each is consist of heterogeneous elements typical of a
♦ population.
♦ Size of the population of clusters.
♦ Cluster size
♦ The number of clusters in the population represents in
the population represents the size of the population of
clusters, while the number of elements in cluster is called cluster
size.

♦ The sample clusters can be drawn using simple random sample or

systematic sampling with a random start.

Steps:
◦ Number each group.
◦ Using SRS draw estimated sample cluster
◦ Identify the group selected.
◦ Study all students in each sample cluster selected.
 MULTISTAGE SAMPLING
♦ Selection of sample is accomplished in 2 or more stages.
♦ The population.
♦ Stage 1 / Primary/ ♦ Secondary sampling /
First Stage Second Stage

◦ Population is divided into primary sampling ◦ The procedure continues until the desired stage is
units. A reached.
◦ sample of such units is selected.
The procedure continues until the desired stage.
Each primary sampling unit is further subdivided
into
Thank you!