DESCRIBING

SAMPLE SIZE AND

SAMPLING
PROCEDURE
 Determining the correct sample size and how the
samples are selected are crucial in ensuring the
accuracy and precision of an estimate leading to
valid research findings.
Sampling is securing some of the elements of the
population.

Population consist of the total elements.

SAMPLE SIZE DETERMINATION
A sample (n) is a selection of respondents for a
research study to represent the total population.

Making a decision about sample size for a survey

is very important. Too large sample may mean waste
of resources, and too small may affect the validity of
the research.
 THE FF. ARE SOME REASONS
FOR THE USE OF SAMPLES
1. A sample saves time compared to doing a
complete census which required more time.
2. A sample saves money because it is less costly
compared to doing a complete census.
3. There is greater error in reporting results of a
census caused by inexperienced interviewers. There
is less sampling error in a survey.
 SLOVIN’S FORMULA
The following information is needed to be able to
determine the sample size using the Slovin’s formula:
1. Population (N) – total members
2. Margin of error – allowable error margin in
research.
3. Confidence level
 SLOVIN’S FORMULA
The sample size can be obtained by the formula:

𝑵
𝒏= 𝟐
𝟏+ 𝑵 𝒆
𝑛 =𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒
𝑁 =𝑡𝑜𝑡𝑎𝑙 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛
𝑒=𝑚𝑎𝑟𝑔𝑖𝑛 𝑜𝑓 𝑒𝑟𝑟𝑜𝑟
 Example 1.
A researcher wants to conduct a survey. If the
population of a big university is 35,000, find the
sample size if the margin of error is 5%.
𝑵
𝒏= 𝟐
𝟏+ 𝑵 𝒆

n=?
N = 35,000 n = 395
e = 5% or 0.05
 Example 2.
Suppose you plan to conduct a study among
1,500 Grade 11 students enrolled in the STEM track.
How many respondents are needed using a margin
of error of 2%?
𝑵
𝒏= 𝟐
𝟏+ 𝑵 𝒆
n=?
N = 1500 n = 938
e = 2% or 0.02
 Example 3.
A teacher at Borbon National High School wants
to conduct a survey to understand students’ attitudes
toward online learning. The school has a total of
1,200 students. The teacher wants to have a margin
of error of 5%. Using Slovin’s formula, calculate the
minimum sample size required for this survey.

n = 300
 Example 4.
A researcher is studying the effectiveness of a
new teaching method in a school with 800 students.
To get reliable data while keeping the survey
manageable, the researcher decides to use a 7%
margin of error. What is the required sample size,
based on Slovin’s formula?

n = 163
 Example 5.
A community health worker wants to assess the
health habits of residents in a town with a population
of 5,000 people. They decide to allow a margin of
error of 10%. Calculate the sample size necessary
for this survey using Slovin’s formula.

n = 98
 SAMPLING
PROCEDURE
 Sampling is a formal process of choosing the
correct subgroup called a sample from a population
to participate in a research study.

To create a sample, you may follow any of the

following categories of sampling techniques.

Probability and Non-probability Sampling

 Probability Sampling is the random selection of
the samples. Each element from the population has
an equal chance of selection.

Four probability sampling procedures:

1. Simple Random Sampling
2. Systematic Random Sampling
3. Stratified Random Sampling
4. Cluster Sampling
 1. Simple Random Sampling is the most
frequently used type of probability sampling
technique.

Every member of the population has an equal

chance of being selected. This method involves
selecting participants randomly, usually through a
random number generator or lottery system.
 Example:

Suppose a high school principal wants to survey

students’ opinions on campus safety. To ensure
fairness, the principal decides to draw a random
sample of 100 students from a list of all 1,000
students enrolled. Using a random number generator,
the principal selects the students without regard to
grade level or any other characteristic.
 2. Systematic Random Sampling involves
selecting every nth individual from a list of the
population, with the starting point chosen randomly.
This method is efficient and straightforward,
especially for large populations.
 Example:

A researcher wants to survey 200 customers at a

retail store. They have a list of 2,000 customers and
decide to select every 10th customer on the list
(e.g., 1st, 11th, 21st, etc.). The researcher randomly
chooses a starting number between 1 and 10, such
as 7, and starts selecting every 10th person from that
point onward.
 3. Stratified Random Sampling divides the
population into different subgroups, or "strata,"
based on a particular characteristic (such as age,
gender, income level, etc.). Then, random samples
are drawn from each subgroup in a way that
represents each subgroup proportionally.
 Example:

A health researcher wants to study the exercise

habits of adults in a city. They divide the city’s
population into age groups: 18-30, 31-45, 46-60, and
61+. They then randomly sample participants from
each group, ensuring the sample mirrors the
population’s age distribution.
 4. Cluster Sampling involves dividing the
population into clusters, typically based on
geographical or naturally occurring groupings.
Instead of sampling individuals, entire clusters are
randomly selected, and all individuals within those
clusters are surveyed.
 Example:

A national education board wants to assess

reading comprehension levels across the country.
They divide schools into clusters by region, randomly
select a few clusters (regions), and then survey all
students within the chosen regions rather than
selecting individuals from all over the country.
 Non-Probability Sampling techniques are
commonly used when it’s impractical or unnecessary
to sample randomly.

Four probability sampling procedures:

1. Convenience Sampling
2. Snowball Sampling
3. Purposive Sampling
4. Quota Sampling
 1. Convenience Sampling involves selecting
participants who are easiest to access. It doesn’t
require a random process; rather, participants are
chosen because they are readily available to the
researcher.
 Example:

A college student conducting a quick survey on

study habits might simply ask classmates in their own
department because they’re easily accessible.
Similarly, a store manager might survey customers
already present in the store to get immediate
feedback on customer satisfaction.
 2. Snowball sampling, also known as chain-
referral sampling, is used to recruit hard-to-reach
populations. It begins with a few initial participants
who then refer others they know, creating a
“snowball” effect.
 Example:

A researcher studying the lives of migrant workers

might start with a small group of known contacts.
These contacts then refer other migrant workers they
know, gradually expanding the sample as each
participant brings in additional members from their
network.
 3. Purposive sampling, participants are chosen
based on specific characteristics or qualities that
make them particularly relevant to the research. The
researcher uses their judgment to select individuals
who best meet the study’s criteria.
 Example:

In a study on the effects of diet on diabetes, a

researcher might purposely select participants with
Type 2 diabetes who follow specific diet plans. This
focused approach helps the researcher gain detailed
insights from individuals who have direct experience
with the topic.
 4. Quota sampling involves dividing the
population into subgroups (or “quotas”) and ensuring
each subgroup is represented in the sample.
However, unlike stratified random sampling,
participants are chosen non-randomly within each
subgroup.
 Example:

A political pollster wants a sample of 500 voters

and decides that 250 should be women and 250 men
to reflect gender distribution. They continue selecting
participants from each gender until reaching the
desired quota, but do not select them randomly.