Course Module for Education Research 1 & 2

POPULATION AND SAMPLING / DATA SOURCE

Sampling
- Selection of a subset (statistical sample) of individuals from within a statistical population to estimate characteristics of
the whole population.
-Used to select a sample from within a general population as it represents the population in question eliminating bias in
the selection process.
- This is a process which involves taking a part of the population, making observations on these representative groups
and generalizing the findings to the bigger population (Ary, Jacob & Razavieh, 1981).
- This refers to strategies which enable you to pick a subgroup from a larger group and then use this subgroup as a basis
for making judgements about the larger group (Vockell, 1983).

Steps used in Sampling

1. Identification of the population;
2. Determining the required sample size;
3. Selection of the sample

Determining a Sample Size for Quantitative Study

Use a formula of Slovin (1960)
n = N / 1 + Ne²

where:
n = sample size
N = population size
e = desired margin of error (percent allowance for non-precision because of the use of the sample instead of the
population)

Survey Sample Size Margin of Error Percent*

2,000 2

1,500 3

1,000 3

900 3

800 3

700 4

600 4

500 4

400 5

300 6

200 7

100 10

50 14

*Assumes a 95% level of confidence

What is the representative sample if the population is 9000 and the margin of error you allow is 2%?
n = N / 1 + Ne²
n = 9000 / 1 + 9000 (0.02)²
n = 9000 / 1 + 9000 (0.0004)
n = 9000 / 1 + 3.6
n = 9000 / 4.6
n = 1,957

n = 500 / 1 + 500 (0.04)²

n = 500 / 1 + 500 (0.0016)
n = 500 / 1 + 0.8
n = 500 / 1.8
n = 278

n = 500 / 1 + 500 (0.02)²

n = 500 / 1 + 500 (0.0004)
n = 500 / 1 + 0.2
n = 500 / 1.2
n = 417

Source:https://www.isixsigma.com/tools-templates/sampling-data/margin-error-and-confidence-levels-made-simple/

Caution: When the normal approximation of your population is small or poor, this sample size formula (Slovin) does not
apply.

Acceptable sizes depending on the type of quantitative research:

• Descriptive Research – 10% of the population; smaller population: a min. of 20% is required
• Correlational Research – 30 subjects
• Ex post facto or casual comparative research – 15 subjects per group
• Experimental research – 15 subjects per group

Suggested sample size for qualitative study:

Qualitative Research
Focus Method Sample Size
Design

People who have experienced

Phenomenological Interviews, FGD 5 to 25
a phenomenon

Interviews/FGD,
Develop a theory from
Grounded Theory then open and axial 20 to 60
grounded in field data
coding

Observation,
Ethnography Context or culture —
interviews

Interviews, FGD,
Organization, entity,
Case Study documents, reports, —
individual, or event
observations

Individual experience & Interviews,

Historical/Biographical 1 to 2
sequence documents

Underlying meaning of a Documents,

Content Analysis certain document, text (paper interpretation & 0
or electronic files) coding of textual
 material

SAMPLING TECHNIQUES

I. PROBABILITY RANDOM SAMPLING - All members of a group (population or universe) have an equal and
independent chance of being selected. Pick the samples randomly without any basis or reason for picking. May have risk
of getting responses that are not significant.
- These are sampling techniques where each member of the population has an equal chance to be selected and included
in the sample.

1. Simple Random Sampling - undertaken through the use of the fishbowl or the lottery technique; or the table of
random numbers where all the members of the population are listed and assigned numbers. Number of samples can be
determined using the Slovin’s formula. If there is a big number of cases (500 or more) then 10 to 20% of the population
can be taken. For smaller population (less than 500), about 50% can be taken. For case studies, a maximum of five cases
can be used.

2. Systematic Random Sampling - A strategy for selecting the members of a sample that allows only chance and a
system to determine membership in the sample. This can be used by selecting every nth member from the list of all
population members.
e.g.,
every number – 50%
every 5th number - 25%
every 20th number - 5%

3. Stratified Random Sampling-Undertaken by first dividing the population into sub-groups or categories using
appropriate classification variables then randomly selecting individuals from each subgroup
e.g., The population is composed of all UP graduate students enrolled during the second semester of school year 2009 –
2010. Examples of variables that can be used to classify the members of the population are specialization and sex. If
there are 20 specializations then there will be 40 sub-groups. The members of each sub-group are identified then
selection of sample from each subgroup is made at random.

4. Cluster Random Sampling - Occurs when you select the members of your sample in clusters rather than in using
separate individuals. Clusters or groups from different categories are first selected. The clusters are internally
heterogeneous, that is, they contain all types of possible respondents.
e.g., The research population is composed of all high school students in the public schools in Manila. Each public school
is a cluster from which the researcher will randomly select the participants.

5. Multi–Stage Sampling - Done by randomly selecting samples starting from the biggest groups to the smallest sub
groups.
e.g.,
The population is described as all Filipino mothers.
* The researcher starts by selecting regions from the three islands, from each region, provinces, cities/municipalities,
barangays then to households.
* In all stages, sampling is done randomly.

Total enumeration sampling is a research method that involves studying the entire population of interest, rather than a
sample. It's also known as a census.
II. NON-PROBABILITY OR NON-RANDOM SAMPLING - Usually selected on the basis of their accessibility or by the
purposive personal judgment of the researcher. Members of the population do not have equal chance to be selected or
taken as part of the sample. Samples obtained using these techniques may not be very representative of the population.

1. Convenience Sampling - Used by a researcher who gets a sample composed of members of the population who are
available and accessible to him/her. He does not have to involve all the members of the population in the selection
process as long as he/ she can get enough cases from those who are available. In simple terms, this is based on the
convenience of the researcher.
e.g.,
You want to know the opinion of Filipinos about national reconciliation in the Philippines through telephone interviews…
Who are you going to interview?

2. Purposive Sampling - Participants are selected or sought after based on pre-selected criteria determined by the/a
research question/s. They can also be selected based on their expertise where they can provide in-depth detailed
information about their topic which is the subject of their research.
e.g.,
Find out the similarities and differences between the dialects spoken in your province.
Who would you ask of their opinion/reaction about this?

3. Snowball Sampling- Select one or more research participants who will refer other participants that may contribute to
the data needed in the research.

4. Quota Sampling- Similar to the stratified random sampling technique that the researcher also classifies the population
into subgroups first before selecting individual members. The samples will match the population with regard to the chosen
set of characteristics. Examples are: age, sex, race, marital status.
e.g.,
Determine the most favored soft drinks from a population of televiewers.
Interview televiewers who drink soft drinks and continue the process until you arrive at your quota.
Ethical Considerations (excluded in content analysis)
• Identify the ethical principles applicable to your research
• Discuss what you did exactly to ensure adherence to the ethical standards:

THE CHARACTERISTICS, PROCESSES, AND ETHICS OF RESEARCH

Ethics - norms for conduct that delineate the boundary between acceptable and unacceptable behavior; -sense of right
and wrong
-an approach, process or perspective for choosing how to act on certain issues or situation, and for probing complicated
problem or issues

Ethical Standards in Research

1. VOLUNTARY PARTICIPATION - Never force anyone to take part in your study. Explain what your research is about
and secure their signature as an indication that they voluntarily participating. Ensure that they may refuse to participate at
any stage of the research.
*Informed Consent - The participants must be fully informed about the nature of research, its purposes and potential risk
and benefits.

2. BENEFICENCE AND NONMALEFICENCE - This is a fundamental ethical principle in research, which means, “to do
good” and “to do no harm” to study participants.
*Respect for Human Dignity - The rights of the study participants must be well protected and respected.

3. CONFIDENTIALITY – Assure participants that personal information is confidential even after the research is done.

4. PRIVACY – work with participants at a place and time that they are most convenient. During the data collection, make
sure that all information collected are kept

5. JUSTICE AND FAIRNESS - Study participants deserve fair and equitable treatment before, during and after the study
period. The researcher should provide equal chances in the selection process, must comply with agreements in regard to
procedures, techniques or benefits due to participants.

6. ACCURACY – data collected and procedure in collecting thereof should be organized. Introduce the concept of
plagiarism and data manipulation. Do not misrepresent the participants.
*Intellectual honesty and respect - Giving acknowledgment/recognition or due respect to the original/previous work of art.
*Things to avoid: fraudulent practices like falsification, alteration, misrepresentation, concealing of findings - biased or
subjective language - labeling people / singling out a group - assuming authorship of another’s work (plagiarism)

ETHICAL CONSIDERATION

Sample Composition:

The researcher followed ethical guidelines, as specified by the Research Ethics Committee, Philippine Normal
University. This included undergoing an Ethics Review process before engaging interview participants to ensure that
procedures were fair and unbiased to all involved. Complete information regarding the nature of the study was included in
the communication letters and was further explained during the actual interview (See Appendices A & B). The interview
was conducted in the LRP’s own locality, either at home or in the Barangay Hall, and in his or her most convenient time.
Approximately one hour for the interview was spent with the permission of the participants.
The data collection tools in the form of questionnaires and word list (See Appendices D & H), as well as the
criteria for the selection of participants discussed in section 2.2, are free from gender, class, ethnic, and cultural biases.
The research data remained confidential throughout the study and the researcher obtained the participants’ permission to
use their real names in the research report. Great care was taken to ensure that these participants were kept completely
anonymous in the research. All participants’ forms were kept secure, locked and properly coded and accessible by
authorized persons only.
The informed consent process was observed. This involved ensuring that the participants were aware that they
were participating in research and asking for their consent to participate with the option of withdrawing anytime (See
Appendix C). The informed consent also included certain aspects of the research process which could affect the
participants’ willingness to participate such as the duration of the interview, audio and video recordings, sharing of
participants’ information to research conferences and future researchers. Finally, the participants and community officials
were given the option of being sent the transcription of their interview and being sent a summary of the results of this
research study.

SAMPLE ONLY
SAMPLE ONLY
Instrumentation
-Identify instruments used such as interview/open-ended survey questionnaires, observation checklist, document analysis
tools, picture/video prompts, etc.
-Explain how the instrument was developed for the study
-Identify parts of interview guide and explain their purpose: demographic questions, interview questions on research
problem number 1, 2, 3, and so on.
-Identify parts and features of other instruments and explain their purpose
-Cite sources if necessary
-Discuss how the instruments were validated: Did you conduct a pilot test? Explain the process and issues uncovered.
-Discuss how you arrived at your final instrument