Vietnam National University –HCMC

University of Social Sciences & Humanities

Faculty of English Linguistics & Literature

SAMPLING
Lê Hoàng Dũng, PhD
[email protected]
 Aims & contents

What? Why?

How?

11/19/2024 Research Methods –LHD 2

 How overwhelmed are you now?
How prepared are you for your sampling?

11/19/2024 Research Methods –LHD 3

 Key questions
•What factors should be
considered when sampling?
•What/Which type of sampling
should I choose? Why?
•How large should my sample be?
•How many respondents should I
have in my sample?

11/19/2024 Research Methods –LHD 4

 HOW? How many respondents in a
sample?

• Question: How large

should my sample be?
• Answer: It depends ….

on WHAT?

11/19/2024 Research Methods –LHD 5

 GROUP DISCUSSION 1
(15 minutes)
• What factors affect the sampling
process?
• List as many factors as you can
• Identify the top five important
factors
• Share the discussion output with
your class

11/19/2024 Research Methods –LHD 6

 WHY? Why do researchers
need to sample?
Sampling

Inference

11/19/2024 Research Methods –LHD 7

 WHAT?
Sample & Population

• A sample is any part

• "Population," as of a population of
used in research, individuals that will
refers to all the participate in the
research study and on
members of a whom information is
particular group. obtained.
• It is the group of • The best sample is
interest to the one that is
representative of the
researcher, the group larger group to whom
to whom the we would like to apply
researcher would like the results of the
to generalize the research study.
results of the study.
11/19/2024 8
HOW & WHAT? Types of samples

Random Nonrandom
(Probability/ (Non-probability
Representative) Non-representative)
• Random sampling: • Nonrandom sampling:
– simple random sampling – systematic sampling
– stratified random – convenience sampling
sampling – purposive sampling
– cluster random sampling

11/19/2024 Research Methods –LHD 9

Representative
vs. Non-
representative
sampling

Research Methods –LHD

 Random
Simple random sampling
• A simple random sample: a sample selected
from a population in such a manner that all
members of the population have an equal
chance of being selected.

E.g.
• Putting the names of
everyone in the accessible
population in a bag and
then randomly drawing
names from the bag. Those
names that are selected
would be the names of the
individuals in the sample.

11/19/2024 Research Methods –LHD 11

 Using random table
• The table of random numbers is a
table of numbers listed in a random
order.
• This table can be used to select
individuals at random.
– A list of names can be numbered.
– The numbers that are selected from the
table of random numbers will correspond
to the names that are selected for the
sample.

11/19/2024 Research Methods –LHD 12

 Part of a Table of Random Numbers

011723 223456 222167 032762 062281 565451

912334 379156 233989 109238 934128 987678
086401 016265 411148 251287 602345 659080
059397 022334 080675 454555 011563 237873
666278 106590 879809 899030 909876 198905
051965 004571 036900 037700 500098 046660
063045 786326 098000 510379 024358 145678
560132 345678 356789 033460 050521 342021
727009 344870 889567 324588 400567 989657
000037 121191 258700 088909 015460 223350
667899 234345 076567 090076 345121 121348
042397 045645 030032 657112 675897 079326
987650 568799 070070 143188 198789 097451
091126 021557 102322 209312 909036 342045

Research Methods –LHD

 Stratified random sampling
• A stratified random sample is one in which the accessible
population is first divided into subsets or strata, and then
individuals are selected at random from each stratum.

• E.g.: a population of high

school students can first be
divided into freshman,
sophomores, juniors, and
seniors, then individuals can
be selected at random from
each of these groups.

Advantage: All groups are represented in the

correct proportions and yet the method retains the
benefits of random sampling within each of these
groups.
11/19/2024 14
 Cluster random sampling
• A cluster random sample is a sample in which
existing clusters or groups are selected and then
each member of the cluster is used in the research.

E.g.: if classes
are selected at
random and
then the
students in
each class
become
participants in
the research
study, the
classes are the
clusters.
11/19/2024 Research Methods –LHD 15
 Two-stage random sampling
• A two-stage random sample is one in
which clusters are first randomly
selected and then individuals are
selected from each cluster.

• E.g.: if classes are selected at

random and then a random selection
of students from each selected class
is chosen to participate in the study.

11/19/2024 Research Methods –LHD 16

Random sampling methods

Research Methods –LHD

11/19/2024 Research Methods –LHD 18
 Notes:
(1) The smaller the number of
cases there are in the wider,
whole population, the larger the
proportion of that population must
be which appears in the sample;
the converse of this is true: the
larger the number of cases there
are in the wider whole population,
the smaller the proportion of that
population can be which appears
in the sample.

(2) As the population increases

the sample size increases at a
diminishing rate and remains
constant at slightly more than 380
cases.

Cohen, L. Manion, L., & Morrison, K.

11/19/2024 (2007, pp.100-118) 19
 Sample size, confidence levels &
sampling error

Cohen, L. Manion, L., & Morrison, K. (2007, pp.100-118)

11/19/2024 20
11/19/2024 Research Methods –LHD 21
 Standard error Z

Exhibit. 14a. Confidence levels and the

normal curve (Cooper, R.D. & Schindler, S.P.,
https://www.surveysystem.com/sample-size- 2006).
formula.htm

11/19/2024 Research Methods –LHD 22

 Cooper & Schindler (2006)

11/19/2024 Research Methods –LHD 23

11/19/2024 Research Methods –LHD 24
Nonrandom
systematic sampling
• A systematic sample is a sample obtained by
selecting every nth name from a list of names.
• With systematic samples once the first name is
selected the entire sample is automatically
determined. Thus, only certain samples are
possible.

11/19/2024 Research Methods –LHD 25

 Convenience sampling
• A convenience sample
– is any group of individuals that is
conveniently available to be studied,
– is readily accessible to the researcher,
– is often an intact group.
• E.g.: the students or volunteers are
chosen conveniently from one class ,
this class forms a convenience
sample

11/19/2024 Research Methods –LHD 26

Convenience
Sampling

Research Methods –LHD

 Purposive sampling
• A purposive sample is a sample
selected because
(i) the individuals have special
qualifications of some sort, or because of
prior evidence of representativeness; or
(ii) the researcher believes they will be
representative of the population.
• Purposive sampling should only be
used when the researcher has a
complete understanding of the
characteristics in the population, as well
as those of the individuals selected for
the sample.
11/19/2024 Research Methods –LHD 28
 Purposive sampling

11/19/2024 Research Methods –LHD 29

Summary: Nonrandom sampling methods

Research Methods –LHD

 Another categorization

Howitt, D., & Cramer, D. (2005, p. 75-79)

11/19/2024 Research Methods –LHD 31
11/19/2024 Research Methods –LHD 32
 SHARING OF GROUP
DISCUSSION OUTPUT
(5 minutes)

• What factors affect the sampling

process?

11/19/2024 Research Methods –LHD 33

 HOW? How many respondents in a
sample?

• Question: How large

should my sample
be?
• Answer: It depends
….
…. large enough to be an accurate
representation of the population
…. large enough to achieve statistically
significant results
11/19/2024 Research Methods –LHD 34
How many respondents in a sample?
• Samples should be as large as a
researcher can obtain with a
reasonable expenditure of time and
energy.
• A recommended minimum number
of subjects is 100 for a descriptive
study, 50 for a correlational study,
and 30 in each group for
experimental and causal-
comparative studies. (!?)
11/19/2024 Research Methods –LHD 35
 WHY? Some general rules for
sampling
• The greater the dispersion or variance within the
population, the larger the sample must be to be
provide estimation precision.
• The greater the desired precision of the
estimate, the larger the sample must be
• The narrower or smaller the error range, the
larger the sample must be.
• The higher the confidence level in the estimate,
the larger the sample must be.
• The greater the number of subgroups of interest
within a sample, the greater the sample size
must be, as each subgroup must meet minimum
sample size requirements.

11/19/2024 Research Methods –LHD 36

 Examples

11/19/2024 Research Methods –LHD 37

 ACCESS: Target vs. Accessible Populations
Research • The effects of computer-assisted instruction
problem to be on the reading achievement of first- and
second-graders in HCMC
investigated

Target • All first- and second-grade children

population in HCMC

• All first- and second-grade children in

Accessible Tran Hung Dao elementary school
population (District 1, HCMC)

Ten percent of the first- and second-

Sample grade children in Tran Hung Dao
elementary school (District 1, HCMC)

11/19/2024 Research Methods –LHD 38

 Example
The attitudes of fifth-year teachers-in-
training toward their student teaching
experience

All fifth-year students enrolled in

teacher-training programs in VN

All fifth-year students enrolled in

teacher-training programs in USSH

Two hundred fifth-year students selected

from those enrolled in the teacher-
training programs in the USSH???
11/19/2024 Research Methods –LHD 39
 2 premises of sample VALIDITY
Accuracy Precision
• An accurate (unbiased) • Precision is
sample is one in which measured by the
the under-estimators standard error/
offset the over- deviation (SE/SD) of
estimators. estimate
• Increasing the sample
size can reduce • The smaller the SD,
systematic variance as the higher the
a cause of error. precision of sample

11/19/2024 Research Methods –LHD 40

 (Cohen, 2006, p.107-8)
11/19/2024 Research Methods –LHD 41
 Concluding ideas: 4 key
factors in sampling
(1) the sample size
(2) the representativeness of the
sample and parameters of the
population
(3) access to the sample
(4) the sampling strategy to be used
Cohen, L. Manion, L., & Morrison, K.
(2007, pp.100-118)

11/19/2024 Research Methods –LHD 42

 GROUP DISCUSSION 2
(15 minutes)

• What difficulties related to

sampling do you encounter in your
group project (A2)?
• Please share your difficulties and
identify how you will solve the
problems ?

11/19/2024 Research Methods –LHD 43

 GROUP PROJECT PRACTICE (& HOMEWORK)

• In groups, write the METHODOLOGY

chapter (i.e. chapter 3) of your GROUP
PROJECT, mainly focusing on:
– Your research design (i.e. what research
method to be applied in your study?)
– Your sampling strategy and sample to be
chosen; explain why & how you will do so
– Your research tools to be used
• WHAT to ask,
• WHY to ask, and
• HOW to analyse what (the data) you will collect.
11/19/2024 44
 References
• Borg, W. R., & Gall, M. (1979). Educational Research: An Introduction
(3rd ed.). New York: Longman. (p.195)
• Cooper, R.D. & Schindler, S.P. (2006). Business Research Methods. (9th
Ed.). NY: McGraw-Hill Irwin.. (Ch. 15)
• Cohen, L. Manion, L., & Morrison, K. (2007). Research methods in
Education. London: Routledge.
• Creswell, J.W. (2012). Educational Research –Planning, Conducting,
and Evaluating Quantitative and Qualitative Research. Fourth edition.
Boston: Pearson Education, Inc.
• Howitt, D., & Cramer, D. (2005). First Steps in Research and Statistics.
London: Taylor & Francis Group.
• Mackey, A. & Gass, S. M. (2005). Second Language Research –
methodology and design. New Jersey: Lawrence Erlbaum Associates,
Publishers. Available at: http://www.tesl-
ej.org/pdf/ej60/sl_research_methods.pdf

11/19/2024 Research Methods –LHD 45

 Thank you

11/19/2024 Research Methods –LHD 46