26/03/2014
PLG 501 Research Methods in Education
Sampling
Selecting
Sample and
Measuring
Instruments
.
The process of selecting
a number of individuals
for a study in such a way
that the individuals
represent the larger group
from which they were
selected.
Nor Hashimah Hashim, Prof. Dr.
School of Educational Studies,
Universiti Sains Malaysia
Sampling
Quantitative Sampling
Purpose is to gain information about
a larger population. A population is
the group to which a researcher
would like the results of a study to be
generalizable.
Random sampling
Quantitative Non-random
sampling
Qualitative
Issues:
nature of the sample
size of the sample
method of selecting the
sample
Purposive sampling
Quantitative Sampling
Quantitative Sampling
Terminology
Population: all members of a specific group
Important issues
Target population population to which the
researcher ideally wants to generalize.
Accessible p
population
p
the p
population
p
to which
the researcher has access.
Sample: a subset of a population
Subject: a specific individual participating in
a study
Sampling technique: the specific method
used to select a sample from a population.
Representation the extent to which the sample is
representative of the population.
Demographic characteristics
Personal characteristics
Specific traits
Generalization the extent to which the results of the
study can be reasonably extended from the sample to
the population.
26/03/2014
Quantitative Sampling
Sampling error
The chance occurrence
that a randomly selected
sample is not
representative of the
population due to errors
inherent in the sampling
technique.
Random nature of errors
Controlled by selecting
large samples.
Quantitative Sampling
Three
Sampling bias
Some aspect of the
researchers sampling
design creates bias in
the data.
data
Non-random of errors.
Controlled by being
aware of sources of
sampling bias and
avoiding them.
important steps in sampling
Identify a population
Define the sample size
Select the sample
Rules for sample size
As many subjects as possible
30 subjects per group for correlational,
causal-comparative, true experimental design.
10-20% percent of the population for
descriptive design.
Quantitative Sampling
Selecting Samples
The larger the population size, the smaller the
percentage of the population needed to get a
representative sample.
Population of less than 100, use the entire
population.
Population is about 500, sample 50%.
Population is about 1500, sample 20%.
Population is larger than 5000, sample
400.
Random
Samples
Simple random
Stratified
Cluster
Systematic
Nonrandom
samples
Convenience
Purposive
Quota
Random Samples
10
1. Simple Random Sampling
Selecting subjects so that all members of a population
have an equal and independent chance of being selected.
Also known
as
probability
sampling
Best method
to achieve a
representative
sample of the
population
Advantages
Easy to conduct.
High probability of achieving a
representative sample.
Meets assumptions of many statistical
procedures.
Four techniques:
1. Simple random
2. Stratified
3. Cluster
4. Systematic
Disadvantages
Identification of all members of the
population can be difficult.
Contacting all members of the sample can
be difficult.
11
12
26/03/2014
Simple Random Sampling
2. Stratified Sampling
Selection Process
Selecting subjects so that relevant subgroups in the
population (e.g., strata) are guaranteed representation.
A strata represents a variable on which the researcher
would like to see representation in the sample.
Identify and define the population.
Determine the desired sample size.
List all members of the population.
Assign all members on the list a consecutive
number.
number
Gender
Select an arbitrary starting point from a table of
random numbers and read the appropriate number
of digits.
Ethnicity
Grade level
If the number corresponds to a number assigned
to an individual in the population, that individual is
in the sample; if not, ignore the number.
Continue until the desired number of subjects have
been selected.
13
14
Stratified Sampling
Stratified Sampling
Proportional and non-proportional (e.g., equal size)
Advantages
Proportional same proportion of
subgroups in the sample as in the
population
More precise sample
Can be used for both proportional and nonproportional samples
Representation of subgroups in the sample
If a population has 45% females and 55% males,
the sample should have 45%
% females and %%
males.
Disadvantages
Non-proportional different, often equal,
proportions of subgroups
Identification of all members of the population can be
difficult.
Identifying members of all subgroups can be difficult.
Selecting the same number of children from each
of the five grades even though there are different
number of children in each grade.
15
16
Stratified Sampling
3. Cluster Sampling
Selection process
Identify and define the population
Determine the desired sample size
Identify the variable and subgroups (e.g., strata) for which
you want to guarantee appropriate representation
Selecting subject by using groups that have similar
characteristics and in which subject can be found.
Clusters are locations within which an intact group of
members of the population can be found. Examples:
Neighborhoods
School districts
Schools
classrooms
Classify all members of the population as members of one
of the identified subgroups.
17
18
26/03/2014
Cluster Sampling
Cluster Sampling
Multistage sampling involving the use of two or more
sets of clusters.
Randomly select a number of school districts from a
population of districts.
Randomly select a number of schools from with each of the
school districts
Randomly select a number of classrooms from within each
school
Advantages
Very useful when populations are large and spread over a
large geographic region
p
Convenient and expedient
Do not need the names of everyone in the population
Disadvantages
Representation is likely to become an issue
Assumptions of some statistical procedures can be
violated.
19
20
Cluster Sampling
4. Systematic Sampling
Selection process
Selecting every Kth. subject from a list of the
members of the population
Identify and define the population
Determine desired sample size
Identify and define a logical cluster
Advantages
List all cluster that make up the population of clusters
Estimate the average number of population members per
cluster
Very easily done
Determine the number of clusters needed by dividing
the sample size by the estimated size of a cluster
Disadvantages
Randomly select the needed numbers of clusters
Susceptible to systematic exclusion of some subgroups.
Include in the study all individuals in each selected
cluster
Some members of the population dont have an equal chance
of being included .
21
22
Systematic Sampling
Non-random Samples
Also known as non-probability sampling
Use of methods that do not have random sampling at
any stage.
Obtain a list of the population.
Useful when the population cannot be describe.
Determine what K is equal to by dividing the size of
the population by the desired sample size.
Three techniques:
Selection process
Identify and define the population.
Determine the desired sample size.
Start at some random place in the population list.
1.
Convenience
Take every Kth individual on the list.
2.
Purposive
If the end of the list is reached before the desired
sample is reached, go back to the top of the list.
3.
quota
23
24
26/03/2014
1. Convenience Sampling
2. Purposive Sampling
Selection based on the researcher experience and
knowledge of the individual being sampled. Usually
selected for some specific reason.
Knowledge and use of a particular instructional
strategy
Experience
p
Being in a specific setting such as a school
changing to a teacher-based decision-making
process
Need for a clear criteria for describing and defending
the sample.
Concerns related to representation and generalizability .
Selection based on the availability of
subjects:
Volunteers
Pre-existing
Pre existing groups
Concerns related to representation
and generalizability
25
3. Quota Sampling
26
Qualitative Sampling
.
Selection based on
the exact
characteristics and
quotas of subjects in
the sample when it is
impossible to list all
members of the
population.
Unique characteristics of qualitative
research
In-depth inquiry
Immersion in the setting
Importance of context
Appreciation
A
i ti
off
participants perspectives
Description of a single
setting
Concerns with
accessibility,
representation, and
generalizability.
The need for alternative
sampling strategies
27
Qualitative Sampling
28
Measuring Instruments
Purposive techniques relying on the
experience and insight of the researcher
to select participants
Homogenous small groups of participants
who fit a narrow homogenous topic
Criterion all participants who meet a
defined criteria
Snowball initial participants lead to other
participants
Sample size very small
29
30
26/03/2014
Type of Measuring Instruments
Cognitive
Tests
Achievement
Tests
Aptitude
Tests
Type of Measuring Instruments
Affective Test
Attitude
Scales
Cognitive
Tests
measure
intellectual
processes.
Achievement tests measure the current
status of individuals on school-taught
subjects.
Aptitude
test
are used to predict in the future. General
aptitude tests typically ask the test
taker to perform a variety of verbal and
nonverbal tasks.
Affective
test
are assessments to designed to
measure characteristics related to
emotion. Most affective tests are selfreport measures in which the individual
responds to series of questions about
him/herself.
31
32
33
34
Type of Measuring Instruments
Five basic types of scales are used to measure attitudes:
Likert scales, semantic differential scales, rating scales,
Thurstone s cales and Guttman Scales. The first is
commonly used.
Attitudes scales ask respondents to state their
feelings about various objects, persons and
activities. People respond to Likert scale by
indicating their feelings along a scale such as
strongly agree, agree, undecided, disagree and
strongly disagree.
Criteria for Good Measuring
Instruments
Validity
Reliability
Content validity
Stability
Criterion-related
related validity
Criterion
Equivalence
Construct validity
Internal consistency
Consequential validity
Split-half reliability
Validity
Kuder-Richardson reliability
Rater reliability
35
Validity is the degree to which a test
measures what it is supposed to
measure, thus permitting appropriate
interpretations of test score.
Each intended test use requires its own
validation.
Validity is measure on a continuum tests are highly valid, moderately valid
or generally invalid.
36
26/03/2014
Validity
Content
validity
Criterionrelated
validity
Validity
Assesses the degree to which a test
measures an intended content area.
Determined by expert judgment of
item and sample validity, not by
statistical means.
Determined by related performance
on a test to performance on a
second test or other measure.
Construct
validity
A measure of whether the construct
underlying a variable is actually
being measured.
Determined by a series of validation
studies that can include content and
criterion-related approaches.
Consequential
validity
Concerned with the potential of test
to create harmful effects for test
takers.
37
Reliability
Reliability
Reliability is the degree to which a test
consistently measures whatever it
measures
Reliability is expresses numerically,
usually a coefficient ranging from 0.0 to
1.0; a high coefficient indicates high
reliability.
38
Stability
A degree to which test scores are consistent over
time.
Determined by correlating scores from the same
test, administered more than once.
E i l
Equivalence
A degree to which two similar forms of a test
produce
d
similar
i il scores from
f
a single
i l group off test
takers.
Internal
consistency
Deals with the reliability of a single test taken at
one time.
Measures the extent to which the items in the test
are consistent among themselves and with the test
as a whole.
39
40
Reliability
Split-half
reliability
Determined by dividing a test into
two equivalent halves (odd items
vs. even items)
KuderRichardson
Ri
h d
reliability
Deals with tine internal consistency
off
test
that
h
are
score
dichotomously (right, wrong).
Rater
reliability
Important when scoring tests that
are potentially subjective.
Thank you.
41
