Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 66

CHAPTER 4

METHODOLGY
What is Research Design?

It refers to an overall


strategy that a
researcher uses to
logically and coherently
integrate the various
components of a study.
QUANTI RESEARCH DESIGN

Classified into five general kinds:

Descriptive
Correlational
Ex post facto
Quasi – experimental
Experimental
Descriptive

 Observeand report on a
phenomenon.
 Type of behavior, or trait.
 The use of scale
Limitation: Inability to establish
causal relationship.
Correlational

 Determining the increase/decrease


relationship.
 Notfor cause and effect but for the
association of the variables.

Limitation: Manipulation is not used.


Variables are measured as they
occur.
Ex post facto

A cause(s) from the existing effects.


 Attempts to have causal
relationship.
 Causes = Effects / Causes = Effect

Limitation: Doesn’t use experimental


manipulation.
Last two design can
be distinguished with
the use of
“Intervention”.
An intervention or
treatment involves the
manipulation of the
independent variable in
the experiment.
 Participants subjected to the intervention are referred
to as

“TREATMENT/EXPERIMENTAL
group”
 Participants not subjected to
the intervention are referred
to as “CONTROL group”
QUASI EXPERIMENTAL

 Causal Relationship between


variables.
 Occurred during the study
itself.
 Divides the subjects into
intact groups.
INTACT GROUPS

Has already been


established before the
study takes place.
(individuals’ characteristics such as
same educational background,
nationality, age bracket etc.)
Limitation: Lack of
randomness in this type of
research design.
Experimental

 Also known as the TRUE


EXPERIMENTAL.
 Aims to establish cause-effect
relationship.
 Applies variable manipulation
extensively.
 Not assigning individuals based on
their characteristics.
Limitation: (1) Not all variables can be manipulated or
controlled (Extraneous variables) – Variable that can
affect your study.
(2) Some procedures maybe impractical and unethical.
(3) Hawthorne effect – refers to the observed change in
behavior due to consciousness that they are under
observations.
Special type of Quanti Design

Prototyping – is a
development approach to
improve the planning and
execution of creative
designs such as software or
technology development.
Typically performed for
experimental purposes.
Good example of
Prototyping is the
development of World
Wide Web.
Prototyping

1. identify the objectives


2. Identify the risks
3. Formulate a hypothesis
4. Construct the prototype.
5. Examine the results.
SAMPLES AND SAMPLING

Sampling- refers to the


process of systematically
selecting individuals, units,
or groups to be analysed
during the conduct of
study. (Target population)
Generalizability –
refers to the extent
your findings can be
applied in other
contexts.
4 Ways of determining the
Sample Size

1. Heuristics
2. Literature Review
3. Formulas
4. Power Analysis
Heuristics
 Normally used in qualitative
studies because it utilizes
“Introspection”.
 -In n, it refers to the rule of
thumb for the sample size used
in a study.
Design Number of
Participants
Survey 800
Correlational 100 to 200
Ex post facto 30+
Experimental 30 or more
Literature Review
- Read similar studies to
yours and check the
sample size that they
used.
Formula
Determining the size with the
use of formula.
Power Analysis
 Most precise
 From the principle of Statistical Power.
 Power analysis is then used to determine the sample
size sufficient for measuring the effect size.
Refers to the probability of
rejecting a false null
hypothesis, thus suggesting
that there is indeed a
relationship between the
independent and dependent
variables.
Effect Size
- Refers to the degree of
difference between the
control and treatment
groups.
SAMPLING

1. Purposive Sampling


or the deliberate
selection of samples
based on their
characteristics. (in N)
Quantitative
studies often
employ random
sampling.
2. Random Sampling
(Probability Sampling)
- Involves the selection of a
group of participants from a
larger population by chance.
TYPES OF RANDOM SAMPLING

1. Simple Random


2. Stratified Random
3. Cluster
Systematic
1. SIMPLE RANDOM SAMPLING

 Individuals in a given population all have an equal


chance of being selected.
 The BEST WAY to obtain a representative sample.

Tip:


You may use fish bowl technique.
2. STRATIFIED

 Similar to simple random sampling (by chance)


 Population is divided into subgroups (strata).
 The samples are not from the population as a whole.
 Different characteristics or classes.
3. CLUSTER SAMPLING

 It involves the grouping of the


population into sub groups or
clusters.
 NOT CREATED BASED on
specific characteristics or
traits. (Hetero)
 This is to overcome a large
size.
4. SYSTEMATIC SAMPLING

 Participants are selected


from a list based on their
order in the population
or a predetermined
interval.
 Specified nth value.
RESEARCH INSTRUMENTS

 INTRUMENTS- are tools used to gather


data for a particular research topic.
Sample instruments for n:
 Performance-based or paper-and-
pencil
 Questionnaires
 Interviews
 Observations
Take note: Observation,
interview , assessment of
performance tasks are prone to
subjectivity.
Consider having “coder or
evaluator”.
Inter-coder or inter-
rater agreement refers
to the level of
concurrence between
the scores given by two
or more raters.
Three ways of developing the
instrument for n

1. Adopting
2. Modify
3. Create your own
instrument
1. Adopting

This means that you will


utilize an instrument that
has been used in well-
known institutions or
reputable studies and
publications.
2. MODIFY

- To change its content base on


the your study.
3. CREATE YOUR OWN

- To formal create your


own and undergo to the
validity and reliability
tests.
INSTRUMENT VALIDITY

Validity refers in the


degree to which an
instrument measure
what it is supposed to
measure.
 Speaking proficiency – Speaking tests have greater validity that
writing tests.
TYPES OF VALIDITY

1. Face
2. Content
3. Construct
4. Concurrent
5. Predictive
FACE VALIDITY

When it “appears” to
measure the variables
being studied.

Note: This is prone to


subjectivity.
CONTENT VALIDITY

Degree to which an instrument


covers a representative
sample or specific elements of
the variable to be measured.
 List of specifications
 Subjective process
CONSTRUCT VALIDITY

Degree to which an instrument


measures the variables being studied
as a whole.
 Measures what should exist
theoretically.
 CONSTRUCT – an
intangible/abstract variable, e.g.
personality, intelligence, or moods.
The last two types
are Classified as
Criterion Validity.
Criterion Validity – refers to
the degree that an
instrument predicts a
variable’s characteristics in a
certain way.
- Evaluated through
statistical methods.
4. CONCURRENT VALIDITY

When it is able to
predict results SIMILAR
to those of a test
already validated in
the past.
 Admission test=NAT
5. PREDICTIVE VALIDITY

When it produces results


SIMILAR to those of
another instruments that
will be employed in the
future.
Admission tests in Math= students’ performance in
mathematics
INSTRUMENT RELIABILITY

Reliability-refers to the
consistency of an
instrument’s measures.
Aspect involved in the
accuracy of
measurement.
FOUR TYPES OF RELIABILITY

1. Test- Retest


2. Equivalent forms
reliability
3. Internal Consistency
reliability
4. Inter-rater reliability
1. Test-retest reliability

 Achieved by administering
an instrument twice to the
same group of participants
and the computing the
consistency of scores.
 Conduct the retest after a short period of time
2. Equivalent forms reliability

Is measured by administering
two tests identical in all aspects
except the actual wording of
items.
Two test have the same
coverage. (level of difficulty)

Pre test and post test.


3 Internal consistency

 Is a measure of how well


the items in two
instruments measure the
same construct.
 Three ways to measure I-C
reliability:
3. 1 The split half method/
Split half coefficient
 Obtainedthrough administering
a single instrument aimed at
measuring only one construct.
 While computing, the results
are divided into two sets for
the comparison.
3. 2 Cronbach’s Alpha

Measures reliability with


respect to each item and
construct being
examined by the
instrument.
3.3 Kuder- Richardson
formula

Test reliability in
terms of instruments
of a dichotomous
nature, such as yes or
no tests.
4. Inter-rater reliability

Measures the consistency of


scores assigned by two or more
raters on a certain set of results.
The KAPPA COEFFICIENT is one
most popular statistical tools in
measuring inter-rater reliability.
The higher the KAPPA, the more reliable the instrument is. (0.70
reliable)
Informed consent – is a
document that explains the
objectives of the study and
the extent of the
participants’ involvement in
your research.
Utilize triangulation in your
method.

Triangulation is a technique
for validating data using two
or more sources and
methods.
Data Analysis Procedure

Data Analysis –
involves the use of
statistical tests to
address your research
questions or
objectives.
Bivariate data – the
data involving these
two variables
(independent and
dependent)
Considerations in Data
Analysis

PARAMETRIC test –rests on


a number of assumptions
about the distribution of
data (frequency of their
occurrence) 30 or more
per group.
NON – PARAMETRIC –
rest on a few or no
assumptions regarding
the distribution of data.
Lower that 30
participants

You might also like