RESEARCH DESIGN

Categories of Research by
METHOD
Quantitative Method

Qualitative method

Mixed Method
 Research Design

• a logical model that shows the strategies for

sample selection, development of
measurement tools, data collection as well as
methods of data processing and analysis

• the framework, a blueprint for the research

study which guides the collection and analysis
of data.
 Research Design
• comprehensive master plan of the research
study to be undertaken, giving a general
statement of the methods to be used.
• function of a research design is to ensure that
requisite data in accordance with the problem
at hand is collected accurately and
economically.
 Research Design

The internal validity (methodological

soundness) of research is strengthened by the
correct choice of research design and the
soundness and appropriateness of decisions
that pertain to sampling, instrumentation,
data collection and analysis.
External validity relates to the generalizability of
experimental findings to the “real“ world.
 Quantitative Research Design

• Selection of a research design depends mainly

on the objectives of the study:

1 To describe, compare, associate (descriptive

designs)
2. To test causal relations (experimental designs)
 Descriptive Design
• Describe the phenomenon under study
attempting to establish a relationship between
factors
• can be used to draw inferences about the
possible relationships between variables.
• are aimed only at providing accurate
descriptions of variables relevant to the
problem under consideration
 Descriptive Design
Can be used for the following purposes.
a) To describe the characteristics of certain groups of
interest e.g. users of the product, potential users,
non users, possible receivers of promotional
communication by the company and so on.
b) To estimate the proportion of people in a given
population who behave in a certain way for
example the proportion of consumers who are
prone to deals.
 Descriptive Design
Can be used for the following purposes.
c) To make specific predictions for specified
future periods.
d) To develop inferences whether certain
variables are associated, for example income
and shopping place preference.
 Descriptive Research Design
Types of Quantitative Research Design
A. Descriptive Design
• Survey
• Prospective designs (longitudinal)
• Retrospective designs (case-control designs)
• Correlational designs
 Descriptive Research Design

SURVEY
• Used when a researcher seeks to gather
information from a large number of people at
one point in time
• Examples
Population census
Prevalence studies
KAP studies
 Descriptive Research Design

PURPOSIVE SURVEY
• Respondents are selected intentionally based
on he needs of the study
CROSS-SECTIONAL SURVEY
• Respondents are selected randomly
• RANDOM – giving each member of the
population an equal chance of being selected
as a participant of the study
 Descriptive Research Design

PROSPECTIVE DESIGNS
(longitudinal designs)

EG X DV
Same
population CG DV
 Descriptive Research Design

EXAMPLE (prospective design)

An investigator is interested in determining he
effects of a smoking cessation program on the
reduction of smoking behavior among a group of
heavy smokers. He then recruits 100 heavy
smokers who are initially comparable in terms of
extraneous characteristics such as number of
sticks smoked daily, duration of smoking,
occupation, age, gender ands other relevant
factors
 Descriptive Research Design

Next, he randomly assigns (by lottery or flipping

of the coins) 50 recruits to the experimental
group(EG) and the other 50 to the control
group (CG). The EG will be exposed to the
smoking cessation program (intervention)
once a week for three months, while the CG
will not be provided the smoking cessation
program.
 Descriptive Research Design

A the end of the intervention, members of the

EG will be followed up each month up to one
year to determine the impact of the
intervention (e.g., how many among them
have completely stopped smoking). The same
thing will be done for the CG.
 Descriptive Research Design

Take note that the outcome factor (cessation of

smoking) is measured more than once. In the
example above, the number of quitters
(dependent variable) is determined every
month for one year.
 Descriptive Research Design

RETROSPECTIVE DESIGN

Past Present
Risk factors Cases
Protective factors Control
 Descriptive Research Design

EXAMPLE
An investigation seeks to determine the risk factors
of physical violence in the home. The researcher
then looks for women who are known (e.g., from
the hospital) to have experienced physical
violence from their spouses and compare them
with another group of women (control group)
with comparable characteristics as the first group
who have no record (or did not report) spousal
violence
 Descriptive Research Design

Then the researcher goes back to their histories

(past experiences, past exposures) to
determine which factors put them at risk for
physical violence
 Descriptive Research Design

Testing associations between two or more

variables
+ correlations – directly proportional
- correlations – inversely proportional
0 correlation – no relationship
 Descriptive Research Design

EXAMPLE
A researcher wants to know if smoking and
coffee drinking are significantly associated. He
hypothesized that if a person smokes, he/she
is also a coffee drinker.
Positive correlation if smoking = coffee drinking
Negative correlation if smoking =/ coffee
drinking
 EXPERIMENTAL DESIGNS

True experimental designs

Quasi-experimental designs
 EXPERIMENTAL DESIGNS

• An experiment is a set of observations

conducted under controlled circumstances in
which the investigator manipulates conditions
to ascertain what effects such manipulation
has on the outcome
 EXPERIMENTAL DESIGNS

Requirements of a good experimental design

1. Presence of a comparison group (experimental
group and control group)
2. The independent variable (IV) can be
manipulated such that any change in the
dependent variable (DV)
3. Extraneous variables are (EV) are effectively
controlled to avoid confounding or spurious
results
 Symbols in experimental designs:

O – symbol for observation which usually means

the administration of a test, or instrument of
some type to obtain a measure; sometimes
this symbol is subscripted with numbers like 1,
2, 3, etc., and these signify repeated
observations, repeat measurement of some
variable like achievement
 Symbols in experimental designs:

X – represents various treatments and controls

administered to groups in the experiment
R – indicates that the groups were randomly
formed
Non R – indicates that the groups were not
randomly formed and are therefore intact
groups
 Pre-experimental Designs

a) One-shot case study: X O

• Only one group is used; no pre-test; no
method of comparison available
b) One-group pretest-posttest design: O X O
• Only one group is used; pre-test and post-test
are used; allows comparison over time; no
one can be sure that the gains could be due to
the treatment effect
 Pre-experimental Designs

c) Static-group comparison
E X1 O
C X2 O
• Two groups are used; a control and
experimental group; since there is pre-test
and no random assignment, one cannot be
sure that the groups were equivalent from the
outset
 True Experimental Design

• Represents the strongest research designs

possible for assessing the existence of causal
relationships
• Also the best designs for controlling threats to
internal validity
• Randomly formed groups or random
assignments of subjects to groups
 True Experimental Design

a) Pretest-Posttest Control Group

R O X1 O
R O X2 O
• Very strong design, weakness is the possible
pretest-posttest interaction which is to limit
generalizability; it is best that the instruments
used should have adequate test-retest or
equivalent forms reliability
 True Experimental Design

b) Posttest only control group

R X1 O
R X2 O
• Since no pretest is present, one must rely
upon random assignments to ensure that the
groups are equivalent at the outset
 True Experimental Design

c) Solomon four group design

R O X1 O
R O X2 O
R X1 O
R X2 O
• The best of the four designs
• Controls almost all sources of experimental invalidity
• Allows the researcher to determine whether the
pretest has an effect on the posttest independent of
the treatment
 True Experimental Design

EXAMPLE
Testing the effectiveness of DRUG A on capacity
to recall words
EG: # words recalled (pre-test) – exposures to
DRUG A (IV) - # words recalled (post test)
CG: : # words recalled (pre-test) – no exposure
to DRUG A (IV) - # words recalled (post test)
 QUASI-EXPERIMENTAL DESIGNS

QUASI-EXPERIMENTAL DESIGNS – not able to

satisfy any of the following requirements:
1. Presence of a comparison group, random
assignment
2. Having a manipulable independent variable
3. Control of extraneous variables
 QUASI-EXPERIMENTAL DESIGNS

EXAMPLE
Testing the effectiveness of Cooperative Learning as a
teaching strategy in mathematics
Two sections are included in the study which are randomly
assigned as experimental group and control group
The experimental group is taught Algebra using
Cooperative Learning while with the control group , the
traditional teaching strategy is used. At the end of the
term, test is administered to both groups and results are
compared.
 Validity
Internal validity
• The degree to which observed differences or
variations on the dependent variable is
directly related to the independent variable
and not to some other uncontrolled variable
External validity refers to the generalizability of
experimental findings to the “real” world
 Validity
Threats to Internal Validity
a) History – the occurrence of events that are
not part of the experiment, or that occur
outside of the experiment, which impact
upon the dependent variable of interest
Example: change in attention span during the
experiment (not past event)
 Validity
b) Maturation – changes in subjects over time
(mental and physical) that are not part of the
experiment
c) Testing effect – subjects who take a pretest in
an experiment may learn thongs from the
testing experience that will improve their
posttest performance on the dependent
variable; such improvement may confound the
effect of the treatment
 Validity
d) Instrumentation – the use of invalid test or
instrument; example, use of two forms of test
which are not equivalent or parallel
e) Statistical regression – the possibility that
results of the experiment are due to a tendency
for groups selected on the basis of extreme
scores to regress toward a more average score
on the subsequent measurements, regardless of
the effect of the experimental treatment
 Validity
f) Differential selection of subjects when intact
or already formed groups are used, they may
differ on some important characteristics; the
threat is that the initial difference will result in
differences on the posttest or outcome, which
will confuse the study
g) Mortality – subjects simply drop out of the
study
 Validity
Threats to external validity
a) Pretest-posttest interaction – pretest may
sensitize the experimental factor so the result
can be generalized only to other pretested
groups
b) Multiple-Treatment Interaction/Interference
– subjects receive more than one treatment
and the and the researcher has no idea which
treatment caused the results
 Validity
c) selection-treatment interaction – the effect of
the treatment is unique to the subjects and
cannot be generalized to other subjects;
Example: research shows that more intelligent
students tend to benefit less from cooperative
learning than the less intelligent students. The
treatment works differently with different
groups
 Validity
d) Specificity of variables – the more specific the
experiment in terms of the subjects,
measuring instrument, outcomes, etc., the
less likely it will be generalizable; example:
grade 4 pupils of Pamplona using only a locally
developed test
e) Experimenter effects – presence or behavior
of the experimenter may influence subjects’
reactions or behaviors
 Qualitative Research Design
Forms of interpretive inquiry
• Participants narrate/ interpret what they
experience
• Researchers interpret what they see, hear, and
understand
• Readers interpret what they see, hear, and
understand about the report
 Qualitative Research Design
Central Methods
• Interviewing people through various
techniques and recording what they say
• Observing people in the course of their daily
routines and recording their behaviors

Description and interpretation takes precedence

over measurement and prediction
 Qualitative Research Design
Characteristics of qualitative research
• Natural setting
• Researchers collect data in the field/ site where
participants experience the issue or problem
under study
• Research as the key instrument: the ones who
actually gather the information, do not rely on
questionnaires/instrument developed by other
researchers,
 Qualitative Research Design
Characteristics of qualitative research
• Multiple sources of data: does not rely on
single data; multiple data source (interviews,
observations, documents as multiple forms of
data)
• Inductive data analysis: build patterns,
categories and themes from the bottom up
 Qualitative Research Design
Characteristics of qualitative research
• Participant’s meanings: informed by
participant’s view of the world (emic)

• Emergent design: research process may

change or shift after researchers enter the
field and begin to collect data (participant-
centered research)
 Qualitative Research Design
Characteristics of qualitative research
• Theoretical lens: provides an overall orienting
lens that shapes he types of questions asked,
informs how data are collected and analyzed
and/ or provides a call for action/change
 Qualitative Research Design
Sampling
• Participants are usually recruited because of
their exposure to or their experience of the
phenomenon in question
• This tends to enrich the data gathered and is
known as purposive sampling or purposeful
sampling
 Qualitative Research Design
Sampling
• Samples can also be selected as a result of
themes that emerge from data analysis for
more in depth analysis and/or to develop a
theory from the data
• The main indicator of sample size in
qualitative research is often the point at which
redundancy or theoretical saturation of the
data is achieved
 Qualitative Research Design
Data Collection
• Some use the concept of data saturation as a
convenient stopping point in data collection
• The chief data collection devices are
observation, interview, artefacts, and
histories, visual documentation
 Qualitative Research Design
Ethnography
- Describes and interprets cultural behavior
- Seeks an emic perspective (insider’s view) of
the culture
- Relies on wide range of data sources
(interview, observation, documents
- Assumption: culture guide the way people
structure their experiences
 Qualitative Research Design
Phenomenology
• Purpose: seeks to understand the person’s or
persons’ perspectives as he/she or they
experience and understand an event,
relationships, program, emotion, etc,
• Process: the same process as used in
ethnographic study
 Qualitative Research Design
Phenomenology
Data collection:
- phenomenologists may study one subject , but
typically 5-25, who is/are purposely selected
- Rely on semi-structured in depth interviews and
researchers work closely with the participants in
collecting the data
- Focuses on the discovery of the meaning of
people’s lived experience
 Qualitative Research Design
Grounded theory
Purpose: using naturalistic iterative data
collection and relationship analysis processes,
researchers derive from data, a theory as an
expected outcome of the inquiry
 Qualitative Research Design

Grounded theory
Process: using iterative process of data
collection and analyses, relationships between
concepts are continually identified and refined
so as to enable theory development
 Qualitative Research Design
Case Study
Purpose: to describe, explain, or assess and
evaluate a phenomenon (e.g., event, person,
program, etc.)
Process: The “case” is studied on site within its
natural context, data-gathering process is
interactive/engaged researcher and
participant
 Qualitative Research Design

Case Study
Data Collection: data is collected primarily by
fieldwork but secondary data collection is
employed as well
 Qualitative Research Design
Narrative Research
• Focus on story; designed to determine how
individuals make sense of event in their lives
• Researchers studied the lives of individuals
and ask one or individuals to provide stories
about their lives.... Retold by the researcher
into a narrative chronology transformed into a
collaborative product
 Qualitative Research Design
Narrative Research
Types:
Biographical study – writes and records another person’s
life
Autobiography – written and recorded by individuals
who are the subject of the study
Life history – portrays an individual’s entire life
Oral History – gathering personal reflections of events
and their causes and effects on individuals or several
individuals
 Example: mixed design

1. Combination of a survey or individual in

depth interviews
2. Use of probability sampling for the survey
and use extreme or deviant sampling for in
depth interviews
 Example: mixed design

Vandalism n Schools
Quantitative part:
1. The prevalence survey of students who
committed a vandalism act at least once in
their college life
2. Types of vandalistic acts
3. Reasons for committing a vandalistic act
 Example: mixed design

Vandalism in Schools
Qualitative Part:
1. Going deeper into the reasons why students
commit a vandalistic act
2. Probing on the “how” it is done
3. Case analysis of a true experience
4. Key informant interviews or focus group
discussions of teachers and school administrators
with regard to possible interventions
 Example: mixed design

Title: Dynamics of intra-household decision-

making in relation to malaria prevention in IP
communities
1. Quantitative Phase: rapid survey
2. Qualitative Phase: FGDs ethnographic
interviews and critical inquiry, limited
participant observation, story telling,
problem solving using vignettes, experiential
narratives