Research Design

A research design is the outline, plan, or

strategy that you are going to use to obtain
an answer to your research question
• Research Designs are related to research
paradigms
• In this regard research designs are classified
into Positivism (Quantitative), Constructivism
(Qualitative) and Pragmatism (Mixed
Methods) categories.
 Quantitative research designs
• Quantitative research does three main things
1. Description of phenomena
2. Demonstration of relationship between/ among
variables.
3. Determination of group difference
For this reason designs in this tradition are
1. Survey/ Descriptive designs
2. Correlational designs
3. Experimental designs
 Survey designs
• Attempt to collect data from members of a population in order
to determine the current status of that population with respect
to one or more variables.
• Systematically gathers information that describes the
characteristics of respondents for the purposes of building
generalizations or theories about the population they represent.
• Survey design is predominantly descriptive and it is for this
reason that the terms descriptive and survey research are
sometimes used interchangeably.
• There are three types of survey designs: 1. Cross-Sectional
Survey Design 2. Longitudinal Survey design.
 Cross Sectional Survey Design
• Involves the collection of data at a specific
point in time from one or more populations .
• It is appropriate when the researcher wants to
get information at one point in time in order
to describe the current characteristics of a
sample.
• Suppose you are interested in how students’
attitudes towards university education change
from first year to four year
• To study this problem, you would select a
sample of students at each grade level and
collect data at one point in time
• As such data collection time is short and there
is no attrition
 Longitudinal Studies
• Involves collecting data from a sample at
different points in time
• Aims at studying changes or continuity in the
sample’s characteristics
• Difficult to implement, but they are essential
for exploring problems in human development
 Types of Longitudinal Studies
• There are three types:
Trend
Cohort
Panel
• They differ mainly in how the sample to be
studied at different point in time is selected
 Trend Studies
• Describe change by selecting a different
sample at each data collecting point from a
population that does not remain constant
• .
• For example: A researcher interested in
studying characteristics of students enrolled in
a research course would survey research
students in that particular year. The annual
survey of research students would continue
until sufficient data is gathered. Note that
though research students are surveyed, the
population from which they are drawn would
vary
 Cohort Studies
• Describe change by selecting a different sample at
each data collecting point from a population that
remains constant
• For example:
• A researcher interested in studying characteristics of
students enrolled in a research course would survey
research students in that particular year. The
researcher would draw another sample from the
same population of research students in the next
year.
 Panel Studies
• Describe change by selecting a sample at the
outset of the study and then at each
subsequent data collecting point surveying the
same sample
• For this reason, you can:
note changes in specific individuals
explore possible reasons why these individuals
have changed
• A researcher interested in studying
characteristics of students enrolled in a
research course would survey research
students in that particular year. In the second
year the same sample would be studied
 Correlational Survey Design
• Used to describe in quantitative terms the
degree to which two or more variables are
related.
• The intention is to discover relationships
between variables through the use of
correlational statistics
• Therefore, it has two purposes:
Prediction
Searching for causal patterns among variables
 Correlational..Cont

• It involves:
collecting data on two or more variables for each
individual in a sample
computing a correlation coefficient
• In Correlational research correlational coefient
is computed and is used to:
Measure the degree and direction of relationship
between two or more variables
Explore possible causal factors. If a significant
relationship between variables is found, their
causality can be tested more definitely by using an
experimental design
 Causal Comparison
• Used if the purpose of the study is to explain an education
phenomena through the study of cause-and-effect
relationships.
• The presumed cause is called “independent variable”
• The presumed effect is called “dependent variable”
• For example: A hypothesis that teacher morale
(independent variable) affects their rate of absenteeism
from work
• In this example the independent variable is teacher morale
whereas the dependent variable is rate of absenteeism
 Causal Comparison..Cont
• The researcher does not manipulate the independent
variable to observe its effect on the dependent
variable
• As such the design does not permit strong conclusion
about cause-and-effect
• But they are still useful for initial exploratory
investigations or in situations where it is impossible to
manipulate the independent variable
• In our earlier example, it would be virtually impossible
for researchers to conduct a study in which they create
work conditions that promote good morale among
some teachers and poor morale among other teachers
• They are limited to observing naturally
occurring variation in teacher morale which
can be measured and related to naturally
occurring variation in teacher absenteeism
rates.
• Studies that rely on observation of
relationships between naturally occurring
variation in the presumed independent and
dependent variables sometimes are called ex
post facto research.
 Experimental Designs
• An experiment is a situation in which a researcher
objectively observes phenomena which are made to
occur in a strictly controlled situation where one or
more variables are varied and the others are kept
constant
• Whenever an experimental research study is
conducted the researcher's interest is always in
determining cause and effect. The causal variable is
the independent variable (IV) and the effect or
outcome variable is the dependent variable (DV
 Experiment cont’d
• Experimental research allows us to identify
causal relationships because we observe the
result of systematically changing one or more
variables under controlled conditions. This
process is called manipulation.
Independent variable manipulation
• The independent variable is the variable that
is assumed to be the cause of the effect. It is
the variable that the researcher varies or
manipulates in a specific way in order to learn
its impact on the outcome variable
 Ways of manipulating the independent
variable
• Presence vs. Absence technique
The independent variable can be manipulated by presenting a
condition or treatment to one group of individuals and withholding
the condition or treatment from another group of individuals.
• Amount Technique
The independent variable can be manipulated by varying the amount
of a condition or variable
• The type Technique
The independent variable is manipulated by varying the type of
condition or treatment administered. Two groups of students can be
taught using two different teaching methods to find out if one
method is more effective than the other.
 Types of experimental designs
• Weak experimental designs
• Strong/true experimental designs
 Weak experimental designs
• are considered weak because they do not control for the influence of many
confounding variables
• ONE-GROUP POSTTEST-ONLY DESIGN ( X O )
 one group of research participants receives an experimental treatment and is then
post tested on the dependent variable
 However you do not know whether the treatment condition had any effect on the
participants because you have no idea as to what their response would be if they
were not exposed to the treatment condition.
 That is, you don’t have a pretest or a control group to make your comparison with.
 Another problem with this design is that you do not know if some confounding
extraneous variable affected the participants' responses to the dependent variable
 Because of the problems with this design it generally gives little evidence as to the
effect of the treatment condition
 One-Group Pretest-Posttest Design
(O X O)
• one group of participants is pretested on the
dependent variable and then post tested after
the treatment condition has been
administered
• better design than the one-group post-test-
only design because it at least includes a pre-
test, that indicates how the participants did
prior to administration of the treatment
condition
• In this design, the effect is taken to be the
difference between the pre-test and post-test
scores
• It does not control for potentially confounding
extraneous variables , so it is still difficult to
identify the effect of the treatment condition.
Posttest only design with non equivalent groups

• includes an experimental group that receives

the treatment condition and a control group
that does not receive the treatment condition
or receives some standard condition and both
groups are posttested on the dependent
variable
• Although the control group is there, the
groups are not rondomly selected
•  Because the participants were not randomly
assigned to the comparison groups, this
design does not control for differential
selection
  
Strong Experimental Research Designs

• A research design is considered to be a "strong

research design" if it controls for the influence of
confounding extraneous variables. This is
typically accomplished by including one or more
control techniques into the research design.
• The most important of these control techniques
are inclusion of a control group and random
selection and random assignment.
 With random selection subjects are given
equal chance of being included in the sample
 With random assignment, the sampled
participants has an equal chance of being part
of the experimental group or control group.
 Pretest-posttest control-group design

• a group of research participants is randomly

assigned to an experimental and control group
• Both groups of participants are pre tested on
the dependent variable and then post tested
after the experimental treatment condition
has been administered to the experimental
group.
• Because the design has a control/comparison
group and random assignment, it controls for
all standard threats to internal validity.
• Note that while this design is often presented
as a two group design, it can be expanded to
include a control group and as many
experimental groups as are needed to test
your research question.
  
Posttest-only control group design

• research design in which the research participants

are randomly assigned to an experimental and
control group and then post tested on the
dependent variable after the experimental group
has received the experimental treatment condition.
• Excellent design because it includes a control or
comparison group and has random assignment as
such it controls for all standard threats to internal
validity
• This design does not include a pretest of the
dependent variable, but this does not detract
from its internal validity because it includes
the control group and random assignment
which means that the experimental and
control groups are equated at the outset of
the experimenT
 Validity of an experiment
• Validity is when an experiment measures what it claims to
measure. Validity is of two major types. These are internal
validity and External validity

• Internal validity refers to the extent to which we can

accurately state that the independent variable produced
the observed effect

• External validity refers to the extent to which the results of

a study can be generalized (applied) beyond the sample
 Threats to internal validity
• Subject Characteristics (Selection
Bias/Differential Selection) The groups may
have been different from the start. If you were
testing instructional strategies to improve
reading and one group enjoyed reading more
than the other group, they may improve more
in their reading because they enjoy it, rather
than the instructional strategy you used
• Maturation --There may be natural changes in
the subjects that can account for the changes
found in a study
• Hawthorne effect: The subjects may respond
differently just because they are being studied
 Threats to Internal Validity cont’d
• Regression (Statistical Regression) -- A class that scores
particularly low can be expected to score slightly higher just by
chance. Likewise, a class that scores particularly high, will have a
tendency to score slightly lower by chance. The change in these
scores may have nothing to do with the treatment.
• Resentful Demoralization of the Control Group -- The control
group may become discouraged because it is not receiving the
special attention that is given to the treatment group. They may
perform lower than usual because of this.

• Implementation --The treatment may not be implemented as

intended
 Threats to Internal validity Cont’d
• Experimental Treatment Diffusion -- Sometimes the
control group actually implements the treatment. If two
different techniques are being tested in two different third
grades in the same building, the teachers may share what
they are doing. Unconsciously, the control may use of the
techniques she or he learned from the treatment teacher
• John Henry Effect -- One group may view that it is
competition with the other group and may work harder
than than they would under normal circumstances. This
generally is applied to the control group "taking on" the
treatment group.
 Threats to Internal Validity Cont’d

• Instrumentation: Unreliable tests or instruments can introduce

serious errors into experiments. With human observers or
judges, errors can result from changes in their skills and levels
of concentration over the course of the experiment

• Experimental mortality: The loss of subjects due to dropout in

long experiments may result in confounding the effects of the
experimental variable. The initial group of subjects may have
been randomly selected but the remaining participants are
likely to be different from the unbiased sample that began it.
 Threats to external validity
• Hawthorne effect (attention causes differences)
Subjects perform differently because they know they are being
studied. "...External validity of the experiment is jeopardized
because the findings might not generalize to a situation in which
researchers or others who were involved in the research are not
present

• Explicit description of the experimental treatment (not

sufficiently described for others to replicate)
If the researcher fails to adequately describe how he or she
conducted a study, it is difficult to determine whether the results
are applicable to other settings.
 Threats to External Validity Cont’d
• Novelty and disruption effect (anything different makes a difference)
A treatment may work because it is novel and the subjects respond to
the uniqueness, rather than the actual treatment. The opposite may
also occur, the treatment may not work because it is unique, but
given time for the subjects to adjust to it, it might have worked.
• Experimenter effect (it only works with this experimenter)
The treatment might have worked because of the person
implementing it. Given a different person, the treatment might not
work at all.
• Pretest sensitization (pretest sets the stage)
A treatment might only work if a pretest is given. Because they have
taken a pretest, the subjects may be more sensitive to the treatment.
Had they not taken a pretest, the treatment would not have worked
 Threats to external validity cont’d
• Posttest sensitization (posttest helps treatment "fall into place")
The posttest can become a learning experience. "For example, the
posttest might cause certain ideas presented during the treatment to
'fall into place'). If the subjects had not taken a posttest, the
treatment would not have worked.

• Measurement of the dependent variable (maybe only works with

M/C tests)
A treatment may only be evident with certain types of
measurements. A teaching method may produce superior results
when its effectiveness is tested with an essay test, but show no
differences when the effectiveness is measured with a multiple
choice test.
 Assignment
• Describe the three main research paradigms
widely used in Educational research. For each
paradigm suggest and justify a research topic in
the field of education to demonstrate the
applicability of the paradigm
• Length 3 pages including references
• Font: Times New Roman
• Font size:12
• Due Date :3rd October 2022
 Assignment 2
• Choose any topic in the field of education.
Develop a statement of the problem , purpose of
the study and three objectives. In developing a
statement of the problem cite at least 6 scholarly
sources.
• Length 2 pages including references
• Font: Times New Roman
• Font size:12
• Due Date :7th October, 2022