CONSTRUCTING

RESEARCH DESIGN

Presented by:
Savira Ramadhani (1410302155)
Rahayu Nastiti A. (1410302202)

A SHORTHAND FOR DISPLAYING DESIGNS

The system of symbols in the research design are:
a. An X will be used to designate a treatment (the
presence of a treatment) and a blank space to
designate a control.
When the treatments are compared, they will be
labeled X1, X2 and so on
b. An O will be used to designate an observation or
measurement and each O will carry an arbitrary
subscript for ease of identification and referral
( O1, O2, and so on)
c.
The letter R will indicate that factors (for
example, selection) have been controlled by using
randomization or some other technique.

PRE-EXPERIMENTAL DESIGNS (NONDESIGNS)

1.

One-Shot Case Study

The one-shot study can be diagramed as follows:
XO

On the basis of a one-shot case study there is no justification

for concluding that X caused O. No control group. This design
has virtually no internal or external validity.

Example:
School institute operate a free-lunch program (X). After the
program has been in operation in six month. Teachers are
interviewed and they report (O) that instances of disruptive
classroom activity are minimal. The school principal then
concludes that the school lunch program is reducing
students tension and aggression.

However, the principal does not know

1. Whether specific experiences or occurrences
(history) other than lunch program have
contributed to the observed behavior change
2. Whether there really was a change relative to
past behavior, and, if there was, whether it is
stable, or
3.
Whether students participating in the lunch
program were likely to change anyway as a
function of selection or maturation.

2. One Group Pretest-Posttest Design

The one-group pretest-posttest design can be diagramed as
shown below:
O1 X O2
This study uses a pretest which provides some information of
the sample. However, this design fails to control for history,
maturation, testing, or statistical regression and thus cannot
be considered legitimate. It is also falls far short of handling
the other sources of internal invalidity. It has also minimal
Control. There is a single selected group under observation,
with a careful measurement being done before applying the
experimental treatment and then measuring after. This design
has minimal internal validity, controlling only for selection of
subject and experimental mortality. It has no external validity.

3. Intact-Group Comparison
The intact-group comparison* can be diagramed as shown below.

a second group or control group that does not receive treatment

(X) as a source of comparison for the treatment-receiving group
is utilized in this approach. Because a control (non treatment)
group is employed, validity factors such as history (and, to a
lesser extent, maturation) are controlled for by the control (non
treatment) group. That is, it some other coincidental event
affected the outcome, it would as likely affect O2 as O1, thus
controlling for history. Thus, the intact-group comparison
considered as a design that in itself does not control satisfactory
all sources of invalidity to be acceptable or legitimate.

TRUE EXPERIMENTAL DESIGN

A design can be called as true experimental design
if it provide completely adequate controls for all
sources of internal invalidity and represent no
compromise
between
experimental
design
requirements and the nature and reality of the
situation in which a study is being undertaken.
There are two kinds of True Experimental
Designs:
a. Posttest-Only Control Group Design
b. Pretest-Posttest Control Group Design

1. Posttest-Only Control Group Design

The posttest-only control group design is the potentially
most useful true design. It can be diagramed as shown
below

This design utilizes two groups, on of which experiences

the treatment while the other does not, thus controlling
for history and maturation. Group assignment is made
on a random basis, which controls or selection and
mortality. No pretest is given to either group in order to
control for simple testing effects and the interactions
between testing and treatment.

2. Pretest-Posttest Control Group Design

The pretest-posttest control group design can be
diagramed as shown below.

Two groups are employed in this design; one group,

the experimental group, receives a treatment (X)
while the second group, the control group, does not.
(The assignment of Ss to both groups is
accomplished on a random basis)*
This design controls for all the simple sources of
invalidity, but by virtue of its use of pretest does not
control for the testing sources of invalidity that may
often plague a study.

For many true experimental designs, pretest-

posttest designs are the preferred method to

compare participant groups and measure the
degree of change occurring as a result of
treatments or interventions.
Pretest-posttest designs grew from the simpler
posttest only designs, and address some of the issues
arising with assignment bias and the allocation of
participants to groups.
One example is education, where researchers want to
monitor the effect of a new teaching method upon
groups of children. Other areas include evaluating
the effects of counseling, testing medical treatments,
and measuring psychological constructs. The only
stipulation is that the subjects must be

FACTORIAL DESIGN
Factorial design has several important features.
First, it has great flexibility for exploring or
enhancing the signal (treatment) in our studies.
Whenever we are interested in examining
treatment variations, factorial designs should be
strong candidates as the designs of choice.
Second, factorial designs are efficient. Instead of
conducting a series of independent studies we are
effectively able to combine these studies into one.
Finally, factorial designs are the only effective
way to examine interaction effects.

Factorial design are modification of the true experimental design with the
further variables are included in addition to the treatment variable.

An

illustration of the modification on the pre-test post test control group design
with

one treatment variable

into factorial design with one

moderator

variable . The moderator variable is indicated by the letter Y with two levels
Y1 and Y2
R O1 X Y1 O2
R O3 Y1 O4
R O5 X Y2 O6
R O7 Y2 O8
It shows that two groups receive the treatment and the two groups do not. If
Y1 represented the

high intellegence

group

and Y2 represented a lower

intellegent group so only half intellegent sub group would be receiving the
treatment. Moreover, the half to be given or not the statment is determined on
a random basis.

QUASI EXPERIMENTAL DESIGN

Quasi-experimental designinvolves selecting groups, upon

which a variable is tested, without any random preselection processes.

Quasi-experimental designs came about because of:

1) difficulty of applying the classical natural science method

to the social sciences
2) overemphasis on theory testing and development
3) high cost of classic natural science methods
4) development of new statistical tools that allowed for
statistical control

For example, to perform an educational experiment,

a class might be arbitrarily divided by alphabetical
selection or by seating arrangement. The division is
often convenient and, especially in an educational
situation, causes as little disruption as possible

After this selection, theexperimentproceeds in a

very similar way to any other experiment, with a
variable being compared between different groups, or
over a period of time.

There are several types of quasi-experimental designs,

including:
time series design
equivalent time series samples
equivalent samples materials design
non-equivalent control group
counterbalanced designs
separate sample pre-test/post-test
separate sample pre-test/post-test control group
multiple time series design
institutional cycle design
regression-discontinuity design

THANK YOU FOR YOUR ATTENTION