Experimental

Research
Designs
 Definition of Terms
• Subjects or Respondents
– These are the people who participate in a research.
• Experimental Treatments
– It is something that researchers administer to the experimental units.
• Test Unit
– The entity whose responses to experimental treatments are being
observed or measured.
• Experimental Group
– It is a group of subjects exposed to the experimental treatment.
• Control Group
– It is a group of group of subjects exposed to the control condition.
• Randomization
– It is called random assignment of subjects or respondents.
You are testing to see if a new plant fertilizer
increases sunflower size. You put 20 plants of
the same height and strain into a location
where all the plants get the same amount of
water and sunlight.
•Subjects– 20 sunflower plants
•Treatment – fertilizer
•Experimental Group – 10 sunflowers plants get
the fertilizer you are testing
•Control Group – the other 10 sunflowers plants
get a regular or commercialized fertilizer
You are testing to see if a new drug works for
asthma. You divide 100 volunteers into two
groups of 50.
•Subjects–100 volunteers
•Treatment – drug
•Experimental Group – 50 volunteers take the
drug
•Control Group – the other 50 volunteers take a
sugar pill
Letters to Consider
X – Treatment
O – Test
(Pretest/Posttest)
R – Random assignment
 A. Pre-Experimental
Designs
• Pre-experiments are the simplest
form of experimental research design.
• In a pre-experiment either a single
group or multiple groups are
observed subsequent to some agent
or treatment presumed to cause
change.
A. Pre-Experimental Designs
Design 1: One-Shot Case Study
Design 2: One-Group Pretest-
Posttest Design
Design 3: Static Group Comparison
Design 4: Parallel-Equated Two
Group Design
 A. Pre-Experimental
Designs
Design 1: One-Shot Case Study

It considers only one

group exposed to the
treatment.
 ONE-SHOT CASE
STUDY DESIGN
experimental
TREATMEN
POST
group T TEST
Design 1: One-Shot Case Study

X O
Example: When one wants to
know the effectiveness of a
seminar, a test is given.
 Design 1: One-Shot Case Study
Example: Effectiveness of a Seminar

X
Experimental Treatment
O Posttest
Group (X) (O)
Participants Seminar Questionnaire
 Design 1: One-Shot Case Study
Example: The Effects of Counselling
Sessions on the Attitudes of Identified
Bullies in School

X
Experimental Treatment
O Posttest
Group (X) (O)
Bully students Counseling Observation
 A. Pre-Experimental
Designs
Design 2: One-Group Pretest-Posttest Design

The Pretest and Posttest are the same

and an increase of measures in the
posttest signifies the effectiveness of
the treatment.
 ONE-GROUP PRETEST-
POSTTEST DESIGN
experimental
group TREATMEN
POST
PRETTEST T TEST
Design 2: One-Group Pretest-Posttest Design

O1 X O2
Example: Measuring the effectiveness
of musical instruments on the study of
mathematics.
Design 2: One-Group Pretest-Posttest Design

O1 X O2
Experimental Pretest Treatment Posttest
Group (O1) (X) (O2)
Students Musical
Instruments
Design 2: One-Group Pretest-Posttest Design
Example: Determine whether praising
primary school children make them do better
in Mathematics

O1 X
Experimental Treatment
O2
Pretest Posttest
Group (X)
Primary
(O1) (O2)
Praising
school
children
Design 2: One-Group Pretest-Posttest Design
Example: Examine the Efficacy of a Drug

O1 X
Measure DRUG
O2 Measure
Patients’ Condition (Treatment) Patients’
Condition
(Pretest) (Posttest)
• RESULT: Significant Improvement from O1 to O2
• QUESTION: Did X (the drug) cause the improvement?
19
 A. Pre-Experimental
Designs
Design 3: Static Group Comparison

It involves a group (Experimental)

which has experienced the
treatment compared with another
group (Control) which has no
experience of the treatment.
 STATIC GROUP
COMPARISON
experimental POST
TREATMEN
group T TEST

POST
control group TEST
Design 3: Static Group Comparison

X O1
O2
Design 3: Static Group Comparison
Example: Determine whether praising
primary school children make them do better
in Mathematics
Experimental Treatment Posttest
Group (X) (O1)
Primary school
Praising
children

Control Group Posttest

Primary school
children
(O2)
 A. Pre-Experimental
Designs
Design 4: Parallel-Equated Two Group Design

It also involves two groups:

the experimental and the
control group.
 PARALLEL-EQUATED TWO
GROUP DESIGN
experimental POST
TREATMEN
group T TEST
PRETEST

control group TREATMEN

POST
PRETEST T TEST
Design 4: Parallel-Equated Two Group Design

O1 X1 O3
O2 X2 O4
Example: Determine the effectiveness of
game strategy in teaching the sets in
Mathematics
 Design 4: Parallel-Equated Two Group Design

Example: Determine the effectiveness of

game strategy in teaching the sets in
Mathematics
Experimental Treatment
Pretest Posttest
Group (X1)
(O1) (O3)
Students Game Strategy

Control Treatment
Pretest Posttest
Group (X2)
(O2) (O4)
Students Game Strategy
B. True Experimental Designs
• It is the most accurate type of
experimental design.
• The true experimental research
design relies on statistical
analysis to approve or disprove
a hypothesis.
B. True Experimental Designs
Design 5: Pretest and Posttest
Control Group
Design 6: Posttest Only Control
Group Design
Design 7: Solomon Four-Group
Design
 B. True Experimental Designs
Design 5: Pretest and Posttest Control Group Design

It also involves two groups,

both of which are formed
by random assignment.
 PRETEST AND POSTTEST
CONTROL GROUP DESIGN
Randomly
selected
POST
experimental TREATMEN
group T TEST
PRETEST

Randomly selected
control group POST
PRETEST TEST
Design 5: Pretest and Posttest Control Group Design

O1 X O3
R
O2 O4
Example: Determine the effectiveness of
Dance for Peace Training Workshop
Design 5: Pretest and Posttest Control Group Design

01 03

02 04
B. True Experimental Designs
Design 6: Posttest Only Control Group Design

It also involves two groups, one

of them receiving the
experimental treatment; both
are post-tested, but are not
pre-tested.
 POSTTEST ONLY CONTROL
GROUP DESIGN
Randomly
selected POST
TREATMEN
experimental TEST
T
group

Randomly selected POST

control group TEST
Design 6: Posttest Only Control Group Design

X O1
R
O2
Example: Determine the effectiveness of
Dance for Peace Training Workshop
Design 6: Posttest Only Control Group Design

01

02
B. True Experimental Designs
Design 7: Solomon Four-Group Design

It has the highest prestige since

it has the greatest validity. It is
the extension of design 5 and
design 6.
 SOLOMON FOUR-GROUP
DESIGN
Experimental
Group A TREATMEN
POST
PRETEST T TEST
Control Group A POST
PRETEST
TEST

Experimental POST
TREATMEN
Group B
T TEST

POST
Control Group B
TEST
 Design 7: Solomon Four-Group Design

O1 X O2
O3 O4
R X O5
O6
Example: Determine the effectiveness of
Dance for Peace Training Workshop
Design 7: Solomon Four-Group Design
01 02
25 teachers
Experimental
Group A

03 C 04
Pretest:
25 teachers Faculty Self- No training
Control Group A Awareness
Questionnaire
X 05
25 teachers Dance for Peace
Experimental Training-
Group B Workshop

06

25 teachers
Control Group B
 C. Quasi-Experimental
Designs
• It involves the manipulation of
an independent variable
without the random assignment
of participants to conditions or
orders of conditions.
 C. Quasi-Experimental
Designs
Design 8: Non-randomized Control
Group Pretest-Posttest Design
Design 9: Time Series Experimental
Design
Design 10: Multiple Time Series
Design
C. Quasi-Experimental Designs
Design 8: Non-randomized Control Group
Pretest-Posttest Design

(Similar with Design 5)

It is also known as the ‘nonequivalent control
group design’. This design is identical to the
pretest-posttest control group design,
except there is no random assignment of
subjects in experimental & control groups.
 NON-RANDOMIZED CONTROL
GROUP PRETEST-POSTTEST
DESIGN
experimental POST
TREATMEN
group T TEST
PRETEST

control group POST

PRETEST TEST
 Design 8: Non-randomized Control Group
Pretest-Posttest Design

O1 X O3
O2 O4
Example: Determine the effectiveness of
Dance for Peace Training Workshop
 Design 8: Non-randomized Control Group
Pretest-Posttest Design
E 01 03

100
teachers C 02 04
C. Quasi-Experimental Designs
Design 9: Time Series Experimental Design

A single group is pretested

repeatedly until pretest scores
are stable , exposed to treatment
and, then, repeatedly post
tested.
 Design 9: Time Series Experimental Design

O1 O2 O3 X O4 O5 O6
C. Quasi-Experimental Designs
Design 10: Multiple Time Series Experimental
Design
It is taken from two groups of test units (an
experimental group and a control). The
experimental group is exposed to a
treatment and then another series of
periodic measurements is taken from
both groups.
Design 10: Multiple Time Series Experimental Design

O1 O2 O3 X O4 O5 O6
O1 O2 O3 O4 O5 O6
Design 10: Multiple Time Series Experimental Design