Experimental Design

A description of what a researcher

would like to find out and how to
find out.
 Experimental Design

A complete sequence of steps or

procedures that need to be followed
when obtaining the needed data
during an investigation.
 Experimental Design
• It serves as a guide during the actual
experimentation.
• It minimizes the cost of experimentation
while maximizing the gathered information
relevant to the problem.
• It also validates the statistical test because
it takes into consideration all the
assumptions that went through the process
 Planning an Experimental Design

Subject of the study (also called

experimental unit)
Main material being used in the
experiment.
Materials- include the ingredients and its
formulations. The ingredients must be
quantified.
 Significance of an Experimental
Design
It serves as a guide during the conduct of an
experimental investigation. It minimizes cost
while gaining maximum information relevant
to the problem.
the assumptions that underlie within the
selected statistical test are considered in the
design of the experiment. This makes the
statistical test of significance valid.
Experimental
Method
A method or procedure involving
the control or manipulation of
conditions for the purpose of
studying the relative effects of
various treatments applied to
members of a sample, or of the
same treatment applied to members
of different samples.
Purpose:

to discover the influence of one

or more factors upon a
condition, group, or situation,
purpose of which is to discover,
“what will be.”
 General Distinguishing Features of
Experiments
1. Experimentation lends itself to easier
manipulation because of quantitative
entities.
2. Observations are done under controlled
conditions.
3. Gathering of valid facts is rigorous.
General Distinguishing Features of
Experiments
4.Experimentation can be conducted in the
laboratory, in the classroom, or in the
fields.
5.Laboratory experiments are intensive and
exacting.
6.Most often experiments are limited to a
small number of cases.
Before you can design an
experiment, you should:
1. Ask the questions you would like to be
answered;
2. Make an educated guess or state your
research hypothesis; and
3. Make a detailed description and
explanation of the procedure of your
experiment.
 Four Parts of Experimental
Procedure:
1. Selection of the appropriate materials for
the test;
2. Specification of the variable to be
measured;
3. Selection of the procedure to be used in
the measurement of the variable; and
4. Specification of the procedure to be used
 Principles of an Experimental
Design
Replication
Randomization
Local Control
Control of Extraneous variables
 Principles of an Experimental
Design
Replication
is a very necessary element in the design
of any research.
Doing just the basic experiment is not
enough. The experiment should be repeated
several times to find an estimate of
variations among observations on the group
 Principles of an Experimental
Design
Randomization
• refers to the assignment of the
experimental subjects to the treatments by
chance.
• It is done to create equivalent groups prior
to the experiment.
• It reduces possible bias in comparative
 Principles of an Experimental
Design
Randomization
• It also assures a valid or unbiased
estimate of population parameters and the
validity of the statistical of significance.
 Principles of an Experimental
Design
Local Control
Is done when balancing, grouping and blocking
of experimental units are employed in the
adopted design.
Experimental units are divided into several
homogeneous parts, known as blocks and each
block is divided into parts equal to the number
of treatment.
 Principles of an Experimental
Design
Control of Extraneous Variables
• It is to make sure that no outside variables
may affect the experimental subjects.
• Identical conditions must be provided for the
control and experimental groups.
• The two groups should differ only in terms of
the absence (control) or presence of the
treatment (experimental).
 An experimental design must deal
with four issues:
1.The people who participate in the
experiment.
2.The independent variable or variables,
which are also called the treatment variables.
These are the variables the researchers
manipulate during the experiment.
 An experimental design must deal with
four issues:
3. The dependent variable, or the effect that
the researchers measure.
4. The plan for controlling extraneous
variables.
Statistical experimental
research design is the
process of planning and
analyzing experiments
to test hypotheses and
gather data
 Pre-Experimental Designs

• The simplest form of experimental research

designs.
• Have little or no control over extraneous
variables.
• Do not randomly assign subjects to different
treatments.
Single-group Design

• Involves a single treatment with two or

more levels.
• A design in which a group of subjects
are administered and then measured.
• It does NOT have an experimental group
or control group.
Table 5.2. Single-Group Design Sample on the Fish
Meal as Supplemental Feed upon the Yield of
Mudcrab (S. serrata) Cultured in the Fishpond)
FISH MEAL YIELD OF MUDCRAB (S. serrata)
TREATMENT (T) (kg)
REPLICATIONS
1 2
3
T1 (5%)
X X
T2 (10%) X
T3 (15%)
X X
X
X X
One-group-after only/One Shot case only

• refers to a research design where only

one group of participants is studied,
and their data is collected only once,
after they have been exposed to an
intervention or treatment.
 One-group-after only/One Shot case only

There is no random assignment of test subjects as

there is only one treatment, and there is no control.
One-group Pretest-Posttest
Design
One-group Pretest-Posttest
Design
With this research design the test unit
is measured twice, one before the test
and once after the test. There is still no
control group; which is to say, a group
not receiving the treatment.
 Static Group Design
With the Static Group design there is a Control Group
(CG) in addition to the Experimental Group (EG). The
experimental group is exposed to the treatment while
the control group is not. Test units, however, are not
randomly assigned to the control or experimental
groups.
 TRUE EXPERIMENTAL
DESIGN
 TWO GROUP DESIGN
 TWO-PAIR GROUP DESIGN
 PRETEST-POST-TEST CONTROL GROUP
DESIGN
 POST-TEST ONLY CONTROL GROUP
DESIGN
TRUE EXPERIMENTAL
DESIGN
True experimental research design is a
research method that establishes cause-
and-effect relationships between
variables.
It's considered one of the most accurate
and rigorous research designs.
 TRUE EXPERIMENTAL
DESIGN
Researchers have complete control over
the extraneous variables and can predict
confidently that the observed effect on
the dependable variable is only due to
the manipulation of the independent
variable.
Two-group Design

Two comparable groups are

employed as experimental and control
groups or two comparable groups are
both experimental groups.
Table 5.3. Two-Group Design Sample on the Growth Rate of Cultivating Eucheuma
using Broadcasting (Control Group) Lantay (Experimental Group) Methods

BROADCASTING LANTAY
RESEARCH METHOD METHOD
STATIONS (KG) (KG)
1 X X
X X
2 X X
3 X X
4 X X
X X
5 X X
6 X X
7 X X
 Table 5.3. Two-Group Design
Sample
FLAVOR ACCEPTABILITY
PANELISTS MILKFISH GOATFISH
LUNCHEON LUNCHEON
MEAT MEAT
1 9 8
2 8 8
3 9 8
4 8 8
5 8 8
6 9 8
7 8 8
8 7 8
Pre-test-Post-Test Control
Group Design
 Pre-test-Post-test Design

This design involves the

experimental group and the control
group which are carefully selected
through randomization procedures.
Table 5.14. Sample of Pre-test and Post-test Design on the Effect
of Traditional and Modern Methods of Teaching Mathematics

METHODS OF TEACHING PRE-TEST POST- TEST

MEAN (X1) MEAN (X2)

Traditional (Control X X
Group) X X
Modern (Experimental
Group)
Two-pair group Design

This design is an
elaboration of the two-group
design wherein there are two
control groups and two
experimental groups.
 Table 5.5. Two- Pair Group Design Sample on the
Acceptability of Canned Milkfish Bone Meal in Salmon
and French Style with and without Sea Vegetable
FLAVOR ACCEPTABILITY
CONTROL GROUP EXPERIMENTAL GROUP
(Without Sea (With Sea Vegetable)
Vegetable)
1 2 1 2
PANELISTS Salmon French Salmon French
Style Style Style Style

1 X X X X
2 X X X X
SOLOMON 4-GROUP
DESIGN
The Solomon four-group design is believed
to be the most prominent experimental
research design because it minimizes the
threat to internal and external validity.
Parallel-group Design
This is a design in which two or more
groups are used at the same time with only
single variable (experimental group)
manipulated or changed. The experimental
group varies while the parallel group
serves as control for comparative
purposes.
Table 5.7. Parallel-Group Design on the Acceptability of
Canned Commercial Liver Spread, Milkfish Bone Meat
Spread and Goatfish Bone Meal Spread
FLAVOR ACCEPTABILITY
CONTROL EXPERIMENTAL GROUPS
GROUP
PANELISTS
Commercial Milkfish Goatfish

1 X X X
2 X X X
3 X X X
4 X X X
Counterbalanced or Latin Square design

Also called “rotation design.”

It involves an exchange of two or
more treatments taken by the
subjects during the experiment.
Table 5.7. Counterbalanced or Latin Square Design Culturing of
Grouper Using Four Supplemental Feeds to Four Fish Cages
FC1 FC2 FC3 FC4

SF1
G1 G2 G3 G4

G2 G3 G4 G1
SF2

G3 G4 G1 G2
SF3
G4 G1 G2 G3
SF4
Completely Randomized Design (CRD)

A design in which a group of test

plants or animals is studied only once but
subsequent treatment is applied to
determine the cause of change. In this
design subjects will undergo
randomization procedures.
Completely Randomized Design (CRD)

• Simplest design to use.

• Design can be used when experimental units are
essentially homogeneous.
• Because of the homogeneity requirement, it may be
difficult to use this design for field experiments.
• The CRD is best suited for experiments with a small
number of treatments.
Completely Randomized Design (CRD)

• Treatments are assigned to experimental

units completely at random.
• Every experimental unit has the same
probability of receiving any treatment.
• Randomization is performed using a random
number table, computer, program, etc.
Completely Randomized Design (CRD)

Advantages of a CRD
1. Very flexible design (i.e. number of treatments and
replicates is only limited by the available number of
experimental units).
2. Statistical analysis is simple compared to other designs.
3. Loss of information due to missing data is small compared
to other designs due to the larger number of degrees of
freedom for the error source of variation.
Completely Randomized Design (CRD)

Disadvantages
1. If experimental units are not homogeneous and
you fail to minimize this variation using blocking,
there may be a loss of precision.
2. Usually the least efficient design unless
experimental units are homogeneous.
3. Not suited for a large number of treatments.
Table 5.11. Sample of Complete Randomized Design on the Yield
of Mudcrab
(Scylla serrata) Using Bread Meal as Supplemental Feed
% SUPPLEMENTAL SAMPLING
FEED per
COMPARTMENT
1 (3 %) X X
X
2 (5 %)
3 (7 %) X X
X
4 (10 %)
X X
5 (15 %) X
X X
X
X X
Randomized Complete Block Design (RCBD)
This experimental design uses a group of test
plants and animals as subjects of the study which
are studied once but subsequent treatments
applied are replicated to determine the cause of
change. There is control in this design and the
subjects will undergo randomization process.
Randomized Complete Block Design (RCBD)

A randomized block design groups are

participants who share a certain
characteristic together to form blocks
and then the treatment options get
randomly assigned within each block.
 STUDY PARTICIPANTS

1. Divide the
sample into all
Subgroup 1: gender
Subgroup 2:
All males subgroups (also All females
called blocks)

2. Within each
subgroup,
randomly assign
T C participants to T C
either treatment
or control
 Table 5.11. Sample of Randomized Complete Block Design
(RCBD) in Culturing Abalone (Haliotis asinina) in Fish Cages
Using Fish Meal, Shrimp Meal, and Fish Silage as Supplemental
Feeds
SUPPLEMENTAL REPLICATION
FEEDS 1 2
3
Fish Meal X X
X
Shrimp Meal
X X
X
Fish Silage
X X
X
Correlational Design

Used to determine the relationship

of two dependent variables, X and
Y, on how they are manipulated by
the independent variable.
Table 5.13. Sample of Correlational Design of Culturing Milkfish
(Chanos chanos) on the Fishpond Using Fish Silage as
Supplemental Feed
WEIGHT (X) LENGTH (Y)
(grams) (centimeters)
MILKFISH
1 X X
X X
2 X X
3 X X
4 X X
X X
5 X X
6 X X
7 X X
QUASI-EXPERIMENTAL
DESIGN