You are on page 1of 73

EDUCATION RESEARCH METHODS

PURE EXPERIMENTAL RESEARCH

 Experimental research refers to the structure or framework of


an experiment.
 It is a study that strictly adheres to a scientific research design.
It includes a hypothesis, a variable that can be manipulated by
the researcher, and variables that can be measured, calculated
and compared.
PURE EXPERIMENTAL RESEARCH

 Most importantly, experimental research is completed in a controlled


environment. The researcher collects data and results will either
support or reject the hypothesis. This method of research is referred
to a hypothesis testing or a deductive research method (Babbie 4).
 With an experimental research design, the researcher lays out how
he or she will manipulate one or more independent variables and
measure their effect on the dependent variables.
PURE EXPERIMENTAL RESEARCH

 An experimental design must deal with four issues namely;


The people who participate in the experiment,
The independent variable or variables, which are also called the treatment,

The dependent variable, or the effect that the researchers measure and the plan

for controlling variables..


The experiment is the design of choice for studies that seek to make causal

conclusions, and particularly evaluations of education innovations. (Slavin, 2002, p.


18)
PURE EXPERIMENTAL RESEARCH

 Experimental design is of many types as shown in the


diagram below;
TRUE EXPERIMENTAL DESIGN

 True experimental designs have several variants namely;


The pretest-post-test control and experimental group design,
The two control groups and one experimental group pretest, post-test-

post-test design,
The post-test control and experimental group design

The pretest-post-test two treatment design,

The matched pairs design,

The factorial design, The parametric design and

Repeated measures design.


The pre-test-post-test control and experimental group design

 Here participants are randomly assigned to either the


experimental group or the control group.
 It is depicted as follows;
 RO XO
 RO O
 The experimental group receives the treatment and the control
group receives either no treatment or an alternative treatment
(to avoid such threats to validity).
The pre-test-post-test control and experimental group design

 Pre-test-post-test can be used in education for instance, If we


focus only on the two groups of schools (trained versus
traditional) in Borman et al. (2007), this study can be used to
illustrate the design. Borman and his associates used a pretest-
posttest control group design to study the impact of their
experimental treatment on reading comprehension. The group
who received training is the experimental group and this group
is depicted in the top line of the design, where;
The pre-test-post-test control and experimental group design

 R- Indicates they were randomly chosen to participate in the


training
 O- Indicates the students were pretested and their vocabulary
knowledge prior to training
 X- Indicates they received the training
 O- Indicates the students were posttested on their reading
comprehension
The pre-test-post-test control and experimental group design

 The control group is depicted in the second line of the diagram.


They were also randomly assigned to their condition (R), were
pretested on their vocabulary (O), and then participated in
traditional reading instruction. The blank space in the second
line between the two Os is used to indicate that this group did
not receive the experimental treatment. They were also
pretested at the end of the study to determine their reading
comprehension levels.
The pre-test-post-test control and experimental group design

 Borman et al. (2007) were able to conclude that students of the


teachers who participated in the training had higher reading
comprehension scores as compared to the control group at
greater than chance level. They attributed the increase to their
experimental treatment because students who were in the
control group and had not been exposed to the treatment did
not score as high on the reading comprehension test.
The pre-test-post-test control and experimental group design

 Campbell and Stanley (1963) selected one design from the


comprehensive treatment to identify the essential features of
what they term a ‘true experimental’ and what Kerlinger (1970)
refers to as a ‘good design. Along with its variants, the chosen
design is commonly used in educational experimentation.
The pre-test-post-test control and experimental group design

 The pretest-post-test control group design can be represented


as:
Experimental RO1 X O2
Control RO3 X O4
The pre-test-post-test control and experimental group design

 It has one weakness which is the interaction effect of testing. Good (1963)
explains that whereas the various threats to the validity of the experiment are
thought of as main effects, manifesting themselves in mean differences
independently of the presence of other variables, interaction affects, as their
name implies, are joint effects and may occur even when no main effects are
present For example an interaction effect may occur as a result of the pretest
measure sensitizing the subjects the experimental variable. Interaction
effects can be controlled for by adding to the pretest –post-control group
design two more groups that do not experience the pretest measures.
The post-test control and experimental group design;

 Here participants are randomly assigned to a control group and


an experimental group, but there is no pretest. The
experimental group receives the intervention and the two
groups are given only a post-test. The design is:
 Experimental1 X1 O1
 Experiment2 X2 O2
The pretest-post-test two treatment design

 Here participants are randomly allocated each of two


experimental groups. Experimental group 1 receives
intervention 1 and experiment group 2 receives intervention 2.
Pretests and post-tests are conducted to measure changes in
individuals in the two groups. The design is;
Experimental 1 RO1 X1 O2
Experimental 2 RO3 X2 O4
The pretest-post-test two treatment design

 The true experiment can also be conducted with one control


group and two or more experimental groups.

Experiment1 RO1 X O2
 Experiment2 RO3 O4

Control RO5 X5
The two control groups and one experimental group pretest-post-test

 This is the Solomon(1949) design, intended to identify the


interaction effect that may occur if the subject deduces the
desired result from looking at the pretest and the post-test. In
the Solomon variant the second control group receives the
intervention but no pretest. This can be modeled thus:
Experimental RO1 X O2
Control1 RO3 O4

Control2 x O5
The matched pairs design

 As the name suggests, here participants are allocated to control


and experimental groups randomly, but the basis of the
allocation is that one member of the control group is matched to
a member of the experimental group on the several
independent variables considered important for the study (e.g.
those independent variables that are considered to have an
influence on the dependent variable, such as sex, age, ability).
The matched pairs design

 So, first pairs of participants are selected who are matched in


terms of the independent variable under consideration e.g.
whose scores on a particular measure are the same or similar),
and then each of the pair is randomly assigned to the control or
experimental group.
The matched pairs design

 Randomization takes place at the pair rather than the group


level. Although, as the name suggests, this ensures effective
matching of control and experimental groups, in practice it may
not be easy to find sufficiently close matching, particularly in a
field experiment, although finding such a close match in a field
experiment may increase the control of the experiment
considerably.
Limitations of Matched Pair Design

 Borg and Gall (1979) indicate that difficulties arise in the close
matching of the sample of the control and experimental groups.
This involves careful identification of the variables on which the
matching must take place.

 Borg and Gall (1979: 547) suggest that matching on a number


of variables that correlate with the dependent variable is more
likely to reduce errors than matching on a single variable.
The factorial design

 In an experiment, there may be two or more independent variables acting on the


dependent variable. For example, performance in an examination may be a
consequence of availability of resources (independent variable one: limited
availability, moderate availability, high availability) and motivation for the subject
studied (independent variable two: little motivation, moderate motivation, high
motivation). Each independent variable is studied at each of its levels (in the example
here it is three levels for each independent variable)
The Factorial Design

 Here the possible combinations are: 1+4, 1+5, 1+6, 2+4, 2+5,
2+6, 3+4, 3+5 and 3+6. This yields 9 groups (3x3
combinations). Pretests and post-tests or post-tests only can be
conducted. I t might show , for example that limited availability
of resources and little motivation had a statistically significant
influence on examination performance, whereas moderate and
high availability and high motivation had statistically significant
effect on performance, whereas high motivation and limited
availability did not, and so on.
Advantage Of The Factorial Design

 It has an advantage of allowing researchers to test for effects of


different kinds of variables that might be expected to influence
outcomes, such as grade level, age, gender, ethnicity or race,
or disability type.
Limitation of The Factorial Design

 The main limitation in the number of variables arises from the


number of participants needed for each condition and the
resulting complexity in interpretation of the results.
Parametric Design
 Here participants are randomly assigned to groups whose parameters are fixed in
terms of the levels of the independent variable that each receives. For example, an
experiment is conducted to improve the reading abilities of poor, average, good and
outstanding readers (four levels of the independent variable ‘reading ability). Four
experimental groups are set up to receive the intervention, thus; experimental group
one (poor readers); experimental group two (average readers); experimental group
three (good readers); experimental group four (outstanding readers). The control
group (group five) would receive no intervention. The researcher could chart the
different effects of the intervention on the groups , and thus have a more sensitive
indication of its effects than it there was only one experimental group containing a
wide range of reading abilities; the researcher would know which group was most and
least affected by the intervention.
Parametric Designs

 Parametric designs are useful if an independent variable is


considered to have different levels or a range of values which
may have a bearing on the outcome.
Repeated Measure Designs

 Here participants in the experimental groups are tested under


two or more experimental conditions. For example, a member of
the experimental group may receive more than one intervention
which may or may not include a control condition. This is a
variant of the matched pairs design and offers considerable
control potential, as it is exactly the same person receiving
different interventions.
Repeated Measure Designs

 Order effects raise their heads here: the order in which the
interventions are sequenced may have an effect on the
outcome; the first intervention may have an influence- a carry-
over effect – on the second, and the second intervention may
have an influence on the third and so on.
Repeated Measure Designs

 Repeated measures designs are useful if it is considered that


order effects are either unimportant or unlikely , or if the
researcher cannot be certain that individual differences will not
obscure treatment effects as it enables these individual
differences to be controlled.
Types of True Experimental Designs

 There are three basic types of True Experimental Designs:

Post-Test Only Control Group Design,


Pre-Test Post-Test Control Group Design,

Solomon Four Group Design.


Post-Test Only Control Group Design

 It is similar to the pretest-posttest control group design except


that no pretest is given. With this research design, test units are
randomly assigned to the experimental and control groups. The
experimental group is exposed to the treatment and then both
the experimental and control groups are measured. But, there is
only one measurement is taken.
Post-Test Only Control Group Design

 Here is the standard notation for a Post-Test Only study: The


effect of the treatment is calculated as O 1 - O2.
Post-Test Only Control Group Test
 Again, Borman et al. (2007) had not administered a pretest,
then the study of reading comprehension would exemplify the
posttest-only control group design.
R- Indicates the random assignment
X- Indicates the treatment of the experiment that the experimental group

received
O- Indicates the measure of the students’ reading comprehension

scores.
 The blank space between R and O on the second line of the
design indicates that the control group did not receive the
experimental treatment.
Advantages of Post-Test Only Control Group Design
 The advantage of this research design is that the random
assignment of the test units should produce roughly equal
control and experimental groups before the treatment is
administered. And, the mortality for the control and experimental
groups should be similar.
 Another advantage is that for large enough groups, this design
can control for most of the same threats to internal and external
validity as the classic controlled experimental design. For
example, it eliminates the threat to internal validity of pre-testing
by eliminating the pre-test.
Disadvantage of Post-Test Only Control Group Design

 It has a disadvantage such as; there can be a threat to internal


validity called a testing threat.
Pre-Test - Post-Test Control Group Design

 Here is the standard notation for a Pre-Test - Post-Test Control


Group study:
Pre-Test - Post-Test Control Group Design

 Selection bias is controlled by the randomized assignments of


test units. Mortality can be a problem if it is not relatively equal
between the experimental and control groups. History can also
be an issue if these factors affect the experimental and control
groups unequally.
 The treatment effect or TE is measured by (O 2 O1) - (O4 O3).
Advantage of Pre-Test - Post-Test Control Group Design

 This design has an advantage; not only can the researcher


determine if there is a difference between experimental and the
control group, but also can determine how much of a change or
how much growth there was between the pretest and the
posttest.
Disadvantage of Pre-Test - Post-Test Control Group Design

 It has also a limitation; there can be a threat to internal validity that is called the
testing threat.
 This posttest is limited in scope and contain many threats to validity. It is very poor at
guarding against assignments bias, because the researcher knows nothing about the
individual differences within the control group and how they might have affected the
outcome. Even with randomization of the initial groups, this failure to address
assignment bias means the statistical power is weak. With this research design, test
units are randomly assigned to experimental and control group A pre-test measure is
taken from both groups.
 The threat can occur when there is an interaction between the pretest and the
treatment.
Solomon Four Group Design
 It was developed for the researcher who is worried about the
effect of pretesting on the validity of the results.
R O X O

RO O

R XO

 As shown above the researcher combines the pretest-posttest control group


design with the posttest-only control group design. Because half the
participants receive the pretest and half do not, the researcher can test the
effect of taking the pretest and thus eliminate that threat to validity without
sacrificing the valuable information that can be obtained from pretest.
Disadvantage of Solomon Four Group Design

 The disadvantage of this design is that it necessitates having


four groups and thus increases the number of participants that
one would need to test.
Solomon Four Group Design
 The design attempts to assess the impact of pretesting on
subsequent measures. It is used when the researcher suspects
that earlier tests influence the results of later tests. With this
research design, test units are randomly allocated to two
experimental groups and two control groups. One of the
experimental groups and one of the control groups is
measured. Both experimental groups are then exposed to a
treatment. Afterwards, both experimental and control groups are
measured. A total of six measurements are taken. The design
aims to account for pre-testing bias and pre-test manipulation
interaction bias.
Standard Notation For A Solomon Four Group Study
 Here is the standard notation for a Solomon Four Group study:
Solomon Four Group Design

 This design has advantages as follows; It allows the researcher


to exert complete control over the variables and allows the
researcher to check that the pretest did not influence the
results.
 It has limitations such as when including a pretest in a study
design it introduces threats to both internal and external validity.
The Solomon four-group design employs a combination of
pretest –posttest design and posttest-only to combat this.
Classification Of Experimental Designs

 Experimental designs are classified into broad categories, VIZ.,


informal experimental designs and formal experimental designs.
Informal experimental designs are those designs that normally
use a less sophisticated form of analysis based on differences
in magnitude, whereas formal experimental designs offer
relatively more control and use precise statistical procedures for
analysis.
Experimental Designs

 Important experiment designs are as follows;


 (a) Informal experimental designs such as
Before –and- after without control design,
After-only with control design and

Before-and-after with control design.

 (b) Formal experimental designs include;


completely randomized design (C.R Design), Randomized block design
(R.B Design),
Latin square Design (L.S design), and

Factorial designs.
Procedures in conducting experimental research

 An experimental investigation must follow a set of logical


procedures. Those that we now enumerate, however, should be
treated with some circumspection. It is extraordinarily difficult
(and foolhardy) to lay down clear-cut rules as guides to
experimental research. At best, we can identify an ideal route to
be followed, knowing full well that educational research rarely
proceeds in such a systematic fashion.
Procedures in conducting experimental research

 First, researchers must identify and define the research


problem as precisely as possible, always supposing that the
problem is amenable to experimental methods.
Procedures in conducting experimental research

 Secondly, researchers must formulate hypotheses that they


wish to test. This involves making predictions about
relationships between specific variables and at the same time
making decisions about other variables that are to be excluded
from the experiment by means of controls. Variables,
remember, must have two properties.
Procedures in conducting experimental research

 The first property is that variables must be measurable.


Physical fitness, for example, is not directly measurable until it
has been operationally defined. Making the variable ‘physical
fitness’ operational means simply defining it by letting
something else that is measurable stand for it – a gymnastics
test, perhaps The second property is that the proxy variable
must be a valid indicator of the hypothetical variable in which
one is interested.
Procedures in conducting experimental research

 That is to say, a gymnastics test probably is a reasonable proxy


for physical fitness; height, on the other hand, most certainly is
not. Excluding variables from the experiment is inevitable, given
constraints of time and money. It follows therefore that one must
set up priorities among the variables in which one is interested
so that the most
Procedures in conducting experimental research

 Third, researchers must select appropriate levels at which to


test the independent variables. By way of example, suppose an
educational psychologist wishes to find out whether longer or
shorter periods of reading make for reading attainment in school
settings (Simon 1978).
Procedures in conducting experimental research

 The psychologist will hardly select five-hour and five-minute


periods as appropriate levels; rather, she is more likely to
choose thirty-minute and sixty-minute levels, in order to
compare with the usual timetabled periods of forty-five minutes’
duration.
Procedures in conducting experimental research

 In other words, the experimenter will vary the stimuli at such


levels as are of practical interest in the real life situation.
Pursuing the example of reading attainment somewhat further,
our hypothetical experimenter will be wise to vary the stimuli in
large enough intervals so as to obtain measurable results.
Comparing reading periods of forty-four minutes, or forty-six
minutes, with timetabled reading lessons of forty-five minutes is
scarcely likely to result in observable differences in attainment.
Procedures in conducting experimental research

 Fourth, researchers must decide which kind of experiment they


will adopt, perhaps from the varieties set out in this chapter.
Procedures in conducting experimental research

 Fifth, in planning the design of the experiment, researchers


must take account of the population to which they wish to
generalize their results. This involves making decisions over
sample sizes and
Procedures in conducting experimental research

 Sixth, with problems of validity in mind, researchers must select


instruments, choose tests and decide upon appropriate
methods of analysis.

 Seventh, before embarking upon the actual experiment,


researchers must pilot test the experimental procedures to
identify possible snags in connection with any aspect of the
investigation. This is of crucial importance.
Procedures in conducting experimental research

 Eighth, during the experiment itself, researchers must


endeavor to follow tested and agreed-on procedures to the
latter. The standardization of instructions, the exact timing of
experimental sequences, the meticulous recording and
checking of observations – these are the hallmark of the
competent researcher.
Procedures in conducting experimental research

 When to use pure experimental research? Experimental


research is applicable in social research when determining a
causal relationships among variables.
Procedures in conducting experimental research

 You must select the experimental group (where you can apply
treatment) and the control group. Selection of subjects in this
group is simply by randomization i.e. by chance. This will
enable you to control certain variables that may affect the
experiment since the subject are selected simply by chance.
The effects of the treatment on the experimental group can then
be compared to the control group. The independent variables
that causes the effects on the dependents variable can then be
determined by holding other extraneous variables constant.
Procedures in conducting experimental research

 (intervention) OO to the experimental group (i.e. manipulating


the independent variable) whilst holding every other variable
constant for the two groups; ensuring that the two groups are
entirely separate OO throughout the experiment (non-
contamination); the final measurement of yield and growth to
OO compare the control and experimental groups and to look at
differences from the pre-test results (the post-test); the
comparison of one group with another;
Challenges to Using Experimental Designs in Educational and Psychological Research

 Many challenges face the researcher who would like to use


experimental designs to investigate educational and
psychological phenomena. Several of these factors include:
School policies restricting differential treatment,
Difficulty in identifying appropriate comparison groups,

Small sample sizes, sampling bias, and ethical considerations.

 Because of these problems, some researchers have turned to


single-subject designs (described in Chapter 7) and qualitative
designs (see Chapter 8).
WAY FORWARD
 In addition to offering the best available treatment rather than no
treatment, Mark and Gamble (2009) list several ways that the concern
about denial of treatment could be addressed, including offering the
“the more effective treatment to those in the other group after the
study is over, when this is practical; providing participants with
benefits that leave them better off than they would have been without
participating in the study (e.g., payment for participation; health
services in a study of job training), even if these are unrelated to the
primary outcome variable” (p. 205).
WAY FORWARD
 In assessing the benefit-risk ratio for study participants, Mark
and Gamble (2009) argue that it is appropriate to consider
opportunities that would not have been present if the study had
not been conducted.
 They use the congressionally mandated experimental trial of an
Early Head Start program that created preschool opportunities
as an example of a situation in which those in the treatment
group would not have had access to the services in the
absence of the experiment.
WAY FORWARD

 Transformative researchers might ask: Is it true that this society


would not provide services to enhance the development of
children who are born into poverty unless an experimental study
was underway?
WAY FORWARD
 Situations in which children need specific interventions at
specific times in their development. Delay in receiving the
intervention may result in prolonging the undesirable conditions
and, possibly, irreversible delays in development.) 2. Have two
(or more) potentially beneficial treatments so all participants
receive some intervention. 3. Compare the treatment group
outcome to some carefully chosen standard. 4. Conduct intra-
individual comparisons rather than cross-group comparisons. 5.
Use individual baselines as comparison standards. 6. Include
minority researchers as part of the research team.
WAY FORWARD

 These authors maintain that experimental research is the only


type of research that can truly establish cause-and-effect
relationships, although they do recognize that there are many
educational problems for which experimental method is
inappropriate.
WAY FORWARD
 To conclude, I can say that experimental research is aimed at
drawing conclusions through controlling the extraneous factors
so that the researcher can provide definite conclusions with
regard to the effect of the independent variable on the
dependent one. Experimental research is suitable for research
whose goal is to examine cause-effect relationships, e.g.
explanatory research. It can be conducted in the laboratory or
field settings, depending on the aim of the research that is
being carried out.
REFERENCES

You might also like