EXPERIMENTAL

RESEARCH
DESIGN
MAJOR CHARACTERISTICS OF EXPERIMENTAL RESEARCH

 Researchers manipulate the independent variable.

Independent variables usually manipulated in educational experimental researches,

experimental, treatment
➢ methods of instruction, types of assignment / learning materials, rewards given to students, types of
questions asked by teachers

Dependent variables – criterion, outcome

➢ achievement, interest in a subject, attention span, motivation, attitudes toward a subject
MAJOR CHARACTERISTICS OF EXPERIMENTAL RESEARCH

 Researchers decide the nature of treatment ( what is going to happen to the

subjects of the study), to whom it is to be applied, and to what extent.

 Researchers want to see whether the treatment made a difference.

If the average scores of the groups differ in the posttest and researchers can’t find any sensible
alternative explanation for this difference, it can be concluded that the treatment did have an
effect and is likely the cause of the difference.
MAJOR CHARACTERISTICS OF EXPERIMENTAL RESEARCH

 Experimental research goes beyond description and prediction, beyond the

identification of relationships , and to at least a partial determination of
what causes them.
For instance, correlational studies demonstrate a strong relationship between socio-economic
level and academic achievement but experimental studies can demonstrate that improving
socioeconomic level will necessarily improve achievement.
RANDOMIZATION
Random selection

Every member of a population has an equal chance of being selected to be a member of a sample

Random assignment
Every individual has an equal chance of being assigned to any of the experimental or control conditions
being compared.
▪ takes place before the experiment begins
▪ enables to form equivalent groups
▪ eliminates the threats of other variables not only those of which the researchers are aware but also
those of which they are not aware that might affect the outcome of the study
▪ not a guarantee for equivalent groups unless both groups are sufficiently large
SOME EXPERIMENTAL STUDIES

 Quality of learning with an active versus passive motivational set

 Comparison of computer-assisted, cooperative, competitive, and individualistic learning

 An intensive group counseling dropout prevention intervention: isolating at-risk adolescents within
high schools
 The effects of student questions and teacher questions on concept acquisition

 Mnemonic versus nonmnemonic vocabulary-learning strategies for children

 Changing teaching practices in mainstream classrooms to improve bonding and behavior of low
achievers
EXPERIMENTAL RESEARCH
• try something and systematically
observe what happens!

1. 2 (or more conditions ) are compared

to assess the effect(s) of particular
conditions/treatments/independent
variable

2. Independent variable is directly

manipulated by the researcher
CONTROL OF EXTRANEOUS VARIABLES
Researchers in an experimental study have an opportunity to
exercise far more control than in most other forms of research.

▪ Determine the treatment

▪ Select the sample
▪ Assign individuals to groups
▪ Assign the group that will get the treatment
▪ Control other factors beside the treatment that may affect the outcome of
the study
▪ Measure the effect of the treatment when the treatment is completed
HOW TO MINIMIZE THREATS DUE TO SUBJECT CHARACTERISTICS
▪ Randomization
subjects randomly assigned to the various groups involved in the experimental study to
ensure that the effects of one or more possible extraneous variables have been
controlled

▪ Holding certain variables constant

Eliminate possible effects of a variable by removing it from the study. However, the
generalizability of the results of the study is correspondingly reduced.

▪ Building the variable into the design

Involves building the variable(s) into the study to assess their effects.
HOW TO MINIMIZE THREATS DUE TO SUBJECT CHARACTERISTICS
▪ Matching
Pairs of subjects can be matched on certain variables of interest like according to age
and then assign one member of each pair(randomly) to each of the comparison groups.

▪ Using subjects as their own control

Performance under both(or all) treatments is compared

▪ Using analysis of covariance

ANCOVA can equate groups statistically on the basis of a variable(covariate) like pretest
scores. The posttest scores of the subjects in each group are then adjusted accordingly.
EXPERIMENTAL RESEARCH DESIGNS
 TRUE EXPERIMENTAL DESIGNS

1.
where : X - exposure to the treatment
O – measurement of the dependent variable
R - random assignment

• Control of certain threats like subject characteristics and maturation is

excellent through random assignment. None of the subjects are measured
twice, hence, testing is not a threat.
• One of the best design to use provided there are at least 40 subjects in each
group.
2.

▪ Use of pretest may raise possibility of a ‘pretest treatment interaction’ threat since it may
alert the members of the experimental group to do better (or more poorly) on the posttest
than the members of the control group
▪ Trade-off – a means of checking whether the 2 groups are really similar, whether random
assignment actually succeeded in making the groups equivalent. If not equivalent, researcher
can seek to make them so by using one of the matching designs
▪ Pretest is necessary if the amount of change over time is to be assessed.
3.

▪ The randomized Solomon four-group design provides the best control of the
threats to internal validity.
▪ A weakness, however, is that it requires a large sample because subjects must be
assigned to four groups. Furthermore, conducting a study involving four groups at
the same time requires a considerable amount of energy and effort on the part of
the researcher.
4. To increase the likelihood that the groups of subjects
will be equivalent, pairs of individuals may be
matched on certain variables, the choice of which is
based on previous research, theory and/or
experience of the researcher.

refers that the members of each matched pair

5. are randomly assigned to the experimental
and control groups.

Pretest of the dependent variable is commonly

used to match but a measurement of any
variable that shows substantial relationship to
the dependent variable is appropriate.
QUASI EXPERIMENTAL DESIGN
 The use of randomization is not included.

 Researchers include other techniques to reduce threats to internal validity

1.
2.

▪ The M in this design means that the subjects in each group have
been matched (on certain variables) but not randomly assigned to
the groups.
▪ No assurance that they are equivalent because even though
matched, subjects already are in intact groups.
3. ▪ This arrangement involves 3 groups. The
order in which the groups receive
treatments should be determined
randomly.

▪ How is the effectiveness of the various

treatments determined?

▪ This design controls well for the subject characteristics threat to

internal validity but is particularly vulnerable to multiple-treatment
interference – that is, performance during a particular treatment
may be affected by one or more of the previous treatments.
TIME SERIES DESIGN

▪ Involves repeated measurements or observations over a period of time

both before and after treatment.
▪ An elaboration of the one-group pretest-posttest design where an
extensive amount of data is collected on a single group.

Is the researcher more confident that the treatment is causing the

improvement?
 FACTORIAL DESIGNS ▪ Modifications of either the posttest-only
control group or pretest-posttest control
group designs (w/ or w/o random
assignment) which allows investigation of
additional independent variables.
▪ Makes possible to determine interaction of
an independent variable with one or more
other variables, called moderator variables.
▪ It involves one treatment and one control group, and a
moderator variable having 2 levels ( Y1 and Y2). This
example has 2 groups treatment (X) and 2 control (C).
The groups receiving the treatment would differ on Y as
would the 2 groups under control. Since each variable
has 2 levels, the above design is a 2 x 2 factorial
design.
REVIEW A PUBLISHED EXPERIMENTAL STUDY ( IN YOUR AREA OF SPECIALIZATION ), CRITIQUE
THE STUDY, IDENTIFY ITS STRENGTHS, AND DISCUSS AREAS YOU THINK COULD BE IMPROVED.
IN CRITIQUING THIS STUDY, USE THE FOLLOWING SERIES OF QUESTIONS

1. Purpose/justification: Is it logical? Is it convincing? Is it sufficient? Do the authors show how the results of the study have important implications for theory,
practice, or both? Are assumptions made explicit?
2. Definitions: Are major terms clearly defined? If not, are they clear in context?
3. Prior research: Has previous work on the topic been covered adequately? Is it clearly connected to the present study?
4. Hypotheses: Are they stated? implied? appropriate for the study?
5. Sample: What type of sample is used? Is it a random sample? If not, is it adequately described? Do the authors recommend or imply generalizing to a population?
If so, is the target population clearly indicated? Are possible limits to generalizing discussed?
6. Instrumentation: Is it adequately described? Is evidence of adequate reliability presented? Is evidence of validity provided? How persuasive is the evidence or the
argument for validity of inferences made from the instruments?
7. Procedures/internal validity: What threats are evident? Were they controlled? If not, were they discussed?
8. Data analysis: Are data summarized and reported appropriately? Are descriptive and inferential statistics (if any) used appropriately? Are the statistics interpreted
correctly? Are limitations discussed?
9. Results: Are they clearly presented? Is the written summary consistent with the data reported?
10. Discussion/interpretations: Do the authors place the study in a broader context? Do they recognize limitations of the study, especially with regard to population and
ecological generalizing of results?
1.
2.
3.