Transcript Document

NEAR EAST UNIVERSITY
FACULTY : EDUCATION SCIENCES INSTITUTE
DEPARTMENT: ENGLISH LANGUAGE TEACHING



Sherwan Najmaldin Noori
Student No. (20143744)
Suppervised by: Asst. Prof. Dr. Cise Cavusoglu
Experimental Study
experiment is a study in which a treatment,
procedure, or program is intentionally
introduced and a result or outcome is observed.
An experimental study is a type of evaluation that
seeks to determine whether a program or
intervention had the intended causal effect on
program participants.
Experimental Design
Experimental design is a blueprint of the
procedure that enables the researcher to test
his hypothesis by reaching valid conclusions
about relationships between independent and
dependent variables.
Types of experimental design
The "One-Shot Case Study"
Treatment
X
Post-test
O
No control group. This design has virtually no internal or
external validity.
2 Group, Post-test Comparison
Treatment
X
Post-test
O
O
The main advantage of this design is randomization. The post-test
comparison with randomized subjects controls for the main effects
of history, maturation, and pre-testing; because no pre-test is used
there can be no interaction effect of pre-test and X. Another
advantage of this design is that it can be extended to include more
than two groups if necessary.
One group Pre-test, Post-test
Pre-test
O
Treatment
X
Post-test
O
Minimal Control. There is somewhat more structure, 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.
Two groups, Nonrandom Selection, Pre-test, Post-test
Group
Experimental group
=E
Control Group = C
Pre-test
O
O
Treatment
X
Post-test
O
O
The main weakness of this research design is the internal validity
is questioned from the interaction between such variables as
selection and maturation or selection and testing. In the
absence of randomization, the possibility always exists that some
critical difference, not reflected in the pretest, is operating to
contaminate the posttest data.
Two groups, Random Selection, Pretest, Post-test
Group
Experimental
group = E (R)
Control Group =
C (R)
Pre-test
O
O
Treatment
X
Post-test
O
O
The advantage here is the randomization, so that
any differences that appear in the posttest
should be the result of the experimental variable
rather than possible difference between the two
groups to start with. This is the classical type of
experimental design and has good internal
validity.
Experimental Research
Experimental research is an attempt by the
researcher to maintain control over all factors
that may affect the result of an experiment. In
doing this, the researcher attempts to
determine or predict what may occur.
Steps in Planning and 5ing
Experimental Research
• Select a topic
• Review the relevant literature and define a
research question
• Develop a research hypothesis
• Select and assign participants to groups
• Select measurement instruments
• Define and administer experimental treatments
• Collect and analyze data
• Make a decision about the hypothesis
• Formulate conclusions
Selecting a Topic.
As with other research methods, the experimental researcher bases
the topic selection on personal interest, experience, and an initial
review of the literature. Typically in experimental research, the
researcher is interested in determining if some treatment causes a
significant change in behavior.
Review the relevant literature and
define a research question
The researcher does an exhaustive literature review to determine the
findings of current research on the topic of interest. This means that
the researcher examines past literature to determine how others
have researched the same topic, what variables or issues were
studied, discussed, or both, and what the findings of those studies
indicated.
Develop a research hypothesis
A research hypothesis is an educated guess
that states the expected outcome of the study.
The researcher is “educated” through the
literature review. Based on the findings of the
literature review, the researcher develops and
states a hypothesis that indicates the
expected causal relationship between the
variables.
Types of hypothesis in Experimental Study
• Directional Hypothesis
States the direction or the expected outcome.
That is, the researcher feels confident enough to
suggest which group would outperform the other
group(s).
• Non-directional Hypothesis
Simply states that there will be some difference
between the variables, but the direction of that
difference is not being predicted.
Types of hypothesis in Experimental Study
• Null hypothesis
states that no significant difference between
the variables is expected after the treatment is
applied. The null hypothesis is implicit in all
experimental research. That is, inferential
statistics always test the null hypothesis, and in
most cases, the researcher hopes to disprove the
null hypothesis in favor of the research
hypothesis.
Select and assign participants to groups
Most experimental studies have at least two
groups, often referred to as the experimental
and control groups. In an experimental study,
the researcher randomly selects and about
assigns participants to groups. Random
selection allows the researcher to take the
findings based on the sample and generalize
those findings back to the entire population.
Select measurement instruments
Instruments or measurement tools for an
experimental study are selected with the
same care and attention as in other types of
research. You want to be certain that the
instrument you select is an appropriate
measure for your dependent variable.
Define and administer experimental treatments
A major part of creating a research proposal
is defining the treatments to be administered
to the participants, also known as the
research plan. This plan should describe all
procedures to be used in the study.
Specifically, what happens to the participants
in each group? How does the treatment for
the experimental group differ from that of the
control group?
Collect and analyze data
The data produced by experimental studies
are quantitative, the researcher who actually
conducts a study examines the data using
statistical procedures. The type of statistical
analysis depends on the type of data you
collected.
Formulate conclusions
The decision made about the hypothesis in an
experimental study is based on statistical
analysis of a study’s data and forms the basis
for the conclusions of a study. Confirming a
research hypothesis can add to the body of
knowledge on a topic and have practical
implications.
Make a decision about the hypothesis
The data collected and analyzed will provide
either support for your research hypothesis or
evidence to the contrary. In general, the
researcher wants to reject the null hypothesis,
which states that there is no real difference
between the treatment groups—in other
words, that any difference found was due to
chance and not to the experimental treatment.
Threats to Experimental Study
Internal validity is the degree to which observed
changes in a dependent variable can be attributed to
changes in an independent variable. Asks the
question, “ Are the measurements I make on my
dependant (i.e. the variable I measure) variable
influenced only by the treatment, or are there other
influences which change it?”
Threats to Experimental Study
• External Validity External validity has to do with the
generalize-ability of the research findings; to what extent can
the findings of an experiment or quasi-experiment be
generalized to and across various populations, settings, and
epochs? To how much the results are generalized to target
population.
Internal Validity Threats
•
•
•
•
•
•
•
History
Maturation
Testing
Instrumentation
Statistical regression
Differential selection of subjects
Mortality
Internal Validity Threats
History
when changes in the dependent variable are due to some
extraneous event that takes place between pre- and posttest,
it makes it difficult to determine whether the results were due
to the experimental manipulation (i.e. changes in the
independent variable) or to the extraneous event.
How to control:
Include an appropriate control group
Internal Validity Threats
Maturation
Change in the participant over the course of time, where such
change is not the focus of interest of the research study. This
may involve growth (e.g., getting smarter or stronger) or
decline (e.g., dementing).
How to control
Include an appropriate control group
Internal Validity Threats
Testing
The reactive effects of testing where the very act of assessment
influences the variable under investigation. Some measures are
highly reactive, whereas other measures are largely un reactive . Also,
repeated testing can increase familiarity with the test, which might
bias scores.
How to control
This threat can be dealt with in various ways, such as by selecting un
reactive measures (e.g., unobtrusive observation) or by including a
control group.
Internal Validity Threats
Instrumentation
When an effect is due to a change in the measuring instrument from
pre- to posttest rather than due to the manipulation of the
independent variable. Instrumentation can affect all forms of
measurement, including observers, self-report tools, interview
schedules, and devices that measure physiological processes.
How to control
Use reliable or valid instrument(s); train observers and use short
observation periods.
Internal Validity Threats
Statistical regression
People selected for extreme scores (very high or very low) will
have less extreme scores when they are retested on the same
or related variables. Why does regression occur? The farther a
score is from the mean, the more extreme it is.
How to control
Include a control group selected using same criteria
Internal Validity Threats
Differential selection of subjects
When the effects on the dependent variable
arise from differences in the kinds of people in
the experimental groups.
How to control
Use random assignment to groups; pretest
participants to see if groups are similar
Internal Validity Threats
Mortality or Attrition
If a participant with a particular score drops out
of the experimental group, a control group
member with a comparable score on the pretest
can be eliminated, thereby controlling for
mortality or subject attrition.
How to control
Pretest to obtain information for examining who
dropped out of one group and eliminate a similar
participant from the other group to maintain
equivalent groups; maintain contact with both
treatment and control groups
External Validity Threats
Multiple-treatment interaction
Participants are exposed to multiple treatments that are
part of some overarching treatment or simply exposed
to more than one treatment; when this occurs, it might
be difficult to determine which treatment resulted in
any difference that is found, limiting generalizability.
How to control
Limit the number of treatments delivered, or deliver
different treatments at different times; if one treatment
has many components, establish comparison groups
receiving different components.
External Validity Threats
Pretest-treatment interaction
Pretest sensitizes participants to the treatment, and
outcome would be different if the participants had
not been pretested.
How to control
Include appropriate control groups who also receive
pretests and a treatment group that receives no
pretest.
References
Bartlett, F. (1995). Remembering : a study in experimental and social psychology. Cambridge
New York: Cambridge University Press.
Brachit, G. H., Glass, G. V. (1968) The External Validity of Experiments.
Research Journal, 5(4) 437-474.
American Educational
Lodico, M., Spaulding, D., & Voegtle, K. (2006). Methods in educational research: From theory
to practice. San Francisco: Jossey Bass.
Markstein, G. H. (2012). Experimental and theoretical studies of flame-front stability. Journal of
the Aeronautical Sciences (Institute of the Aeronautical Sciences), 18(3).
Wind Goodfriend: True Experimental Design. (n.d.). Education Portal Web site. Retrieved
from http://education-portal.com/academy/lesson/true-experimental-design.html#lesson.
Thank
you
.
--------------------------------------------------------------------------------