RESEARCH
DESIGN
Dr. Nadia k. Alaswad
On completion of this lecture, you will be prepared to :
1. Identify criteria for exploratory, descriptive, and explanatory studies.
2. Define experimental research.
3. Differentiate between internal and external validity in experimental designs.
4. Identify six threats to internal validity.
5. Identify three threats to external validity.
6. Distinguish among true experimental, quasi-experimental, and pre-experimental designs.
7. Discuss four types of nonexperimental research designs.
Glossary:
Comparative studies Pre-experimental designs
Comparison group Prospective studies
Control group Quasi-experimental designs
Correlational studies Random assignment
Descriptive studies Retrospective studies
Experimenter effect Study limitations
Exploratory studies Survey studies
Ex post facto studies Time-series design
External validity True experimental designs
Hawthorne effect Manipulation
Internal validity
INTRODUCTION
This lecture introduces the concept of research design,
which is the pattern, method, or plan, for a research
study. The choice of a research design concerns the
overall plan for the research study.
According to the amount of existing knowledge about
the variable(s) can be used as the criterion for classifying
research as exploratory, descriptive, or explanatory.
Exploratory studies
Exploratory studies are conducted when little is known about the phenomenon of
interest, a flexible approach rather than a structured approach to data collection would
be used.
To determine what questions, need to be asked, you would conduct a review of the
literature. It is likely that you would find little written on this topic therefore,
exploratory Hypotheses are not appropriate.
Descriptive studies:
In descriptive studies, phenomena are described or the relationship between
variables is examined. A descriptive study is similar to an exploratory study
however, the two categories can be distinguished by considering the amount
of information that is available about the variable(s) under investigation.
When enough information exists to examine relationships between variables,
descriptive studies may be conducted in which hypotheses are tested.
Example: Old age and mortality rate of patients with COVID-19
Explanatory studies
Explanatory studies search for contributing explanations for the relationships
among phenomena. This type of research is usually experimental. Enough
knowledge exists about the variables of interest that the investigator can
exercise some degree of control over the research conditions and manipulate
one or more of the variables.
Example: Mesenchymal Stem Cell Infusion Shows Promise for Fighting
Coronavirus (COVID-19) in elderly patients.
Although the terms exploratory, descriptive,
Research design
and explanatory research can be used to
indicate the type of study being conducted.
Quantitative Qualitative
Furthermore, the designs can be classified
into two broad categories of quantitative
Experimental
and qualitative designs.
Quantitative designs are divided into Nonexperime
ntal
experimental and nonexperimental
designs.
What is experimental research?
Experimental research is concerned with cause-and-effect relationships. A
cause-and-effect relationship occurs when one thing or event makes some other
thing or event happen.
All experimental studies involve manipulation or control of the independent
variable (cause) and measurement of the dependent variable (effect).
For example: Effect of Regular
Cause Exercise and obesity
Effectrate.
independent dependent
variable variable
Validity of experimental designs
In experimental studies, as well as in other types of research, the researcher is
interested in controlling extraneous variables that can influence study results.
Extraneous Variables are those variables the researcher is not able to control,
or does not choose to control, and which can influence the results of a study.
Other names for extraneous variables are study limitations..
Internal and external validity in experimental
External designs
validity
would we expect
The internal validity of an experimental the same results
design concerns the degree to which changes with other
samples of
in the dependent variable (effect) can be participants, or
attributed to the independent variable research
conditions?
Internal validity
(cause). Threats to internal validity are
The observed
extraneous factors other than the differences in a
dependent variable
independent variable included (obesity) are only
related to an
External validity concerns the degree to independent variable
(Exercise)
which study results can be generalized to
Threats to internal validity
1. Selection bias: The selection process for the participant subjects have biased the
results of the study.
2. History: The threat of history occurs when some event besides the experimental
treatment occurs during the study, and this event influences the result.
3. Maturation: becomes a threat when changes that occur within the subjects
during an experimental study influence the study results.
Threats to internal validity (Cont.)
4- Testing: threat may occur in studies where a pretest is given or where subjects
have knowledge of baseline data.
5- Instrumentation Change: When instruments such as sphygmomanometers
are used in the pretest and posttest phases of a study these instruments should be
checked for their accuracy throughout the study.
6- Mortality: occurs when the subjects do not complete a study.
Threats to external validity
1. Hawthorne Effect: occurs when study participants respond in a certain
manner because they are aware that they are being observed.
2. Experimenter Effect: is a threat to study results that occurs when researcher
characteristics or behaviors influence subject behaviors.
3. Reactive effects of the pretest occurs when subjects have been sensitized to
the treatment because they took the pretest.
Types experimental Research
designs
TRUE QUASI- AND PRE-
EXPERIMENTAL. EXPERIMENTAL. EXPERIMENTAL
DESIGNS
True experimental designs
The true experimental designs are those in which the researcher has a great deal of
control over the research situation. A true experimental design has three criteria;
1- The researcher manipulates the experimental variable(s)
2. At least one experimental and one comparison group are included in the study.
3. Subjects are randomly assigned to either the experimental or the comparison
group.
Types of True experimental designs
1- Pretest-posttest 2- Posttest-only 3- Solomon four-
control control group group design.
design,
Pretest-posttest control
It is probably the most frequently used experimental design. In this design,
(a) the subjects are randomly assigned to groups,
(b) a pretest is given to both groups,
(c) the experimental group receives the experimental treatment, and the
comparison group receives the routine treatment or no treatment, and
(d) a posttest is given to both groups.
R O1X O2 (Experimental group)
R O1 O2 (Comparison group)
Posttest-only control group design
In the posttest-only control group design,
(a) Subjects are randomly assigned to groups,
(b) The experimental group receives the experimental treatment, and
the comparison group receives the routine treatment or no treatment,
(c) a Posttest is given to both groups.
R X O2 (Experimental group)
R O2 (Comparison group)
Quasi-Experimental Designs
Quasi-experimental designs are those in which there is either no
comparison group or subjects are not randomly assigned to groups.
Types of quasi-experimental designs.
1- Nonequivalent control group design.
2- Time-series design.
THE SOLOMON FOUR-
GROUP DESIGN
is a type of experiment where participants get randomly assigned
to either 1 of 4 groups that differ in whether the participants
receive the treatment or not, and whether the outcome of interest
is measured once or twice in each group.
1.A treatment group with both pre-intervention and post-
intervention measurements (a.k.a. pretest and posttest)
2.A control group with both pretest and posttest measurements
3.A treatment group with only a posttest measurement
4.A control group with only a posttest measurement
Types of quasi-experimental designs.
1- The nonequivalent control group design is similar to the pretest-posttest
control group design except There is no random assignment of subjects to
the experimental and comparison groups.
O1X O2 (Experimental group)
O1 O2 (Comparison group)
2- Time-Series Design
In a time-series design, the researcher periodically observes or measures
the subjects. The experimental treatment is administered between two of the
observations.
O1 O2 O3 X O4 O5 O6
Pre-experimental Designs
Pre-experimental designs is considered very weak and in which the researcher has little
control over the research. Its simplest form of 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.
Types: pre-experimental designs
1- One-shot case study: a single group is exposed to an experimental treatment and observed
after the treatment. XO
2- One-group pretest posttest design: It provides a comparison between a group of subjects
before and after the experimental treatment. O1 X O2
Non-experimental research designs
Non-experimental research is the most proper type of research to obtain the
needed data (Descriptive). In trying to determine clients’ perceptions of
pain, the only way to obtain this information would be to ask these clients
about their pain.
Types of non-experimental research;
1- Survey studies: are investigations in which self-report data are collected from
samples with the purpose of describing populations on some variable(s) of interest.
2- Correlational studies, the researcher examines the strength of relationships between
variables by determining how changes in one variable are associated with changes in
another variable.
3- Comparative studies: examine the differences between intact groups on some
dependent variable of interest. This description may sound like the aim of many
experimental studies.
Comparative studies:
Comparative studies are frequently classified as;
- Retrospective (ex post facto studies) after the fact
- Prospective.
In retrospective studies, the dependent variable (effect) is identified in the present, and an
attempt is made to determine the independent variable (cause of the disease) that occurred
in the past.
While, In prospective studies the independent variable or presumed cause (e.g., high
cholesterol blood levels) is identified at the present time, and then subjects are followed in
the future to observe the dependent variable (e.g., incidence of coronary artery disease).
Types of non-experimental research
(Cont.);
4- Methodological Studies:
Nurse researchers must be sure to use instruments in research projects that are valid
and reliable measures of the variables of interest. Methodological studies are concerned
with the development, testing, and evaluation of research instruments and methods.
5- Secondary Analysis Studies:
Sometimes researchers gather a lot of data in a study. They may not actually analyze
all the data that were gathered. In secondary analysis studies, data are analyzed that
were gathered in a previous study.
