One-Group Time Series Designs
The second most common quasi-experimental design is the one-group time
series design. This type of design may be used when neither randomization nor
a comparison group is possible. Researchers may opt to study one group over
a prolonged period of time prior to administering the intervention and then
make multiple observations after the intervention is conducted. For example,
the faculty decides to change the pass rate on exams from 75% to 80%. They
could compare the number of student nurses passing at 75% for four semesters
to the number who pass at 80% over four semesters. Although many factors
contribute to pass rates among student nurses, following the data for an ex-
tended period of time helps faculty to determine the effect of a policy change.
Preexperimental Designs
One-group posttest-only and nonequivalent-groups posttest-only designs are
often referred to as preexperimental rather than quasi-experimental. The dif-
ference between pre- and quasi-experimental designs is that quasi-experimental
designs, while lacking some elements of an experiment, use other strategies to
control for extraneous variables. With preexperimental studies, many threats
to internal validity can be found because these are posttest-only designs. An
example of a one-group posttest-only study is when a researcher implements
an educational intervention to teach new mothers the benefits of breastfeeding.
After the intervention, the mothers’ knowledge of breastfeeding was tested.
Without a pretest to determine the mothers’ previous knowledge and without
any information about their prior history of breastfeeding, it would be almost
impossible to determine what effect the intervention had on the breastfeeding
outcome. One-group posttest-only designs provide a low level of evidence, and
no change in nursing practice should be made based on this type of design.
Adding a comparison group slightly increases the quality of evidence found
in posttest-only designs. A nonequivalent-groups posttest-only design involves
manipulation of the IV and two or more groups of subjects who are compared
on the DV. For example, a researcher works in an agency where the policy is
that all new mothers will receive the breastfeeding educational intervention.
Because randomization of mothers is not possible, the researcher decides to
compare breastfeeding knowledge of mothers from a hospital requiring the
educational intervention to breastfeeding knowledge of mothers from a hospital
that does not offer that intervention. Because this is a nonequivalent-groups
posttest-only design, it is impossible for the researcher to have any informa-
tion about breastfeeding knowledge of the mothers in either group prior to the
intervention. It is impossible to determine the equivalence of the two groups
because the researcher does not have any pretest information. If the results of
KEY TERMS
one-group time
series design: A
quasi-experimental
design where
one group is
measured prior
to administering
the intervention
and then multiple
times after the
intervention
one-group
posttest-only
design: A
preexperimental
design involving
one group and
a posttest with
little control over
extraneous variables
nonequivalent-
groups posttest-
only design: A
preexperimental
design involving
two groups
measured after an
intervention with
little control for
extraneous variables
preexperimental:
A posttest-only
design that involves
manipulation of
the independent
variable but
lacks control for
extraneous variables7.2 Quasi-Experimental Designs 179