Exam 3 Flashcards
Highly structured studies of cause and effect applied to determine the effectiveness of an intervention.
experimental designs
a subgroup of the sample of an experimental study from which the intervention is withheld.
control group
studies of cause and effect similar to experimental designs but using convenience samples or existing groups to test interventions.
quasi-experimental designs
a subgroup of the sample of a quasi-experimental design from which the intervention is withheld. Subjects are similar to and COMPARED with the experimental group, but they are not randomly assigned.
comparison group
the strongest type of quasi-experimental design in which subject responses in two or more groups are measured before and after an intervention.
nonequivalent comparison group before/after design
a type of quasi-experimental design in which data are collected after the intervention is introduced. lack of baseline data may introduce extraneous variables in the results.
nonequivalent comparison group post-test only
an intact-group design that relies on observation of the relationships between naturally occurring differences in the intervention and the outcome.
ex post facto research
a intact-group design that involves categorization of subjects into groups. an outcome of interest is measured and differences are attributed to the differences in classification of subjects.
casual-comparative
an intact group designs that involves observation of subjects who exhibit a characteristic matched with subjects who do not. differences between the subjects allow study of relationships between risk and disease without subjecting healthy individuals to illness.
case-control study
a type of quasi-experimental design in which only one group receives the intervention; an outcome is measured repeatedly overtime.
time-series design
most design decisions are made before the research begins
priori design (quantitative studies)
statistical tests that are appropriate for data that are normally distributed (that is, fall in a bell curve).
PARAMETRIC TESTS
statistical tests that make no assumptions about the distribution of the data.
nonparametric tests
statistical tests that are able to yield reliable results even if their underlying assumptions are violated.
robust tests
analysis of a single variable in descriptive statistics or a single dependent variable in inferential analysis
univariate analysis