Chapter 9; Design Flashcards
Research Design
The overall plan for answering the research questions. Provides direction for the study.
Cause probing
Therapy, prognosis, and etiology questions. There is a hierarchy of designs for yielding best evidence.
Key criteria for inferring causality
- A cause (independent variable) must precede an effect or outcome.
- There must be a detectable relationship between a cause and effect or outcome
- The relationship between the two does not reflect the influence of a confounding variable.
Counterfactual
is what would have happened to the same people simultaneously exposed and not exposed to a causal factor. The effect is the difference between the two.
Experiments
involve an intervention, the use of a control group, and randomization or random assignment
Gold standard experiment
Randomized controlled trials; because they come closer than any other design in meeting the criteria for inferring causal relationships.
Posttest-only design
involve collecting data only once; after randomization and the introduction of the treatment.
Pretest-posttest design
data are collected both before the intervention (at baseline) and after it.
crossover designs
people are exposed to more than one experimental condition in random order and serve as their own controls.
Various conditions in the control group
- No treatment/intervention
- An alternative treatment is used
- A placebo is used
- Standard care “usual care” is used
- Different treatment doses are used
Quasi-experiments
involve an intervention
but lacks a comparison group or randomization.
The nonequivalent control group, pretest-posttest design
involves comparing the intervention group to a comparison group that was not created through randomization
within-subjects design
one group is studied before and after the intervention.
Nonexperimental (observational research)
includes descriptive research-studies that summarize the status of phenomena
Correlational studies
examine relationships among variables but involve no intervention.
Prospective cohort designs
researchers begin with a possible cause, and then subsequently collect data about the outcomes
Retrospective designs (case-control designs)
involve collecting data about an outcome in the present and then looking back in time for possible causes.
Cross-sectional designs
involve the collection of data at one time period
Longitudinal designs
involve data collection at two or more times over an extended period. In nursing, most longitudinal studies are follow-up studies of clinical populations.
Longitudinal studies are usually…
expensive, time consuming, subject to the risk of attrition (loss of participants over time) but yield valuable information about time related phenomena.
study VALIDITY
concerns the extent to which appropriate inferences can be made.
THREATS TO VALIDITY
are reasons that an inference could be wrong. A key function of quantitative research design is to rule out validity threats.
Statistical conclusion validity
concerns the strength of evidence that a relationship exists between two variables.
Internal validity
concerns inferences that the outcomes were caused by the independent variable, rather than extraneous factors.
External validity
concerns inferences about generalizability, whether findings hold true over variations in people, conditions, and settings.
