Statistical Sciences 2035 Quiz: Threats to external validity
7 Oct 2018
School
Department
Professor
Document Summary
Likely to limit the degree to which generalizations can be made from the particular experimental conditions to other populations or settings. Failure to describe and operationalize independent and dependent variables explicitly. Reactive bias which is a problem where participants display different behaviors simply because they are participating and no longer represent the population from which they were drawn, thus limiting any generalization. Threats to internal validity come from issues with sample size, the measures used and experimental design employed and might result in the commitment of type i or type ii error: Small sample sizes limit the power of statistical test, which indicates low statistical power. Especially when undertaking exploratory research in new areas of investigation, researchers often (cid:494)fish(cid:495) around with all possible associations between variables in order to identify statistically significant findings. Fishing expeditions increase the likelihood of type i error.
