EXPERIMENTAL RESEARCH
"gold standard"
Internal validity- strength of experimental research
External validity- generalizability
Laboratory experiments - conducted in a laboratory (artificial settings)
Field experiments- conducted in a field setting
Basic Concepts
Hybrid Experiment Designs
click to edit
treatment groups- administered one or more experimental stimulus
control groups - no stimulus given
Treatment manipulation- treatments that sets the design apart
pretest measures- treatment conducted before the treatment
posttest measures- conducted after treatment
Random selection & assignment - the process of randomly drawing a sample from a population or sampling frame
Factorial designs- four or higher-group designs
Threats to internal validity- internal inference
Testing threat- conditioned by pretest responses
Instrumentation threat- possibility that the difference between pretest & posttest scores
Maturation threat- caused by natural maturation
Mortality threat- subjects may drop out of study at different rates
History threat- dependent variables
Regression threat-statistical tendency of a group's overall performance on a measure
main effect
interaction effect
Randomized block design - homogeneous subgroups
Solomon four-group design- sample divided into two treatment groups and two control groups
Quasi-Experimental Designs
Switched replication design- two phases with three waves of measurement
single group with two outcomes, one influenced by treatment and the other not.
non-equivalent switched replication - omit random assignment
Separate pretest-posttest samples design- useful way of collecting pretest & posttest are not available for the same subjects
regression-discontinuity design- assigned to treatment or control group based on cutoff score
proxy pretest design- the pretest score collected after the treatment is administered.