Any experiment designed to identify the active elements of a treatment condition, the relative contributions of different variables in a treatment package, and/or the necessary and sufficient portions of an intervention. These take many forms, but the basic strategy is to compare levels of responding across successive phases in which the intervention is implemented with one or more components left out.
An experiment in which the researcher attempts to duplicate exactly the conditions of an earlier experiment.
A procedure that prevents the subject and the observer(s) from detecting the presence or absence of the treatment variable; used to eliminate confounding of results by subject expectations, parent and teacher expectations, differential treatment by others, and observer bias.
A procedure that prevents a subject from detecting the presence or absence of the treatment variable. To the subject the placebo condition appears the same as the treatment condition: e.g., a placebo pill contains an inert substance but looks, feels, and tastes exactly like a pill that contains the treatment drug (Source: CHH, 2 Ed).
AKA treatment integrity.
(a) Repeating conditions within an experiment to determine the reliability of effects and increase internal validity; (b) repeating whole experiments to determine the generality of findings of previous experiments to other subjects, settings, and/or behaviors.
An experiment in which the researcher purposefully varies one or more aspects of an earlier experiment. A systematic replication that reproduces the results of previous research not only demonstrates the reliability of the earlier findings but also adds to the external validity of the earlier findings by showing that the same effect can be obtained under different conditions.
An undesirable situation in which the independent variable of an experiment is applied differently during later stages than it was at the outset of the study.
The extent to which the independent variable is applied exactly as planned and described and no other unplanned variables are administered inadvertently along with the planned treatment. Also called "Procedural fidelity."
Type I error
An error that occurs when a researcher concludes that the independent variable had an effect on the dependent variable, when no such relation exists; a "false positive"
Type II error
An error that occurs when a researcher concludes that the independent variable had no effect on the dependent variable, when in truth it did; a "false negative."