Chapter 8 - Experimental and Quasi - Experimental Designs `

Booster Sessions

Elements of experiments that are reintroduced some point later in the course of experimental research to research to reinforce treatment effects that may have atrophied over time

Brief Interventions

Experimental trials that are often as short as a few minutes in duration

Causal Inference

The attribution of one variable as the cause of another

Confounding variables

Related to both the exposure and the outcome of interest. May be established as the “cause” of the outcome; however, it is only associated with the outcome because of it’s relationship with the other exposure measured. These make it difficult to determine the cause-and-effect relationships between variables 

Contamination

Occurs when the control group is inadvertently exposed to some of the treatment. This might occur due to error, members of the experimental group sharing information or aspects of the treatment with the control group, or by some other manner

Control group

The group used as a standard for comparison in a control experiment, which receives no treatment, lesser treatment, or treatment for an unrelated problem

Double-blind experiment

An experiment conducted on human subjects, in which neither the individuals participating in the experiments nor the researchers conducting the experiment know who belongs to the control group or who belongs to the treatment group. This reduces bias in experiments

Experiment

A type of research design conducted under controlled conditions for the purpose of demonstrating a known truth, examining the validity of a hypothesis, or determining the efficacy of something previously untried 

Experimental group

A group of subjects that are exposed to the treatment condition of the experiment

Exposure

The condition of being subject to some effect or influence

Intent-to-treat

An analysis that includes all students receiving a treatment or participants in an experiment in both the pretest and posttest regardless of how much of an intervention they may have been exposed to. This is a conservative method for evaluating the outcome of an experiment

Internal validity

The degree to which the results of a study are actually true. A strong research design and a valid and reliable questionnaire increase the likelihood that the findings of the study are correct 

Lagged effects

Effects of a treatment intervention or experimental condition that come about well after the fact, often after measurement and the official experiment has ceased 

Nonequivalent groups design

The most frequently used design in social research. This design is similar to a pretest, posttest randomized experiment, but lacks the feature of randomization 

Posttest

A survey or other data-collection method administered to research participants after completion of a treatment to determine change in behavior and effect of the treatment. This is used in conjunction with a pretest

Pretest

A preliminary test administered to determine baseline behaviors and characteristics prior to treatment

Quality Assurance

The researcher’s ability to be certain that the program is being administered as expected

Quasi-experiment

An empirical study similar to an experiment in all manners with the exception of lacking the element of random assignment of participants

Single-blind experiment 

An experiment where information that could reduce bias or otherwise skew the result is withheld from the participants but is completely known to the experimenter 

Time-series design

A quasi-experimental research design in which periodic measurements are made on groups or individuals both before and after the implementation of an intervention or policy 

Treatment as usual

The treatment received by the control group within an experiment. May be no treatment at all, another unrelated program, or a bare-bones version of the experimental condition treatment program

Unit of analysis

The entity that you are studying in research. Can be individuals, groups, artifacts, geographical areas, or social interactions