Designed Experiment with Post-Treatment Measurement
(Redirected from A/B Experiment)
Jump to navigation
Jump to search
A Designed Experiment with Post-Treatment Measurement is a designed study where interventions are assigned to experiment subjects, and where posttest measures are taken.
- AKA: Interventional Study, Scientific Control.
- Context:
- Input: an Experiment Subject Population.
- output: an Experiment Outcome Dataset (for an experiment evaluation).
- It can be designed by an Experiment Design Task.
- It can range from being a Field Experiment to being a Laboratory Experiment.
- It can range from being an Experiment With Comparator to being an Experiment Without Comparator.
- It can range from being a Posttest-only Experiment to being a Pretest-Posttest Experiment.
- It can range from being a Single-Measure Experiment to being a Repeated-Measures Experiment.
- It can range from being a Randomized Experiment to being a Non-Randomized Experiment.
- It can range from being an Experiment with Baseline Measures to being an Experiment without Baseline Measures.
- …
- Example(s):
- Counter-Example(s):
- an Observational Study, such as a case study, a survey-based study, a retrospective cohort study, or a natural experiment.
- See: Multi-Armed Bandit Testing, Online System Experimentation, Experiment Question, Multivariate Testing.
References
2014
- http://en.wikipedia.org/wiki/Clinical_trial#Types
- One way of classifying clinical trials is by the way the researchers behave. …
… In an interventional study, the investigators give the research subjects a particular medicine or other intervention. Usually, they compare the treated subjects to subjects who receive no treatment or standard treatment. Then the researchers measure how the subjects' health changes.
- One way of classifying clinical trials is by the way the researchers behave. …
2005
- (Everitt & Howell, 2005) ⇒ Brian S. Everitt, and David Howell (editors). (2005). “Encyclopedia of Statistics in Behavioral Science." Wiley. ISBN:9780470860809
- QUOTE: In a controlled observational cohort study, two groups of subjects are selected from two populations that (hopefully) differ in only one characteristic at the start. The groups of subjects are studied for a specific period and contrasted at the end of the study period. For instance, smokers and nonsmokers are studied for a period of 10 years, and at the end the proportions of smokers and nonsmokers that died in that period are compared. On the other hand, in an intervention study, the subjects are selected from one population with a particular characteristic present; then, immediately after baseline, the total study group is split up into a group that receives the intervention and a group that does not receive that intervention (control group). The comparison of the outcomes of the two groups at the end of the study period is an evaluation of the intervention. For instance, smokers can be divided into those who will be subject to a smoking-cessation program and those who will not be motivated to stop smoking. … The first step in any intervention study is to specify the target population, which is the population to which the findings should be extrapolated. This requires a specific definition of the subjects in the study prior to selection. In a clinical trial, this is achieved by specifying inclusion and exclusion criteria. [1]
- QUOTE: In a controlled observational cohort study, two groups of subjects are selected from two populations that (hopefully) differ in only one characteristic at the start. The groups of subjects are studied for a specific period and contrasted at the end of the study period. For instance, smokers and nonsmokers are studied for a period of 10 years, and at the end the proportions of smokers and nonsmokers that died in that period are compared. On the other hand, in an intervention study, the subjects are selected from one population with a particular characteristic present; then, immediately after baseline, the total study group is split up into a group that receives the intervention and a group that does not receive that intervention (control group). The comparison of the outcomes of the two groups at the end of the study period is an evaluation of the intervention. For instance, smokers can be divided into those who will be subject to a smoking-cessation program and those who will not be motivated to stop smoking. … The first step in any intervention study is to specify the target population, which is the population to which the findings should be extrapolated. This requires a specific definition of the subjects in the study prior to selection. In a clinical trial, this is achieved by specifying inclusion and exclusion criteria. [1]
1992
- (Keppel et al., 1992) ⇒ Geoffrey Keppel, William H. Saufley, and Howard Tokunaga. (1992). “Introduction to Design and Analysis, 2nd edn." W.H. Freeman and Company. ISBN:0716723212