Stats 1045 Vocab 1 Flashcards
Treatment Group
Subjects in an experiment who are given the treatment under study.
Control Group
Subjects in an experiment who are given the treatment under study.
Response
The outcome measured on all subjects in a statistical experiment.
Blind Controls
An experiment where ONLY the SUBJECTS are UNaware if they received a placebo.
Double Blind Controls
When neither subjects nor those who evaluate the response know who got a placebo
Placebo
A neutral agent that resembles the treatment but lacks the active ingredient.
Randomized Controls
A random process (like a coin flip) assigns subjects to treatment or control.
Historical Controls
A new treatment is used on subjects and results compared with historical data.
Contemporaneous controls
Assignment to treatment and control are done at the same time and both measured.
Confounded Results
inaccurate conclusions when subjects in treatment and control groups differ.
Controlled Experiments
A statistical study comparing two groups (treatment and control) where the investigators assign each subject to a group.
Association
The only relationship that can be established with observational studies: when two or more conditions tend to occur together, but causality is undetermined.
Causation
A definitive relationship that can be established only with controlled experiments: where treatment can be shown to cause a specific response.
Confounder
A third variable, associated with both the treatment and the response, that creates a difference between the treatment and control groups.
Simpson’s Paradox
When relationships between percentages in subgroups are reversed when the subgroups are combined.
