Causal Inference Flashcards
(14 cards)
Descriptive Inference
Describes the correlation between two features in a population
Predictive Inference
provides information about the value of a feature for a unit we do not observe
Causal Inference
describes the causal effect of a treatment on an outcome
Estimad
The quantity of interest and also determines the type of inference
Causal effect
when a change to a feature of the world (D) results in a change in some other feature of the world (Y). It can have a positive, negative, or null effect
Counterfactual
the “what if” or alternative outcome in an experiment
Individual Causal effect
the causal effect of the treatment on the outcome is the difference between its two potential outcomes. Ti = y1i - y0i
y1i
the outcome when the units are in the treatment group
y0i
the outcome when the units are in the control group
The fundamental problem of causal inference
Impossible to observe individual treatment effects at the same time because we can only observe one state of the world at a time (either the treatment or control)
ATE
average treatment effect
ATT
average treatment effect on the treated
ATC
average treatment effect on the control
SUTVA
Stable unit treatment value assumption
