Assumptions in Causal Inference

Lucy D’Agostino McGowan

  1. Consistency
  2. Exchangeability
  3. Positivity

Consistency

  • We assume that the causal question you claim you are answering is consistent with the one you are actually answering with your analysis.
  • Mathematically: \(Y_{obs} = (X)Y(1) + (1-X)Y(0)\)
  • Well defined exposure
  • No interference

Well defined exposure

  • We assume that for each value of the exposure, there is no difference between subjects in the delivery of that exposure
  • Put another way, multiple versions of the treatment do not exist

Application exercise

  1. Think of an example where this might be violated
  2. Turn to the person next to you and tell them your example
  3. Pick your favorite between the two of you, we’ll share them with the class
03:00

No interference

  • We assume that the outcome (technically all potential outcomes, regardless of whether they are observed) for any subject does not depend on another subject’s exposure

Application exercise

  1. Think of an example where this might be violated
  2. Turn to the person next to you and tell them your example
  3. Pick your favorite between the two of you, we’ll share them with the class
03:00

Exchangeability

  • We assume that within levels of relevant variables (confounders), exposed and unexposed subjects have an equal likelihood of experiencing any outcome prior to exposure
  • i.e. the exposed and unexposed subjects are exchangeable
  • This assumption is sometimes referred to as no unmeasured confounding.

Application exercise

  1. Think of an example where this might be violated
  2. Turn to the person next to you and tell them your example
  3. Pick your favorite between the two of you, we’ll share them with the class
03:00

Positivity

  • We assume that within each level and combination of the study variables used to achieve exchangeability, there are exposed and unexposed subjects.
  • Said differently, each individual has some chance of experiencing every available exposure level.
  • Sometimes this is referred to as the probabilistic assumption.

Application exercise

  1. Think of an example where this might be violated
  2. Turn to the person next to you and tell them your example
  3. Pick your favorite between the two of you, we’ll share them with the class
03:00