Lecture 17 Causal Diagram Practice

Nick Huntington-Klein

March 3, 2019

Recap

  • To make a diagram:
  • List all the relevant variables
  • Combine identical variables, eliminate unimportant ones
  • Draw arrows to indicate what you think causes what
  • (See if the model implies that any relationships SHOULDN’T exist and test that)
  • Think carefully!

Recap

  • If we’re interested in the effect of X on Y:
  • Write the list of all paths from X to Y
  • Figure out which are front-door paths (going from X to Y)
  • and which are back-door paths (other ways)
  • Then figure out what set of variables need to be controlled/adjusted for to close those back doors

Testing Relationships

  • Just a little more detail on this “testing relationships” thing
  • Our use of front-door and back-door paths means that we can look at any two variables in our diagram and say “hmm, if I control for A, B, and C, then that closes all front and back door paths between D and E”
  • So, if we control for A, B, and C, then D and E should be unrelated!
  • If cor(D,E) controlling for A, B, C is big, our diagram is probably wrong!

Testing Relationships

  • What are some relationships we can test?