Showing posts with label rct. Show all posts
Showing posts with label rct. Show all posts

Friday, February 18, 2022

RCT bingo!

A vocabulary of causal inference testing

I was having a clear-out and I came across a printout of some notes I made a while back. It was a list of terms used in causal inference testing. At the time, I used it as a checklist or dictionary to ensure I knew what I was talking about - a kind of RCT bingo if you like.

(Myriam Thomas, CC BY-SA 4.0, via Wikimedia Commons)

I thought I would post it here in case anyone wants to play the same game. Do you know what all these terms mean? Are there key terms I've missed off my list?

  • ATE - Average Treatment Effect
  • CATE - Conditional Average Treatment Effect
  • Counterfactual
  • DAG - Directed Acyclic Graph
  • Dynamic Treatment Effect
  • Epsilon greedy
  • Estimands
  • External and internal validity
  • Heterogeneity (treatment effect heterogeneity) 
  • Homophily
  • Instrumental Variable (IV)
  • LATE - Local Average Treatment Effect
  • Logit model
  • RCT - Randomized Control Trial
  • Regret
  • Salience
  • Spillover
  • Stationary effect (and it's opposite non-stationary effect)
  • Surrogate
  • SUTVA - Stable Unit Treatment Value Assumption
  • Thompson sampling
  • Treatment effect heterogeneity
  • Wald estimator