What are randomised controlled trials good for?

摘要: Randomized controlled trials (RCTs) are widely taken as the gold standard for establishing causal conclusions. Ideally conducted they ensure that treatment ‘causes’ outcome—in experiment. But where else? This is venerable question of external validity. I point out comes in two importantly different forms: Is specific conclusion warranted by experiment true a target situation? What will be result implementing there? paper explains how probabilistic theory causality implies RCTs can establish conclusions and thereby provides an account what exactly is. Clarifying exact form shows just necessary it to hold new setting also much more needed see actual outcome would there were implemented.