Get startedGet started for free

Thinking about confounders in an RD design

Suppose your friend says "I don’t believe the results in Black (1999) because she doesn't control for whether there is a public park nearby the house. Having a park nearby increases the value of a house. Also, districts that have high test scores also tend to have more parks. So this test score effect might just be because of this unobserved confounder!"

Do you agree, disagree, or partly agree with your friend's statement?

This exercise is part of the course

Causal Inference with R - Instrumental Variables & RDD

View Course

Hands-on interactive exercise

Turn theory into action with one of our interactive exercises

Start Exercise