Identifying Key Variables in an RD Design
A pair of researchers named Jonah Berger and Devin Pope recently published a study about the results of professional basketball games that found that, surprisingly, sometimes losing can lead to winning. The researchers were looking at the determinants of winning in the National Basketball Association (NBA), and they had compiled a dataset of thousands of NBA games. When they looked at the halftime and final scores of each team, and after controlling for other important factors (like the winning percentage of each team), they found that teams who were slightly ahead at halftime were actually more likely to lose the game than the team that was behind at halftime. One theory to explain this outcome is that the team losing at halftime tries a little harder in the second half, while the team winning at halftime relaxes a little too much and loses the game.
So in this study, which variable is the outcome variable, which is the running variable, and which is the treatment variable?
This exercise is part of the course
Causal Inference with R - Instrumental Variables & RDD
Hands-on interactive exercise
Turn theory into action with one of our interactive exercises
