An intuitive introduction to Regression Discontinuity

preview_player
Показать описание
When the circumstances are right, regression discontinuity can be an excellent way to extract causal estimates from observational data. In this video I give you a prototypical situation where RD is applicable and explain how it works. I also describe situations where the method fails and say a few words about fuzzy discontinuities.

Intended audience: Folks who have had some exposure to linear regression models, but want to learn more statistical methods.
Рекомендации по теме
Комментарии
Автор

Great explanation of RDD, thanks a lot.

SpaceDode
Автор

Hi. Thank you for this video. I have to apply RDD in a real life problem and I am not able to understand how to do it. Our intervention is a training program at district level which will help correct and more identification of a particular disease. This disease is defined by a value which is less than a particular no. Now my intervention will focus only on those individuals in the city who have value below that no and above that no will become our control. We will collect data on both baseline and endline for all invididuals in the district. I just know what my cut off point is. Rest is unclear.

pragjn
Автор

Excellent video! One question. What about splitting the data in to groups at the discontinuity and running e.g. anova or t test? Would that not allow for a similar interpretation?

seppschulz
Автор

Very helpful introduction! Thanks a lot :)

hhkchildhood
Автор

3:57 How does using the distance to cut off (x' = x - x0), as opposed to x, ensure that the two lines connect to each other if there's no effect?

enisten