Regression Discontinuity Design, Probit/logit models
4 important questions on Regression Discontinuity Design, Probit/logit models
Name the 3 requirements for RDD mentioned in the slides
2. You need a way to split the group (treatment assignment rule)
3. No manipulation (bunching)
Provide a simple definition of fuzzy regression discontinuity
Provide the definition (more formal) of Sharp and Fuzzy RD
Fuzzy when the threshold shift is not from 0 to 1 (but somewhere in between)
- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding
Provide the 3 scenarios that could lead to a Fuzzy RD
- The rules on who gets treatment and who doesn’t is not always followed strictly
- Treatment is optional (“threshold might only induce ‘encouragement’ to take treatment”
- Those that should get treatment have the choice to reject treatment (how is this different from point 2?)
The question on the page originate from the summary of the following study material:
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding