i have questions for the fuzzy RDD. 1. why do we have to generate variables above and below? 2. what is the importance of the 2 variables? do the p value have to significant or how? 3/ so on the first stage of the 2sls, the treatment status is dependent on centered running variable and the treatment assignment. but why is the IV only (scholar=eligible)? don't we have to input the centred running variable? the c_pretest? hope you don't mind answering my questions. thank you
just for sharing, in time 31.32 for anyone may get the result in optimum selected bandwidth different from the value 9.654 as in this video due to "mass points detected in the running variable" just try to add masspoints (off) because the default masspoints option is masspoints (adjust), so then you will get same result, hope it is usefull🙏