For testing the validity of parallel trend assumption I need to know how many observations I have ( state-year level) in each lag of my event study. The idea is that parallel trend tests can be underpowered, and I need to make sure that I have enough observations in the pre-time to be able to correctly reject the null hypothesis.
I've so far figured out how I can address the issue. The problem is - still quite didnt wrap my head around how I can code it :
1. I need to Create a relative year measure first
2. Then , I need to Use bysort or a loop and "tab statefip" for relative year values (if statement)
Any suggestion how I should code it up for these two steps ?
Related Posts with Testing underpowerment of pre intervention dummy
Correlation of one variable across countries in Panel DataHi all, I am working with a Panel-Data set that includes a number of variables (e.g. Credit, GDP) a…
Creating a Panal Data Sheet in excel for STATAGood day, I am working on my thesis, and I have separate variables from OECD on excel sheets. Indiv…
Correction for Probit with FE (Cross-section) - Incidental parametersDear all, I am running a probit model (since my dependent variable is binary) using Fixed Effects (…
SIC codes matchingHi, I want to match the SIC codes of the target and acquirer using SDC data (SIC codes). I already d…
New package on SSC: peerreviewThanks to Kit Baum, a new package -peerreview- is now available on SSC. -peerreview- randomly assig…
Subscribe to:
Post Comments (Atom)
0 Response to Testing underpowerment of pre intervention dummy
Post a Comment