I'm conducting a DiD analysis using OLS and I want to verify the robustness of my results by validating my use of OLS over other methods. A downfall of OLS is that my dependent variable (a dummy for unemployed or not) could sometimes lie outside the {0,1} range. Therefore it is argued logit may be a better method. Is there a test to show exactly how many (if any) of my dependent variable results lie outside of that range?
Related Posts with Test to back-up use of OLS over logit/probit
Repeated observations in panel data Dear all, I am trying to build a long database. I have data from 2004 to 2018 where, during four y…
log fileDear All, just a quick question. I am running some estimates and producing a log file. The latter i…
Is it possible to use itsa for interrupted time series with multiple panels all affected by a policy?Hi, I am running an interrupted time series analysis to assess the impact of a policy on medicine c…
Sorting panel data with numerous conditionsHi. I am currently working with longitudinal data I have converted to panel data and I now need some…
Hausman test has suggested Random effects model but I want to use Fixed effectsHello everyone, I am using EU dataset for 27 countries for 5 different years. My goal is to determi…
Subscribe to:
Post Comments (Atom)
0 Response to Test to back-up use of OLS over logit/probit
Post a Comment