I am in the process of running two different xtabond2 models, and have a question regarding the specification of “small T large N”. Our first model has 1880 employees over 9 years (T=9, N =1880, or around 4800 observations, total). Our second model has 1880 employees over 342 time periods (so T=342, N=1880, or around 100,000 observations, total).
I am wondering if there is a rule of thumb regarding what is meant by “small T large N”. If xtabond2 is not appropriate for the second model, can you recommend an alternate specification?
These employees belong to 32 firms and we intend to include firm fixed effects, in addition to time fixed effects in both models. Is the inclusion of firm fixed effects acceptable in the xtabond2 model?
Thanks for your help.
Related Posts with xtabond2 question on large N small T
Gini decomposition by subgroups - ineqdec0Hi everyone, I am estimating the monetary value of in-kind benefits (like education) to be added to …
Event study - sorting groups and assigning estimation windowsHello Statalist! Since my last post didn't get any answers, im trying with the help of the FAQ to c…
Difference in Differences with propensity score matching for repeated cross sectional surveysDear Statalisters! I'm pretty new to Statalist and found a lot of posts regarding DID and PSM, but n…
Mixed command and random effectsHi. I have data on 600 participants at 5 time points with 2 measurements at each time point for aver…
Saving error messageHi all, I am using a plug-in called traj from https://www.andrew.cmu.edu/user/bjones/strtxmpl2.htm.…
Subscribe to:
Post Comments (Atom)
0 Response to xtabond2 question on large N small T
Post a Comment