Dear all,
Thanks to Prof. Baum, a new package is available in SSC.
VC_PACK is a set of commands that can be used for the estimation and assessment of varying coefficient models with a single running variable. This is a kind of semiparametric regression model.
You can read about the details here:https://journals.sagepub.com/doi/abs...36867X20953574
It estimates model of the following type:
y = x * b(z) +e
where Z is a single continuous variable. The coefficients b(z) are approximated using local linear regression.
You will find that this command is faster than -npregress kernel- for the estimation of optimal bandwidths when samples are of moderate size.
Please let me know if you find any problems with this.
Best regards
Fernando
Related Posts with new to SSC vc_pack: Estimation of smooth varying coefficient models
Does -xtmixed- use the full data set ?Dear all, In texts books, we are told that mixed effects models use the "full" data set. For exampl…
-estimates use-, error message when reading stored estimates across Stata versionsI have one model estimates file made using Stata v15.1. My co-worker is trying to do -estimates use-…
Dealing with multiple or statementsI am mapping ICD-9 codes to CCS and the coding can be quite inefficient. Some CCS include hundreds o…
test equality of coefficients from different models estimated by user written commandsDear All, I want to test equality of regression coefficients from to models. My first model is basi…
Maximum CSV size in Stata SE and what to do about 'fat' dataI have a dataset with 4600 observations of 3500 variables. The .xlsx file is 90 MB and the .csv vers…
Subscribe to:
Post Comments (Atom)
0 Response to new to SSC vc_pack: Estimation of smooth varying coefficient models
Post a Comment