Quantcast
Channel: The Stata Blog - Latest Comments
Viewing all articles
Browse latest Browse all 1126

Re: Multiple equation models: Estimation and marginal effects using gsem

$
0
0

Thanks for a really interesting post. You use "vce(unconditional)" because, as you say, you are estimating a population rather than a sample effect. Is this motivated only by substantive interest, or would you consider the default delta method standard errors "vce(delta)" to be innapropriate in a situation such as this when you have estimated multiple models simultaneously?


Viewing all articles
Browse latest Browse all 1126

Trending Articles