Two-way clustered standard errors after xtpoisson

[Carrie Zhai]

Hello, statalists.
I am using xtpoisson with clustered standard errors. So far I can only use the option "vce(cluster id)" to cluster on one dimension. I wonder, can I do a two-way clustering on both id and time?
Thank you very much for your attention.

[Phil Bromiley]

You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

I don't know of a poisson panel estimator that is built for two dimensional clustered errors. See if cmp does it. You can probably code it in gsem although it won't be simple.