Drop random effects parameters from output table in Stata

Question

I want to create a regression table (using esttab) from a mixed-effects regression estimated via xtmixed in Stata, but I want the output without the random effects parameters. How can I drop the random effects parameters from the output table? E.g., in the case of two variables...

xtmixed (Dependent Variable) (Independent variable) || (Grouping Variable))

... I don't want the lns1_1_1 and the lnsig_e values in my esttab-table. What is the best way to do this?

Answer 1

There is a keep() and a drop() option. For example:

webuse productivity, clear

xtmixed gsp private emp hwy water other unemp || region: || state:, mle
estimates store m1

// check result names
matrix list e(b)

// with -keep()- option
estout m1, keep(private emp hwy water other unemp gsp:_cons)

// with -drop()- option
estout m1, drop(lns1_1_1:_cons lns2_1_1:_cons lnsig_e:_cons)

In the context of multiple equation estimation, resulting matrices have elements with two-part names. The general form is equation-name:varname. The result of matrix list shows this. Afterwards, just use the appropriate names in the keep() and drop() options.

See [U] 14.2 Row and column names for more details on the naming conventions.

(Recall esttab is a wrapper for estout.)