Hi Statalist
This is a question about implementing the Hausman-Taylor estimator -xthtaylor- within multiple imputation (i.e. following -mi estimate:- )
Specifically, I have completed the preceding steps in -mi- implementation
. mi set mlong
. mi register imputed ...
. mi register regular ...
. mi impute chained ...
However, when it comes to running
. mi estimate: xthtaylor [dep var] [exogenous vars] [endogenous vars], endog([endogenous vars])
The following error message appears:
mi estimate: command not supported
xthtaylor is not officially supported by mi estimate; see mi estimation for a list of Stata
estimation commands that are supported by mi estimate. You can use option cmdok to allow
estimation anyway.
My questions are:
1) Is -xthtaylor- not supported due to technical/computational reasons – in other words, is this something that a later version Stata may be able to support? Or are there theoretical reasons prohibiting the use of -xthtaylor- within -mi estimate-?
2) If the option -cmdok- is used to force an estimation, are there reasons to be sceptical of the results? (i.e. is this a recommended approach?)
Thank you very much for your help.
This is a question about implementing the Hausman-Taylor estimator -xthtaylor- within multiple imputation (i.e. following -mi estimate:- )
Specifically, I have completed the preceding steps in -mi- implementation
. mi set mlong
. mi register imputed ...
. mi register regular ...
. mi impute chained ...
However, when it comes to running
. mi estimate: xthtaylor [dep var] [exogenous vars] [endogenous vars], endog([endogenous vars])
The following error message appears:
mi estimate: command not supported
xthtaylor is not officially supported by mi estimate; see mi estimation for a list of Stata
estimation commands that are supported by mi estimate. You can use option cmdok to allow
estimation anyway.
My questions are:
1) Is -xthtaylor- not supported due to technical/computational reasons – in other words, is this something that a later version Stata may be able to support? Or are there theoretical reasons prohibiting the use of -xthtaylor- within -mi estimate-?
2) If the option -cmdok- is used to force an estimation, are there reasons to be sceptical of the results? (i.e. is this a recommended approach?)
Thank you very much for your help.
