Tewodaj Mogues <[email protected]> has two questions about -xtdpdsys-.
a) -xtdpdsys- doesn't seem to allow for the specification of instruments
that are external to the model, in the way that for example -xtabond-
allows through the subcommand -inst()-, or -xtdpd- by including the
instruments in the subcommand -div()- but not in the variable list of
regressors. Is it correct that external instruments are not an option in
-xtdpdsys-?
This statement is correct. -xtdpd- allows you to specify the external
instruments.
b) The subcommand for predetermined and endogenous variables in
-xtdpdsys-, i.e. -pre()- and -end()-, do not accommodate time-series
operators, although one may in many cases want to include as a regressor
just the first lag of a variable (and not both the contemporaneous
variable plus its first lag).
...
Is there no straightforward way to deal
with this other than creating new variables or using xtdpd? By the way,
this problem appears to also obtain in -xtdpdsys- as well as -xtabond-.
The -pre()- and -endog()- options in -xtabond- and -xtdpdsys- create
instruments based on a variable being specified as predetermined or
endogenous. If time-series operators were allowed, confusion might arise as
whether the original variable or the time-series operated variable was, say,
predetermined. For this reason, time-series operators are not allowed in
these varlists.
-xtdpd- accepts time-series operators in all its varlists and you can specify
the instruments you want.
-xtabond- and -xtdpdsys- were designed to handle relatively simple dynamic
panel-data models and to have correspondingly simple syntaxes. If your
model is more complex, I recommend using -xtdpd-.
--David
<[email protected]>
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
