[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: passthru option in xtabond2
Dear Statalist users,
After reading the help file of the xtabond2 command, I see that the passthru
option in the gmmstyle () section allows to create instruments that use not
the first-differences of the specified variable but the original levels, to
be used in the equation in levels. The reason is that "under the standard
assumptions" these instruments are not valid. Could anybody ellaborate on
this point? Why (or when) is the sole use of levels (disregarding first
differences) as instruments justified in the context of xtabond2?
Thanks for any information,
Express yourself instantly with MSN Messenger! Download today - it's FREE!
* For searches and help try: