[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: xtabond2 and intercooled Stata 9.2
I am quite new to Stata and I am having trouble using the XTABOND2
program.. either my computer crashes or gives me an error message.
I used the following command...
xtabond2 chasim L.chasim L.chdiff L.asiminflr eta, gmm(L.chasim)
iv(L.chdiff L.asiminflr eta) nomata
... and I got the following error message.
Building GMM instruments.no room to add more variables due to width
With 50 time periods xtabond2 will attempt to create a gazillion
instruments, and no matter how many Gb of RAM you have, it will fail.
Either limit the lags used in the gmm instruments with the suboption
lag( ) or use the collapse option to reduce their number.
More fundamentally, you must consider whether this data set fits the
'small T, large N' criteria that rationalize the DPD (Arellano-Bond)
estimator. 50 is not that small, and this may not be the most sensible
estimation technique in the case where T is a significant fraction of
Kit Baum, Boston College Economics
An Introduction to Modern Econometrics Using Stata:
* For searches and help try: