Dear all,
I try to perform a Panel data analysis for countries and years.
I am curious if there a command routine in stata exists that I could use to test for the right model.
The routine should include all the relevant steps of tests (like in an decision tree) to the end.
For example:
Starting with a regression model:
tsset company time, yearly
reg depvar indepvar
reg depvar indepvar, robust
xtpcse depvar indepvar
Testing for Heteroscedasticity:
whitetst
bpagan depvar indepvar
xtgls depvar indepvar, panels (heteroscedastic)
matrix list e (Sigma)
...
Testing for Autocorrelation:
...
Regards,
Christian
-----------------------------------------------------------------------
Christian Rosenberger
DROEGE & COMP.
405 Lexington Ave.
35th Floor, Chrysler Building
New York, NY 10174
phone +1 - 212-557 7616 | fax + 1 - 212-557 6788
-----------------------------------------------------------------------
This message is confidential and may be privileged. It is intended
only for the use of the addressee named above. If you are not the
intended recipient, any unauthorised dissemination, distribution
or copying is illegal. We do not guarantee the security or completeness
of information hereby transmitted and are not liable in either respect
or in respect of any delay. Nothing in this message is intended as an
offer or solicitation for the purchase or sale of any matter. Any
prices or data, unless specifically verified and identified as such,
are not warranted as to completeness or accuracy.
