Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Re: negative haumsan test statistics


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Re: negative haumsan test statistics
Date   Fri, 1 May 2009 14:00:43 +0100

As earlier advised, please specify the source of any user-written
commands you refer to. 

Nick 
n.j.cox@durham.ac.uk 

Yee Kyoung Kim

it's xtabond2


On Fri, May 1, 2009 at 8:53 PM, Martin Weiss <martin.weiss1@gmx.de>
wrote:
>
> Which command generates the System GMM results?

Yee Kyoung Kim

>> Thank you for the reply.
>> I have not reversed the order.
>> System GMM is suppposed to be consistent.
>> Therefore, I did as below...
>>
>> Hausman gmm fe
>>
>> Does it mean that the gmm estimates are no longer consistent?
>>
>> I tried -suest- but GMM does not generate "score" that is required
for
>> "predict". So, this doesn't help ...

>> On Fri, May 1, 2009 at 7:48 PM, Martin Weiss <martin.weiss1@gmx.de> 

>>> Are you sure you have respected the advice in the help file -h
hausman-:
>>> "specify to hausman the models in the order "always consistent"
first and
>>> "efficient under H0" second."?
>>>
>>> A reversal of the models reverses the sign of the test statistic...
>>>
>>> ****
>>> qui{
>>> webuse nlswork4, clear
>>> xtreg ln_wage age msp ttl_exp, fe
>>> estimates store fixed
>>> xtreg ln_wage age msp ttl_exp, re
>>> est store re
>>> }
>>>
>>> hausman fixed .
>>> //reversed
>>> hausman re fixed
>>> ****
>>>
>>> Apart from that, Stata offers you -suest- as a general
alternative...

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index