dear all,
we are estimating an Arellano and Bond (AB) model, in which the dependent
variable is a ratio that is zero for a substantial part of the sample (about
30%). Before implementing the AB we have tested for selection bias and we have
rejected such an hypothesis. On the basis of this evidence, may we present the
AB estimates obtained for the full sample or do you reckon is more appropriate
to eliminate the zeros before estimating?
thank you very much for your suggestions
Maria
-------------------------------------------------
This mail sent through IMP: http://horde.org/imp/
*
* 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/
