st: RE: xtreg and xtivreg2

["Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>]

Susan,

xtreg does drop it - it just doesn't tell you.  You can confirm this by
cross-checking the coefficient estimates reported by xtreg,fe and
xtivreg2,fe when the same specification is used, i.e., no endogenous
regressors.  They should be identical.

--Mark (xtivreg2 author)

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Averett, Susan L
> Sent: 02 April 2011 22:27
> To: statalist@hsphsun2.harvard.edu
> Subject: st: amendment to my previous post
> 
> I do have one school where there is one individual. Why is 
> that person not dropped from xtreg but is dropped from xtivreg2?
>  

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Averett, Susan L
> Sent: 02 April 2011 22:25
> To: statalist@hsphsun2.harvard.edu
> Subject: st: xtreg and xtivreg2
> 
> Hi all: I am running two different models. I have a cross 
> section of data where respondents attend different schools. I 
> am using xtreg to do school fixed effects models.  My school 
> variable is psuid. I have multiple observations per school.
> 
> My code is:
> 
> xtset  psuid
> 
> xtreg unsafesex $rhsage parenting mom_teenmom $rhs 
> pc43_badsex if female==1, fe cluster(psuid)  
> 
> This works fine. I also have a potentially endogenous 
> variable so I am running: 
> xtivreg2 unsafesex $rhsage parenting mom_teenmom $rhs 
> (pc43_badsex=talkparents kidtrouble) if female==1, fe 
> cluster(psuid)  first
> 
> Both of these run but the second one gives me a message:
> Warning - singleton groups detected.  1 observation(s) not used.
> 
> whereas the xtreg model does not give me this message and 
> does not drop an observation. Furthermore, in my psuid 
> variable which is the schools, there are no schools with only 
> one student. 
> 
> I am at a loss to explain what could be going on.
> Thanks,
> 
> 
> Susan Averett
> *
> *   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/
> 


-- 
Heriot-Watt University is a Scottish charity
registered under charity number SC000278.


*
*   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/