st: RE: Random effects models with different observations per group (household)

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

Menale,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> menale kassie
> Sent: 13 September 2006 16:02
> To: SATAT
> Subject: st: Random effects models with different 
> observations per group (household)
> 
> Dear statalisters,
> 
> I have repeated cross-sectional plot (farm field) 
> observations per household. Some households have only one 
> plot (i.e. one plot per household) and some households have 
> more than one plot. Is it feasible to apply random effects 
> when some households have only one plot and others have more 
> than one plot?

I don't see why it isn't feasible.  The random effects estimator is a
matrix-weighted combination of the between and within estimators.  If a
household has only one plot, it's a singleton and hence contributes to
the between estimator but not the within estimator.  In practice, it's
obtained via feasible GLS: do OLS on quasi-demeaned data, where
quasi-demeaned means subtracting some fraction <1 of the group mean from
the observation.  In the case of a singleton, the "group mean" is just
the observation itself ... but I don't see what problems could arise
from this.

Cheers,
Mark

Prof. Mark Schaffer
Director, CERT
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3296
email: m.e.schaffer@hw.ac.uk
web: http://www.sml.hw.ac.uk/ecomes
 

> Any idea is appreciated. The model structure 
> can look like the following
> 
> Yhp =  xhp + uh + ehp
> where h and p is indexing household and plot respectively
> 
> Kind Regards,
> Menale
> 
> __________________________________________________
> Do You Yahoo!?
> Tired of spam?  Yahoo! Mail has the best spam protection 
> around http://mail.yahoo.com
> *
> *   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/
> 
> 

*
*   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/