Hi Ben,
Sure - investigate the mvpatterns command and drop where _mv >0
Peter
-----------------------------------------------------
Peter Adamson
Leukaemia Research Fund
Epidemiology and Genetics Unit
Margaret Smith Building .-.
University of Leeds / \
30 Hyde Terrace E . G . U
LEEDS LS2 9LN _ / \ _
+44 (0)113 3433578 direct line
+44 (0)113 2459806 fax
http://www.egu.leeds.ac.uk/
-----------------------------------------------------
> -----Original Message-----
> From: [email protected] [mailto:[email protected]]
> Sent: 10 September 2003 15:23
> To: [email protected]
> Subject: st: dropping missing variables
>
>
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> Is there a way in which I can drop variables that have only missing
> observations? This is something that happens quite often in general
> purpose surveys in which specific sub-groups are analyzed. It is quite
> annoying to keep all those unnecessary variables in memeory, and quite
> tiring to identify and eliminate them all.
>
> Any suggestions are welcome.
>
> groetjes,
> Ben Kriechel
>
> -----BEGIN PGP SIGNATURE-----
> Version: PGPfreeware 6.0.2i
>
> iQA/AwUBP18l6+db8S0dfCWJEQJFSQCg5hCWDD8KhMFh4lDfqkkEY6JgoqgAoL6b
> ObhIa9JqA5+HKJLL/Ln0U3Oc
> =A9Vu
> -----END PGP SIGNATURE-----
> *
> * 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/
