You replicate this with the grunfeld dataset and the mvalue variable.
sysuse grunfeld,clear
egen double t1 = total(mva), by(com)
egen double t2 = total(kstock), by(com)
//t1 not dropped
areg invest kstock t1, ab(com)
//t2 dropped
areg invest mvalu t2, ab(com)
replace t1 = t1/100
//Now, t1 is dropped
areg invest kstock t1, ab(com)
replace t2 = t2*10000
//Now, t2 is not dropped
areg invest mvalu t2, ab(com)
Scott
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Schaffer, Mark E
> Sent: Monday, February 27, 2006 4:53 PM
> To: [email protected]
> Subject: RE: st: behavior of -areg-
>
> Maybe try egening your total_hh_nr variable as a double? If areg uses
> doubles and you generate a float, it might not be perfectly collinear.
>
> --Mark
>
*
* 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/
