<>
It is possible in case the -drop- does not matter b/c -x1- is not part of
the estimation anyway:
*************
clear*
set obs 1000
gen x1=rnormal()
gen x2=rnormal()
gen y=1+2*x1+3*x2+rnormal()
replace x1=500 in 200/205
replace x1=. in 206/210
replace x2=. in 212/214
reg y x?
preserve
drop if x1>100 & x1!=.
reg y x2
restore
preserve
drop if x1>100
reg y x2
restore
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Francesco
Trivieri
Gesendet: Montag, 12. Oktober 2009 11:49
An: [email protected]
Betreff: st: drop command & missing values
dear users,
when I drop some observations by writing:
1) drop if x>123
Stata drops also the missing values of the x variable. When I use the
following
2) drop if x>123 & x!=.
Stata does not drop the missing values
As missing values are discarded in any estimations, Stata should consider
the same obsevations whather command I use (1 or 2). By constrast, the
number of obsevations is much smaller when I run a regression after using
the command 1)
thank you
Francesco
*
* 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/
*
* 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/