<>
Use the name of the dependent var instead of "mean". You have used a special
syntax that is only applicable to -regress-
*************
webuse lbw, clear
logit low age lwt smoke ptl ht ui if race==2
est store a
logit low age lwt smoke ptl ht ui if race==3
est store b
suest a b
test [a_low]smoke=[b_low]smoke
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Schlesinger,
Traci
Gesendet: Montag, 19. Oktober 2009 18:15
An: [email protected]
Betreff: st: suest followed by hausman
dear stata users:
i am interested in finding out whether the affects of one variable (adj_red)
on an individual's likelihood of being sentenced to incarceration (incar)
varies depending on whether or not the individual is being sentenced in a
state that uses sentencing guidelines (guidelines). as such, i am using
suest followed by a a hausman test. however, currently my code works until
i get to the test line, when i get the error: "equation [a_mean] not found /
r(303);". interestingly, if i run this same code using reg instead of
logistic, the code works.
what am i doing wrong? the code is below.
thanks in advance for any feedback!
traci
#delimit ;
logistic incar adj_red black latino age agesq murder rape robbery assault
oviolent burglary theft MVT forgery fraud oproperty drugt odrug weapons
driving chg1att cjstatus priarr priorfta priconv pripris county year if
guidelines == 1;
est store a;
logistic incar adj_red black latino age agesq murder rape robbery assault
oviolent burglary theft MVT forgery fraud oproperty drugt odrug weapons
driving chg1att cjstatus priarr priorfta priconv pripris county year if
guidelines == 2;
est store b;
suest a b;
test [a_mean]adj_red=[b_mean]adj_red;
*
* 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/
