Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: drawing graph for quantile regression after using multiple imputation (ICE command)
From
Elisabetta Petracci <[email protected]>
To
[email protected]
Subject
st: drawing graph for quantile regression after using multiple imputation (ICE command)
Date
Mon, 17 Jan 2011 05:25:20 -0500
Dear all,
*I have used the ICE command to impute missing values on different
varaibles, using 15 replications. With "mi combine" I ran a quantile
regression and I got the parameter *estimates and their standard
error.
*Now, I would plot the coefficients but I don't how to do this after
the missing imputation. The usual command "grqreg" does not work.
*The following is the sintax I used, not necessarily useful to answe
this question I guess:
ice quantobuonasalute cometivedi4_new o.istruz_madre o.af m.diffi
o.imm sex01 cls_bmi_new, dryrun
ice quantobuonasalute cometivedi4_new o.istruz_madre o.af m.diffi
o.imm sex01 cls_bmi_new, saving(prova_ice_medie) m(15)
use prova_ice_medie, clear
tab cls_bmi_new
gen bmi1=1 if cls_bmi_new==1
replace bmi1=0 if cls_bmi_new==0 | cls_bmi_new==2
gen bmi2=1 if cls_bmi_new==2
replace bmi2=0 if cls_bmi_new==0 | cls_bmi_new==1
micombine qreg quantobuonasalute cometivedi4_new _Iistruz_ma_2
_Iistruz_ma_3 _Iistruz_ma_4 _Iaf_1 _Iaf_2 _Idiffi_1 _Idiffi_2 _Iimm_1
_Iimm_2 sex01 bmi1 bmi2,quantile(90)
*Thank you very much,
Elisabetta
*
* 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/