<>
-ssc d parmest- by Roger Newson and -mean- (which does take -iweights-)
could be combined to achieve this, I think
*************
use http://www.stata-press.com/data/r11/psidextract.dta, clear
keep if id<50
//just a dopey xmpl weight
bys id: gen imweights=_n
mean lwage [iweight = imweights], over( id, nolabel)
capt ssc inst parmest
parmest, saving(myfile, replace)
u myfile, clear
keep parm estimate stderr min95 max95
l, noo sep(0)
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Johan Hellstrom
Gesendet: Freitag, 24. Juli 2009 16:42
An: [email protected]
Betreff: st: Mean with confidence intervals for a collapsed data set
Dear Statalisters,
For graphing purposes I want to aggregate a panel data set, from unit to
group level, to get a mean value for each group, each year. Nonetheless, I
would also like to have 95 %-confidence intervals (CI) around the calculated
mean. What is making things a bit complicated is that I need to use
(importance) weights when aggregating the data set.
One way of doing this is by using the 'statsby'-program together with the
'ci'-program, but this does not allows importance weights.
statsby mean=r(mean) upper=r(ub) lower=r(lb), saving("C:\....", replace)
by(group year): ci var
Can anyone suggest a solution to get mean values with confidence intervals
using importance weights in this particular case?
Best,
Johan Hellström
*
* 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/
