Dear Nick:
Thanks again for your insights. In general, it works
but with little correction to your suggestion
commands.
You suggested the following:
bysort hhold (id) : gen S_age = Age[S_id]
bysort hhold S_id : egen meanS_age = mean(S_age)
by hhold S_id : egen nS = count(S_id) if S_id < .
*for husbands
bysort hhold (nS) : gen Sn_age = meanS_age[2] if _n==1
*for wives
by hhold : replace Sn_age = meanS_age[1] if S_age==. &
S_id < .
The above doesn't work for the following given the way
S_age is defined:
hhold id S_id Age S_age
23 2 1 30 35
23 1 2 35 30
23 4 . 65 .
23 3 . 3 .
45 2 1 50 40
45 1 2 40 50
45 6 2 30 50
45 8 . 5 .
45 5 . 5 .
45 4 . 8 .
45 7 . 2 .
45 3 . 12 .
Hence, instead of S_age, if we use the actual age i.e.
"Age" (and also adjusting the "if" constraint in the
last command line), the following works:
bysort hhold S_id: egen meanS_age = mean(Age) if
S_id~=.
by hhold S_id : egen nS = count(S_id) if S_id < .
*for husbands:
bysort hhold (nS): gen Sn_age = meanS_age[2] if _n==1
*for wives:
by hhold: replace Sn_age = meanS_age[1] if Sn_age==. &
S_id<.
Hence we get,
hhold id S_id meanS_age nS Sn_age
23 2 1 30 1 35
23 1 2 35 1 30
23 4 . . . .
23 3 . . . .
45 2 1 50 1 35
45 1 2 35 2 50
45 6 2 35 2 50
45 8 . . . .
45 5 . . . .
45 4 . . . .
45 7 . . . .
45 3 . . . .
But as you rightly note, this works only where we have
at most one married man. Since multi-family household
(with & without polygamy) is very common in my data (&
in developing countries), i am currently trying to get
around this problem.
Thanks again. -Asad.
The last bit of my previous posting needs revision:
> bysort hhold (nS) : gen S_age = meanS_age[3 - _n]
Should be
bysort hhold (nS) : gen S_age = meanS_age[2] if _n ==
1
That's the husbands.
by hhold : replace S_age = meanS_age[1] if S_age == .
& S_id < .
That's the wives.
Nick
n.j.cox@d...
__________________________________________________
Do You Yahoo!?
Sign up for SBC Yahoo! Dial - First Month Free
http://sbc.yahoo.com
*
* 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/
