Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: calculating number of bimesters


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: calculating number of bimesters
Date   Tue, 16 Dec 2008 17:34:03 -0000

I guess that bimester 1 = Jan-Feb, 2 = Mar-Apr, ..., 6 = Nov-Dec. 

Then 

gen year0 = cond(phase < 3, 2002, 2004) 
gen bimester0 = cond(phase < 3, phase + 3, cond(phase == 3, 2, phase)) 
gen mytime = 6 * (year - year0) + (bimester - bimester0) + 1 

Nick 
n.j.cox@durham.ac.uk 

By the way, Rodrigo: You started a thread on 4 December 

<http://www.hsph.harvard.edu/cgi-bin/lwgate/STATALIST/archives/statalist.0812/date/article-221.html> 

-- and David Elliott and I posted various replies, raising subsidiary questions, but I never saw any reply from you. 

Rodrigo Briceño

I need to calculate the amount of bimesters a
household stay in a program. For that purpose I have three different
variables:
1. Phase of incorporation (phase): it has 6 numeric values where
1=july-august 2002, 2=sep-oct 2002, 3=mar-apr 2004, 4=jul-aug 2004,
5=sep-oct 2004, and 6=nov-dic 2004
2. Two variables that contain the information about the time the
household dropped the program:
2. 1 Year: from 2002 to 2008
2. 2 bimester: from 1 to 6

In what way can I calculate the amount of bimesters (or months) that a
household stayed in the program? Example above (time is the variable
which values I need):

HH  phase  year    bimester  time
1      3         2007       2         19 (or 38 months)
2      1         2004       1          10 (or 20 months)


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index