Yoshiro:
The simplest solution is to estimate the separate regressions and store the estimates, but in each regression you only use six observations. In the code below the estimates are stored in the matrix be where the first column is the district id and the second the slope.
reg population year if id == 1
mat b = 1, _b[year]
forvalues i = 2/1000{
reg population year if id == `i'
mat b = b \ `i' , _b[year]
}
HTH,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
-----Original Message-----
From: [email protected] [mailto:[email protected]]On Behalf Of Yoshiro Nagao
Sent: vrijdag 7 april 2006 8:11
To: [email protected]
Subject: st: slope for each individual
I have such a dataset as follows:
************************************
district ID,year,population
1,1998,2000
1,1999,2010
1,2000,2020
1,2001,2030
1,2002,2040
1,2003,2050
2,1998,1000
2,1999,1010
2,2000,1020
2,2001,1030
2,2002,1040
2,2003,1050
....
1000,2002,4060
1000,2003,5000
************************************
For the each district, population
is recorded every year between
1998 and 2003.
I would like to calculate
individual "regression coefficient (slope)"
for the each district.
General slope is not of my interest.
*
* 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/
