<>
Difficult case...
*************
clear*
inp siren str20 country taxrate
17251067 Spain 0.35
36320950 "Czech Republic" 0.31
45750817 Tunisia 0.33
end
g byte choice =1
compress
fillin siren country
format siren %9.0f
replace choice=0 if choice==.
bys country (taxrate): replace taxrate=taxrate[1]
drop _fillin
sort siren (country)
l, noo sepby(sir)
*************
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von
[email protected]
Gesendet: Dienstag, 10. März 2009 12:04
An: [email protected]
Betreff: st: problem in the preparation of my dataset to run a conditional
logit model
Hello,
I have a dataset whose beginning is this one:
siren country tax
17251067 Spain .35
36320950 Czech Republic .31
45750817 Tunisia .33
"Country" is the investment location choice of firms called "siren". Tax
is the statutory corporate tax rate of the country.
(There are other firms' and countries' characteristics that I did'nt
indicate)
I would like to shift my dataset like that:
siren country tax choice
17251067 Czech Republic .31 0
17251067 Spain .35 1
17251067 Tunisia .33 0
36320950 Czech Republic .31 1
36320950 Spain .35 0
36320950 Tunisia .33 0
45750817 Czech Republic .31 0
45750817 Spain .35 0
45750817 Tunisia .33 1
With this new dataset I aimed at writing to stata:
****
clogit choice country tax, group(siren)
****
The problem is that I don't know how to transform my dataset, and I don't
find anything on the Internet. Could someone indicate me what kind of
command I can deal with?
Thank you very much for help
Isabelle
*
* 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/
