Hi Pamela,
I don't really get what you wan't to do. It is unclear for example what
you mean by "I also know how often 1 or 2 should be each given in total
for each year." - I do not see any year variable.
Nevertheless, if you just want to replace your missing values with 1's
and 2's randomly, with probabilities prob1 and prob2 respectively, try
the following commands:
set seed 12345
gen random = uniform()
replace st = 1 if random < prob1 & st == .
replace st = 2 if st ==.
drop random
tom
On Jan 18, 2006, at 6:08 PM, Pamela Mueller wrote:
I need to fill in missing values in my dataset. For most sectors I
know
how many start-ups there were for each year, but the data was not given
if the number of startups is less than 3 (hence one or two).
I know that the missing should be 1 or 2 and I know the probability for
either one. I also know how often 1 or 2 should be each given in total
for each year.
I tried recode, impute, mvencode but it did not work.
Maybe someone has a hint?
Thank you!
Pamela
sect st prob1 prob2
1 4
2 3
3 . 0.3 0.7
4 8
5 0
6 . 0.45 0.55
7 3
8 5
9 . 0.48 0.52
--
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Pamela Mueller
Max Planck Institute of Economics
Kahlaische Strasse 10
07745 Jena, Germany
tel +49 3641 686 723
fax +49 3641 686 710
pmueller@econ.mpg.de
www.econ.mpg.de
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*
* 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/
Tom Trikalinos, MD
ttrikalin@mac.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/