Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Vassilopoulos Achilleas" <vassilopoulos.statalist@gmail.com> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | RE: st: RE: RE: RE: problem with commands |
Date | Mon, 13 Sep 2010 15:50:50 +0300 |
Crysa - the only thing that differs between what you are writing and the commands is the "but they differ in the 3rd digit" in c. I have not incorporated this part in the commands since I didn't see any sic_mother being the exact same with sic_sub in the piece of data you've posted in your very first e-mail. I'm sorry if this was the reason for your trouble. Anyway, following is my suggestion but keep in mind that it will make a difference only if you have any subsidiaries with the same sic as their mothers (in all three digits): replace this command : count if (year_inc_sub<=`y') & (twosic_moth==twosic_sub) with that one: count if (year_inc_sub<=`y') & (twosic_moth==twosic_sub) & (sic_sub!=sic_mother) and leave everything else unchanged. If you still get the same results (i.e. 3 for all observations), I would strongly recommend that you carefully examine your data. Do some calculations by hand to make sure that it is not indeed 3 for all. Hope this helps, _____________ - _______________ Achilleas Vassilopoulos Agricultural University of Athens, Dept. of Agricultural Economics and Rural Development, Lab. of Political Economy and European Integration. Iera Odos 75, 11855, Athens, Greece Tel: (+30) 210-5294726 Fax: (+30) 2105294786 e-mail : avassilopoulos.aua@gmail.com -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of ???s???a G?a?????p????? Sent: Monday, September 13, 2010 12:44 PM To: statalist@hsphsun2.harvard.edu Subject: Re: st: RE: RE: RE: problem with commands Dear Statalisters, Based on my previous e.mails, I would like to thank you for the help. I let you know that finally, I have the variable 'year' years from 1990-2005 in a sequence. Unfortunately, another problem which still remains has to do with the estimation of diversification variable. The diversification variable should be created under the following logic: For observation in year 1990 the value of diversification should be the sum of a, b, and c below: a) take the total number of subsidiary companies which were incorporated in 1990 or earlier whose 1st digit of sic_sub is different than the 1st digit of sic_mother and multiply them by 3; divide this number by the total number of companies which where incorporated in 1990 or earlier (in the example, the total number of companies existing in 1990 is 4) b) take the total number of subsidiary companies which were incorporated in 1990 or earlier for which only the 1st digit of their sic_sub is the same as the 1st digit of sic_mother and multiply them by 2; divide this number by the total number of companies which where incorporated in 1990 or earlier c) take the total number of subsidiary companies which were incorporated in 1990 or earlier, whose 1st and 2nd digits of sic_sub are the same as the 1st and 2nd digits of sic_mother but they differ in the 3rd digit, and multiply them by 1, divide this number by the total number of companies which where incorporated in 1990 or earlier As you see below, my results look like: +-------------------------+ | id_mot~r year diver | |-------------------------| 1. | X 1990 3 | 2. | X 1991 3 | 3. | X 1992 3 | 4. | X 1993 3 | 5. | X 1994 3 | |-------------------------| 6. | X 1995 3 | 7. | X 1996 3 | 8. | X 1997 3 | 9. | X 1998 3 | 10. | X 1999 3 | . ..... |-------------------------| 11.. | X 2005 3 | +-------------------------+ The diversification variable has always the value '3'. This is not true, indeed. I suppose that there is an error in this part of the command which you suggested me: ********************** scalar a=scalar(digit)*3/scalar(total) count if (year_inc_sub<=`y') & (firstsic_moth==firstsic_sub) scalar digit2=r(N) scalar b=scalar(digit2)*2/scalar(total) count if (year_inc_sub<=`y') & (twosic_moth==twosic_sub) scalar digit3=r(N) scalar c=scalar(digit3)*1/scalar(total) *********************** Especially, I feel that something is wrong in the part "scalar c=scalar(digit3)*1/scalar(total)" but I cant correct it. Any suggestions? Thank you very much ,again, for consideration! Chrysa * * 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/