08-10-2012 02:16 AM
I am looking to perform the following functions
-Sum the squared revenues(REVT_SQUARED) by industry (HERFSIC) and year (FYEAR). As there are 7 different industries and 61 different years (1950-2011) there should be approx. 427 total revenues(TOTREV)...
-Divide the firms individual squared revenue (REVT_SQUARED) by the total revenue(TOTREV) for that particular industry (HERFSIC) and year (FYEAR) and call this variable "CONRATIO"
-CONRATIO'S should look like 0.15, 0.34 0.22 etc.
Help on performing this command would be very helpful. I am currently receiving very low concentration scores such as; 0.0003, 0.0012 etc. I am worried there might be an error with my command. data below
08-10-2012 02:52 AM
I'm a bit confused by "squared revenue" - not obvious why this would be of interest. But I'm assuming TOTREV is supposed to be the sum of squared revenue, not the sum of individual revenue, otherwise the ratio doesn't make much sense either. (You would get different answers depending on whether you worked in dollars or cents.)
Under those assumptions:
proc summary data=have nway;
class herfsic fyear;
output out=total_squared_revs (drop=_type_ _freq_) sum(revt_squared)=totrev;
create table want as select
a.revt_squared/b.totrev as conratio
from have as a join total_squared_revs as b
on (a.herfsic=b.herfsic AND a.fyear=b.fyear);
08-10-2012 03:15 AM
Squared revenue is just the revenue variable^2,
TOTREV is the summation of the squared revenue by year and industry. So your assumptions are correct.
I am following the calculation of the herfindahl index