BookmarkSubscribeRSS Feed
amanjot_42
Fluorite | Level 6

Hi guys!

 

I am trying to come up with matching firms (control firms) for my treated group of firms. I have two separate files: one containing data relating to treated firms with company identifier (CUSIP) and other data, another with non-treated firms with company identifier (CUSIP) and other data. 

Can you please help me in coming out with matched control firms, which are from the same treatment year, same industry, and same 10*10 size-book-to-market portfolios.

 

Treated firms:

 

CUSIP  Fyear  SIC(industry) Treatment_yeardummy  Size  Book-to-market

10000  2000  12  0  25  2

10000  2001  12  1  24  3

10000  2002  12  0  23  4

10000  2003  12  0  22  4

12000  2005  13  0  43  6

12000  2006  13  0  43  7

12000  2007  13  0  44  3

12000  2008  13  1  45  2

14000  2010  11  0  21  4

14000  2011  11  1  22  8

14000  2012  11  0  23  4

 

Non-treated firms:

 

CUSIP  Fyear  SIC(industry)  Size  Book-to-market

14000  2001  12   26  4

14000  2002  12   30  3

14000  2003  12   31  5

14000  2004  12   32  4

15000  2006  13   66  6

15000  2007  13   67  8

15000  2008  13   65  7

15000  2009  13   69  2

17000  2010  11   10  4

17000  2011  11   12  9

17000  2012  11   13  4

 

Cheers

Amanjot

2 REPLIES 2
ChrisNZ
Tourmaline | Level 20

1. Please provide your data as a data step.

2. What's the expected output?

Reeza
Super User
PROC PSMATCH. Or Mayo Clinic has some greedy matching algorithms - usually used for medical case control but can be used for other applications.

SAS Innovate 2025: Save the Date

 SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!

Save the date!

How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 2 replies
  • 819 views
  • 0 likes
  • 3 in conversation