/************************************************************************************
* STEP ONE: Extract Compustat data;
************************************************************************************/
 
data comp1;
  set comp.funda;
  where fyear>=1986
    and indfmt='INDL' and datafmt='STD' and popsrc='D' and consol='C';
  keep gvkey datadate fyear;
run;
 
/*******************************************************************************************
* STEP TWO: Link GVKEYS to CRSP identifiers;                                               *
* Use CCMXPF_LNKHIST table to obtain CRSP identifiers                                      *
********************************************************************************************/
 
proc sql;
  create table comp2 as
  select a.*, b.lpermno as permno
  from comp1 as a, crsp.ccmxpf_lnkhist as b
  where a.gvkey=b.gvkey and b.linkprim in ('P', 'C') and
  b.LINKTYPE in ('LU', 'LC') and
  a.datadate >= b.LINKDT and (a.datadate <= b.LINKENDDT or missing(b.LINKENDDT))
  order by gvkey, datadate;
quit;