Friday, February 1, 2008

Use a sample to hasten preliminary analysis

I have used following ways;

**************************
proc surveyselect data=onenn method=srs n=10000 out=onen;
run;

**************************
data onen;
merge
fa7684 fa8694 fa9600 nur92 nur94 n94_dt
temp(in=mstr) nur96 nur98 act8600
nur82 nur88 n84_dt n86_dt n90_dt
fileb n767880 meddata
temp db7602
fatalmi mi stroke anginew
fatalstk deadff2004 pact spact end=_end_;

by id;
exrec=1;
if first.id and mstr then exrec=0; /*** mas = master file ie. n80_cf ***/
if famdb82=1 then famdb88=1;
else famdb88=0;
random=RANUNI(-1); /* GENERATE A RANDOM VECTOR */
%let k=5000;
run;

PROC SORT DATA=onen;
BY random; /* SORT OBSERVATIONS BY THE RANDOM VECTOR */
run;

DATA onensample;
SET onen(drop=random);
IF _N_ le &k; /* SELECT THE FIRST K OBSERVATIONS */
/*both magne