**  This example provides SAS code for calculating "person years" in a cohort study  ;
**  For each age group, age at the start and age at the end must be calculated. ;
* counting Person Years by year and age group; 
proc format 

value age5f * 5 year age group format; 
20-<25='01' 
25-<30='02' 
30-<35='03' 
35-<40='04' 
40-<45='05' 
45-<50='06' 
50-<55='07' 
55-<60='08' 
60-<65='09' 
65-<70='10' 
70-<75='11' 
75-<80='12' 
80-<85='13' 
85-<90='14' 
90-<95='15' 
95-high='16'; 
* format to identify minimum age value for age group. Note that this could probably be done mathematically as well; 
value agesrtf 
01='20' 
02='25' 
03='30' 
04='35' 
05='40' 
06='45' 
07='50' 
08='55' 
09='60' 
10='65' 
11='70' 
12='75' 
13='80' 
14='85' 
15='90' 
16='95' ; 
* age group labels; 
value age5l 
01='20-<25' 
02='25-<30' 
03='30-<35' 
04='35-<40' 
05='40-<45' 
06='45-<50' 
07='50-<55' 
08='55-<60' 
09='60-<65' 
10='65-<70' 
11='70-<75' 
12='75-<80' 
13='80-<85' 
14='85-<90' 
15='90-<95' 
16='95+' ; 
run; 
data pyears; 
set temp; 

* partition person years by year (calendar), and age group; 
* sdate=study start date (SAS date); 
* edate=study end date (SAS date)= minumum of date of death, date of event, date of loss to follow-up or end of study; 
* bdate=birth date (SAS date); 
do year=year(sdate) to year(edate);

* calculate date at start of year (sdate_year) and date at end of year (edate_year);

sdate_year=max(sdate,mdy(1,1,year)); 
edate_year=min(edate,mdy(1,1,year+1)); 
format sdate_year edate_year yymmddn8.; 

* calculate age at start date (sage) and age at end date (eage);

sage= yrdif(bdate, sdate_year, 'ACT/ACT'); 
eage= yrdif(bdate, edate_year, 'ACT/ACT'); 
* ensure that person years are distributed to each age group appropriately;

do agegrp=input(put(sage,age5f.),2.) to input(put(eage,age5f.),2.); 

* Be careful about the last age group (95+). If you have people older than 100 years in your cohort, their person years past age 100 will not be counted by this method. You will have to adjust age_end in this case.;

age_end=min(eage,input(put(agegrp,agesrtf.),3.)+5); 
age_start=max(sage,input(put(agegrp,agesrtf.),2.)); 
pyear=age_end-age_start; 
if pyear> then output; 
end; 
format bdate sdate edate yymmddn8.; 
format agegrp age5l.; 
end; 
run;