Proc LIFETEST

[rcleven2]

I am replicating a lifetime risk analysis that the CDC put out a few years ago regarding HIV infection among race and risk category. Currently the process uses a program called DEVCAN which was built for calculating lifetime cancer mortality. PROC LIFETEST is the only SAS procedure that is close to what I need. 

Its looks as though PROC LIFETEST, for survival analysis starts with a cohort and follows that group over time. Well, I am conducting this for an entire state's population and don't have each citizen as an observation. Is there a way to calculate with LIFETEST using this data format:

AGE         POPULATION      RACE          SEX             RISK              HIV_POS

1               8,000                    White           F                  None              5

2               9,000                    White           F                  None              0

3               10,000                  White           F                  None              0

.

.

85+           13,000                  White           F                  None              7

1               8,000                    Black           M                  None              8

...Instead of having each line be an observation like i have seen in each paper and example so far?

[Reeza]

Do you have dates attached to those? Part of PROC LIFETEST does require a indication of the time of when events happen and it doesn't look like your data has those components.

[rcleven2]

The date component would be met using Age as the increasing time value.

[Reeza]

Then look at the FREQ statement in LIFETEST.