cluster size

[Deepai]

Hello helping hands,

I have 20,000 individuals in my dataset. All these individuals belong to 400 different clusters. I want to get how many people are there in each cluster.  i want to get the cluster size in the same dataset. Sorry i am very new with SAS.

Thanks

[PGStats · Accepted solution]

You could use something like:

proc sql;
create table newTable as
select *, count(distinct individualId) as clusterSize
from myData
group by clusterId;
quit;

where individualId and clusterId are variables in your dataset.