Hi All - I have a dataset which contains account number, balance, limit and apr. I have to separate out 10% population from this dataset. This 10% population  should be a (stratified) random sample from the dataset  and also the distribution of balance,limit and apr between 10% popluation and remaining 90% population should be equal ( approximately equal) . I have used proc surveyselect procedure for sampling dataset based on one variable. proc surveryselect data = dataset out=new_dsn samprate=.1 outall; strata cust_flag; run; Can you some one help me how to do the samething for many variables. Thanks Dhana ... View more

I have a dataset like this Cust_no acct_no open_date enrollment 001 123 19-Jun-08 0 001 456 27-May-08 1 001 789 24-Oct-06 0 001 101 12-Jun-01 1 The customer need to enroll their account number in the reward program, so that they will get some discount or future benefits. A customer can have any number of accounts and he can enroll any number of account in the program. In the above example the customer has 4 accounts and he has enrolled two of his account in the program. But for the internal processing we will consider only one account which was enrolled & opened very recently should be considered. From the above example how can we take out only the second record which satisfies the above critieria. Cust 2 has enrolled in the program and with account number 456 being the one which opened recently. When I sort the dataset by descending open_date I am getting the most recently opened account, but it is not always the most recently opened account is enrolled in the program. Thanks Dhana ... View more