Use PROC POWER and the TWOSAMPLEMEANS statement. The TWOSAMPLEMEANS statement has example syntax, For a complete example and discussion, see the Getting Started examples for PROC POWER and modify the example for the one-sided t-test. ... View more

That looks like homework. Have you tried PROC POWER?     Documentation: http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_power_a0000001016.htm   User Written: http://www2.sas.com/proceedings/forum2008/368-2008.pdf ... View more

I think you might want to consider performing Partial Least Squares Regression on this data (PROC PLS).   This is, in a certain manner of speaking, similar to Principal Components Regression (not Factor Analysis regression), but has better mathematical properties than Principal Components Regression (and probably better mathematical properties than Factor Analysis regression). PLS has no difficulty handling ordinal or categorical predictor variables.   For age I have age varlable i want to categorise 1-15 as 1 16-30 as 2,30-rest as 3. Please note that you are creating your own problems by making a continuous variable AGE into a categorical variable, and your life would be so much easier if you treat AGE as a continuous variable. Normally, turning continuous variables into categories is not recommended at all since you are losing information; for example, age 15 and 16 are very close together on a continuous scale but if you create categories, 16 is very different than 15. While I don't know your problem or what types of results you are trying to achieve, in most cases, I wouldn't do this (yes there are exceptions). ... View more

If your tables are in SAS then using hash lookup tables could be quite efficient. In case your current month table could contain more than one record per customer then a tweak to below code would be required. /*assume tht its last 8months table which have 1million records*/ data Last8Month;   input custid name$ salary pan$ aprv :anydtdte.;   format aprv ddmmyy10.;   cards; 001 john 200000 AAAAAA 02/02/2014 002 raju 300000 BBBBBB 01/01/2013 002 raju 400002 BBBBBB 01/01/2014 003 david 600000 CCCCCC 04/04/2013 004 krishna 203030 DDDDDD 05/02/2015 005 mukesh 240000 EEEEEE 04/03/2014 003 david 782226 CCCCCC 08/05/2014 ; run; /*assume that it contains current table whose wanna apply for new credit cards which contain 10thousand records*/ data Current;   input custid name$ salary pan$ aprv :anydtdte.;   format aprv ddmmyy10.;   cards; 002 raju 400000 BBBBBB 12/05/2015 005 mukesh 240000 EEEEEE 12/05/2015 003 david 782226 CCCCCC 01/7/2015 ; run; data _null_;   if _n_=1 then     do;       if 0 then set Last8Month current;       dcl hash h(dataset:'current');       _rc=h.defineKey('custid');       _rc=h.defineData(all:'y');       _rc=h.defineDone();       dcl hash declined(dataset:'current(obs=0)',ordered:'y',multidata:'n');       _rc=declined.defineKey('custid','aprv');       _rc=declined.defineData(all:'y');       _rc=declined.defineDone();     end;   set Last8Month end=last;   if h.check()=0 then     do;       _rc=declined.add();       _rc=h.find();       _rc=declined.add();     end;   if last then declined.output(dataset:'want'); run; proc print data=want noobs; run; ... View more

This link may be helpful: http://support.sas.com/documentation/cdl/en/itechwcdg/64888/HTML/default/viewer.htm#p1t48e0y92v4jqn1csygma6z7178.htm ... View more

In clinical trials data processing there is "always" a document that provides information on how incomplete dates (or anything else) should be imputed.  You should read that. Perhaps something like this. 01-JUL-year when you have only the year. 15-mon-year when you have only month and year. Sometimes the imputation is slightly different if the date is a start versus an end date. The point is, the answer to the imputation is in the documentation for the analysis and you already have that. ... View more

You can mark you question as answered then, with your answer as the correct answer. ... View more