Patients visit at month in first 6 months and then every 3 months after that.   data have; input id $ time; /* time is study duration, unit is month, */ datalines; 1 1.5 2 3.4 3 5.6 4 9.8 5 13.2 6 2.5 7 10.1 8 15.6 9 7.5 10 21.1; RUN; /* each cycle is a month; want to know how many patients at each cycle */ What I want is like below: cycle1 10 /* 10 patients alive at end of 1st month */ cycle2 9 /* 9 alive at end of 2nd month */ cycle3 8 cycle4 7 cycle5 7 cycle6 6 cycle9 5 /* after first 6 months, patients visit every 3 months */ cycle12 3 cycle15 2 cycle18 1 cycle21 1 cycle24 0 /* if there is time >27, then cycle27 has value 0 */ My current idea is using select in proc sql: proc sql; create table want as select count(id) into: cycle1 from have where time>=1; select count(id) into: cycle2 from have where time>=2; ... select count(id) into: cycle6 from have where time>=6; select count(id) into: cycle9 from have where time>=9; select count(id) into: cycle12 from have where time>=12; ... QUIT; But I need to determine the last cycle. Maybe something like: last cycle = int(max(time)/3)*3 ... View more

    PROC LIFETEST data= adsl2 alphaqt=0.05 alpha=0.05 method=km outsurv=km_outsurv1 ; TIME aval * cnsr (1); STRATA TRT01PN; ODS OUTPUT ProductLimitEstimates=kme_sd1; RUN; ods listing; got warning like this: WARNING: The likelihood ratio test for strata homogeneity is questionable since some strata have no events.   In this case, is there a way to opt out the LRT? or is there a preferred way to handle this? ... View more

data have; input id $ line startdate $10.; datalines; A 1 2015-06-20 A 2 2015-07-31 A 3 2015-08-27 B 1 2016-05-01 B 2 2016-08-02 ; RUN;   what I want: ID  line   startdate         enddate A    1    2015-06-20    2015-07-30 A    2    2015-07-31    2015-08-26 A    3    2015-08-27    . B    1    2016-05-01    2016-08-01 ... View more

Here is the data I have data have; input id $ treatment $ linenumber date yymmdd10. ; format date yymmdd10.; cards; 001 A 1 2014-08-15 001 A 1 2015-06-20 001 A 2 2015-08-29 001 A 2 2018-02-28 001 A 2 2018-05-07 001 B 3 2018-08-01 001 B 4 2019-02-01 001 C 5 2019-03-03 ; run; I want to calculate the gap between the dates, and then create two flags: within the same ID/Treatment/Linenumber, if gap >90 days then GT90_within_line =1; within the same ID/Treatment, when linenumber changes, if the gap < 90 days, then LT90_btw_line_within_trt = 1   The expected output data will be like this:   Can anyone help? Many thanks in advance! ... View more