Thank you Arthur. Thank you for your help and your interest. I totally undertood your last email. I will try next time. Best, V. ... View more

Sorry, but  I am disagree, a forum is to learn from thisn, a problem generate new ideas. The above example constitute the real problem, the above problem is the one  I want to achieve...is not fair saying I have enough examples to at least to solve the problem...I am trying to solve this problem from yesterday, is not an easy problem, because if not, it will be solved. Best, V. ... View more

Hi Arthur, my problem is more complex than that simple example, but this example give you an idea what I wwant to achieve. Read carefully: The idea is  imputed only the missing value of the last visits with LOCF, the missing intermediate visits remaining missing, and the carried baseline (i.e week2) if it is missing remaining missing. In Bold face I show the visits need to be imputed with LOCF data new; input subjid week value; datalines; 1  Baseline 10 1 Week2   12 1 week8  14 1 week12 16 2 baseline 12 2 week2   4 2 week8  14 3 Baseline 13 3 week4  5 3 week12   2 4 baseline 1 4 week2   3 5 Baseline 3 5 Week2  5 5 week12 6 run; and I am looking for the want dataset: 1  Baseline 10 1 Week2   12 1 week8  14 1 week12 16 2 baseline 12 2 week2   4 2 week8  14 2 week12 14 3 Baseline 13 3 week4  5 3 week12   2 4 baseline 1 4 week2   3 4 week4   3 4 week8  3 4 week12 3 5 Baseline 3 5 Week2  5 5 week12 6 It is is a not easy problem I think, because you need to consider all the possible variations always keeepen imputed the last visits, and not the missing intermediate visisits, and the missing visits follow baseline. I hope it is more clear now. Thnaks a lot. V and the visit following ... View more

Hi Arthur, your last post did not come out in my email Yes, this is the last request. Thank you. I will try later if it works. Thnak you again for your time. ... View more

Hi again!...this problem make me nuts......is the last vistiS, not only the last visit...i Explain: data new;       length subjid $8 day $10 value 8;      input subjid day value;      datalines;      1   baseline 10      1   week2   12      1   week4   14      1   week8   16      1   week12  12      2   baseline 10      2   week4    12      3  baseline  10      3  week2      4      3  week8      2      ; The new code need to imputed the only the last visits: i am looking for this want dataset:    1   baseline 10       1   week2   12      1   week4   14      1   week8   16      1   week12  12      2   baseline 10      2   week4    12      2  week8     12      2  week12     12      3  baseline  10      3  week2      4      3  week8      2      3  week12   2 Can you help with this last one request! Thnaks Arthur. ... View more

Thank you brilliant, It works. In the mean time, I got the easy way, flagging the imputed data, and keeping only the last record But, yours is much better, thank you again Arthur. *Flaggin the imput data and keeping the last visit; proc sort data=new out= newtest;   by subjid day; run; proc sort data=want out=wanttest; by subjid day; run; *flagging the imputed data (LOCF); data locftest;   merge newtest(in=a) wanttest(in=b);   by subjid day;   if b and not a then do;   locf=1;   output;   end;   else do;   locf=0;   output;   end; run; data locf;   set locftest; if upcase(day)='BASELINE' then weekno=0;       else if upcase(day)='WEEK2' then weekno=2;       else if upcase(day)='WEEK4' then weekno=4;       else if upcase(day)='WEEK8' then weekno=8;       else if upcase(day)='WEEK12' then weekno=12;       run; proc sort data=locf; by subjid weekno; run; data locfok;   set locf;   by subjid weekno;   if locf=1 and not last.subjid then delete;   run; ... View more

Initial code, developed to hikuo and moddified for you, missing visit is imputed as the LOCF, but the baseline is not carried forward , i.e week2 if it is missing reamining missing in subject2, and week2, week4 willremaining missing in subject3: proc format;          value $seq             'baseline'=1               'week2'=2               'week4'=3               'week8'=4               'week12'=5               ;               value seq               1='baseline'               2='week2'               3='week4'               4='week8'               5='week12'               ;       run;   data new;      length subjid $8 day $10 value 8;      input subjid day value;      datalines;      1   baseline 10      1   week2   12      1   week4   14      1   week8   16      1   week12  12      2   baseline 10      2   week4    12      3  baseline  10      3 week8      4      ;       data new1;         set new;         _day=put(day,$seq.);         run; data new1;         set new;         _day=put(day,$seq.);         run;       data want;         set new1;         by subjid;         set new1(firstobs=2 keep=_day rename=_day=__day) new1(obs=1 drop=_all_);            if not last.subjid  then do _i=_day to __day-1;                 day=put(_i,seq.);                  if not missing(value) then output;           if _day = 1 then call missing(value);              end;         else do _i=_day to 5;                 day=put(_i,seq.);                 output;              end;              drop _:; run; this is the dataset:                                   1      1       baseline      10                                   2      1       week2         12                                   3      1       week4         14                                   4      1       week8         16                                   5      1       week12        12                                   6      2       baseline      10                                   7      2       week4         12                                   8      2       week8         12                                   9      2       week12        12                                  10      3       baseline      10                                  11      3       week8          4                                  12      3       week12         4 Now, my problem, is that only I am interested to impute the last visit, i.e i need to ridd off week8, because it was a visit missing in the original dataset, in with this condition, because it is not a last visit, it will remain missing...then my finaldataset ,  modifying the above code , have to be like that:                                   1      1       baseline      10                                    2      1       week2         12                                   3      1       week4         14                                   4      1       week8         16                                   5      1       week12        12                                   6      2       baseline      10                                   7      2       week4         12                                   8      2       week12        12                                   9      3       baseline      10                                  10      3       week8          4                                  11      3       week12         4 Thnak you. ... View more

Sorry Data_null and Ksharp very interesting your contribution, i will keepo it in my mind, after finish it...but still I want to end it with the Haikuo code....then Hi Arthur, You did it for the week post baseline, but now I am interesting only in imputed the last visit, the intermediate weeks as well as the post baseline visit,  if there are missing, will remaining missing, only i want to impute the last visit...can you do it in this code?... Thnaks. data want;   set new1;   by subjid;   set new1(firstobs=2 keep=_day rename=_day=__day) new1(obs=1 drop=_all_);      if not last.subjid  then do _i=_day to __day-1;           day=put(_i,seq.); /* another line changed */           if not missing(value) then output;           if _day eq 1 then call missing(value);        end;   else do _i=_day to 5;           day=put(_i,seq.);           output;        end;        drop _:; run; ... View more

Brilliant, proc sql works. I think with not proc sql more manipulation is required for thiis kind of many-many merge I think. Thanks a lot. ... View more

sorry PGStats....the non sql procedure is not right:                                  1     1      0       0       a                                   2     1      3       0       a                                   3     1      6       0       a                                   4     1      0       1       b                                   5     1      3       1       b                                   6     1      6       1       b                                   7     1      0       2       c                                   8     1      3       2       c                                   9     1      6       2       c                                  10     2      0       0       a                                  11     2      3       0       a                                  12     2      6       0       a                                  13     2      0       1       b                                  14     2      3       1       b                                  15     2      6       1       b                                  16     2      0       2       c                                  17     2      3       2       c                                  18     2      6       2       c ... View more