That is NOT an ERROR.  It is a NOTE.  You still not NOT include the CONTEXT needed to make complete sense of the NOTE.  You did not show the part of the LOG that shows the CODE being run so we don't know what statement was on line 16 and column 15.   But assuming the issue is with converting BIRTHDATE to a number the value of BIRTHDATE displayed in the log is helpful.  It is showing the it is empty, so that is definitely does not represent a valid date.   You can prevent that note in two ways.   You could first test if BIRTHDATE is empty and only execute the INPUT() function when it is not. if not missing(birthdate) then birthdate_num=input(birthdate,mmddyy10.); Or you could suppress ALL of the notes about invalid values by including the ?? modifier before the informat.  Then even if the value of BIRTHDATE is 'dawn of time' you won't get an invalid value NOTE. birthdate_num=input(birthdate,??mmddyy10.)   ... View more

Since your other post indicating this process has to deal with additional columns, which is a stupid way to deal with data as code needs to be modified one way or another for almost any step where the variable names keep changing, perhaps  you should READ YOUR DATA into a proper format to begin with.   Preventing problems is usually way easier than fixing them with cumbersome code.   This for example reads 5 pairs of variables into a "long" format with on observation per "date". Your implication from your previous and this post is that the poorly designed data contains sequential date values. So this read such. data example; input id @@; do date= '01May2024'd to '05May2024'd; input final due @@; output; end; format date date9.; datalines; 1 2 3 4 5 6 7 8 9 10 11 ; I strongly suspect you are starting with some spreadsheet file and don't realize the problems that many people create by the structures such as yours. SAVE the file to CSV, and an infile statement pointing that file and update the values of "date" in the do loop and you may be able to read this into a much more flexible data set: data example; infile "C:\somepath\file.csv" dlm=',' dsd ; input id @@; /* other variables before the date named columns go here*/ do date= '01May2024'd to '05May2024'd; input final due @@; output; end; format date date9.; run;     ... View more

@NewUsrStat  Looks like @PaigeMiller already provided the code that returns your desired result. Suggest you mark it as the solution. ... View more

To re-order the values (not variables) on the X-axis, you would have to sort data set WORKING4 in the order that you want the values to appear. Then in PROC GLM you would use   Proc GLM data=working4 (rename=(change_fev1pp = Change)) order=data;     You might also be able to use ORDER=FORMATTED but since we don't know what the format is that your are using, I can't say if that would work.  ... View more

I've been searching around for this so long!   I feel like I've finally found oasis!   Thank you very much! ... View more

You need to change your data structure by PROC TRANSPOSE to get this kind of graph.   data have; call streaminit(123); do total_qual_care_score=0 to 8; do id=1 to 100; TM_non_ADRD_group=rand('bern',0.2); MA_non_ADRD_group=rand('bern',0.8); output; end; end; run; proc transpose data=have out=temp; by total_qual_care_score id; var TM_non_ADRD_group MA_non_ADRD_group; run; proc summary data=temp nway; class total_qual_care_score _NAME_; var col1; output out=temp2 mean=mean lclm=lclm uclm=uclm; run; data want; set temp2; by total_qual_care_score ; if first.total_qual_care_score then call missing(cum_mean,cum_lclm,cum_uclm); cum_mean+mean; _lclm=mean-lclm;cum_lclm=cum_mean-_lclm; _uclm=uclm-mean;cum_uclm=cum_mean+_uclm; run; PROC SGPLOT data=want; vbarparm category=total_qual_care_score response=mean/ group=_NAME_ name='x' ; scatter x=total_qual_care_score y=cum_mean/markerattrs=(size=0) yerrorlower=cum_lclm yerrorupper=cum_uclm; xaxis label='Total Quality of Care Score'; yaxis label='Proportion satisfied'; keylegend 'x'/title=''; RUN;     ... View more

This is includes the "incremental number":   data want; set db; by id; if first.id then counter=1; else counter+1; combined=catx('_',id,put(discharge,date9.),counter); drop counter; run; ... View more

Why not leave the data untransposed?   The only reason I can see you might want to have this data arranged with columns qtr1, qtr2, ... is for a report, and if that's what you want, do not transpose, use PROC REPORT which will work on untransposed data.   data two; input name $ qtr amount; datalines; adam 1 10 adam 2 20 adam 3 30 adam 4 40 paul 1 23 paul 2 33 paul 3 41 paul 4 67 ; proc report data=two; columns ('Name' name) (' ' amount),qtr; define name/' ' group; define qtr/'Quarter' across; define amount/' ' sum; run; ... View more

Some of us (like me) refuse to (or cannot) download attachments. Please include the log in your reply by copying the log as text and pasting it into the window that appears when you click on the </> Icon.   Repeating with emphasis:   Also, please go back to your original post and change the subject line to provide a meaningful subject line that describes the problem. "Getting Error..." doesn't provide any meaningful information. Probably 95% of posts here could say "Getting Error..." and then the whole forum would be much less useful. ... View more

I've been playing around with some data to make a p-chart recently, where I also have varying subgroup sizes.  As I was reading up again on p-charts, I was surprised to see Donald Wheeler is actually a fan of using IR-charts where most textbooks would advise using a p-chart (or np-chart or c-chart or u-chart).  His basic argument is that if the p-chart assumption of a binomial distribution is right, the IR-chart will give you about the same limits, but if the assumption of binomial distribution is wrong, the IR-chart will give you better empirical limits rather than using the p-chart's model-based limits.  See e.g. https://www.qualitydigest.com/inside/quality-insider-article/what-about-p-charts-093011.html and https://www.qualitydigest.com/static/magazine/jul/spctool.html  Since Wheeler's books were my introduction to SPC, I tend to like his ideas.  So for my case with data like yours, I'm thinking I may just make an IR-chart of the p-values.  Another side benefit of me is that this will also give each lot equal weight, independent of sample size.  A typical p chart or mean chart with varying sample size will give more weight to the lots have more data.  That makes sense if your process is under control, and the sample size for each lot is not meaningful information.  But in some cases with two-stage sampling designs, when there is a lot with poor performance characteristics they sample more data.   So you can end up giving more weight to poor-performing lots.   One thing I love about SPC is that it's a very practical / applied field.  In the end, you could make a p-chart and an IR-chart, and you could try making different p-charts with different values for LIMITN.  With SPC, your goal is not to calculate the "correct" process limits in the same way that you might want to calculate the "correct" estimate of the variance of a parameter in some fancy statistical model.  Instead, your goal (in my experience), is to calculate "useful" limits, where "useful" means do the process limits help you understand your process, and are they useful in helping bring the process under control and identifying lots with special cause variation. ... View more

With 8 events in 630 patients, it's really not surprising that nothing is significant. I think it is also unlikely that another analysis method would return a different result.    The real answer is that you don't have enough data to find statistical significance. ... View more

Thank you very much Patrick for your help! ... View more

The problem is that what you want is to double count in the ALL row (actually "up to ten" count), for which tabulate does not provide a mechanism.   I suggest a data set VIEW with a new variable, to be included in the proc tabulate.   data vneed / view=vneed; set have (keep=columnvar rowvar1-rowvar10); row_count=n(of rowvar:); run; proc tabulate data=vneed; class columnvar rowvar1-rowvar2; var row_count; table rowvar1-rowvar2 row_count*sum='Col Total' ,columnvar; run; ... View more

If you were submitting native teradata queries on one of the teradata servers, would you be able to query data from the second teradata server?   If not, then I don't see how you can avoid pulling the ID's from both servers down to SAS to do the join.   I suppose you could try pulling just one set of ID's from teradata  server A and then you could push the ID's up to teradata server B and do the join in teradata.  So that would only require transferring one set of ID's, but you would have to pull it from server A and then push it to server B, so it's still a lot of time moving data.   I would work with your admins to see if you can get a fast connection between the two teradata servers. ... View more