Hi, I am trying to identify 2 visits atleast 90 days apart after intervention date. For example, if I have a dataset like this  Intervention_date      Visit_1        Visit 2        Visit_3         Visit_4            follow-up date (intervention+365);            1/2/2020          4/2/2020    5/7/2020    6/8/2020         1/1/2021          2/3/2020          5/4/2020    6/1/2020    8/4/2020        10/4/2020   I have the intervention date but I do not have visit_1 to visit_4 yet. I have created a follow_up date as 12 months after intervention date (intervention date + 365) so as to see all visit_dates. I would expect that my visit_1 to visit_4 should be within intervention and follow_up date.   Task 1: I will like to create  visit_1 which is the first visit for each individual after the intervention date. I am thinking of using visit_1 = min(Intervention_date); I do try it but did not work as expected.   Task 2: I will like to create the second visit (visit_2) which will be at least 90 days after the visit_1. So the way am thinking this will be if a person has there visit_2 at least 90 days after visit_1, then visit_2 =1; else visit_2=0;   Am struggling with doing this in SAS and will appreciate any help. Thanks     ... View more

Hi, I am familiar with this issue but cant fix it. I'm getting the following error from pro tabulate:   WARNING: A class variable is crossed with itself in the table statement at line 867. This may cause unpredictable results. WARNING: A class variable is crossed with itself in the table statement at line 867. This may cause unpredictable results. NOTE: There were 5361 observations read from the data set WORK.AGE. NOTE: PROCEDURE TABULATE used (Total process time): real time 1.16 seconds   I know this is as a result of a cross tab of the same variable however, I do not know how to resolve the issue in this code (FYI: I found the code online and modified it).   This is a part of the code:   %macro do_freq_gender; %do j=1 %to &numvars; proc tabulate data=gender; class gender &&var_&j. ; table (&&var_&j. all), (gender all='All') * (N colpctn='% of Col'); format gender sexf. &&var_&j. &&fmt_&j.; run; %end; %mend;   Any help please. Thanks. ... View more

Hi, How do I find the hazard function estimate for a categorical variable using weibull distribution. My categorical variable is categorical variable is Tumt: 0=large,1=squamous,2=small,3=adeno I want hazard function for patients with large tumors (large =0). I see that proc lifereg can be used to calculate weibull distribution but I don't know how to get the hazard function for a specific categorical variable or can I use proc lifetest? if yes how do I code it pls. This is my code:   proc lifereg data=Cancer ; class tumt ; model survdays*dead(0) = treat  tumt / dist=Weibull; probplot; inset; run;   ... View more

Hi, This is from the free online paper: Using New SAS 9.4 Features for Cumulative Logit Models with Partial Proportional Odds. On page 7, a subset data was created: The dataset “MB” is comprised of 408 of the 508 observations in the dataset.  Dataset “XV” contains 100 observations and will be used for cross-validation purposes for the model. Question: Was the data MB still contain 508 or not. From my understanding, MB only contain 408, so my question is how was 408 MB separated from 508 because proc selectsurvey will only recreate 100(XV) from MB and MB will still contain 508 atleast from my sas knowledge. How do I have 408 with the proc selectsurvey and not 508? Thanks   ... View more

Hi, I have a folder with two levels. The first level has 20 second level folders. I have sasfiles in each of the second level and will like to create a single libname for them. How do I do that?  For example:  First level folder : /_U/N/RC/Proj/SAS Second level folder : /_U/N/RC/Proj/SAS/data1/a.sas7bdat                                  /_U/N/RC/Proj/SAS/data2/b.sas7bdat                                  /_U/N/RC/Proj/SAS/data3/c.sas7bdat                                  /_U/N/RC/Proj/SAS/data4/d.sas7bdat When I write a libname to reference all the second level files using the   libname x "/_U/N/RC/Proj/SAS"; run; its not working and I do not want to go through the pain of writing 20 libnames and putting all the libref in  another single libname or is that what I have to do?  ... View more

Hi, I'm getting this error from a propensity score code. I don't know how to fix the error. Any help please. I found a similar question online where someone suggested to amend the target line and add -MEMSIZE 30G. I don't know what that means. Please provide a clear step by step description on how to fix it. Thanks   NOTE: PROC LOGISTIC is modeling the probability that case_stat=1. ERROR: The SAS System stopped processing this step because of insufficient memory. NOTE: There were 758172 observations read from the data set AOA.M_2007_2011_A. WARNING: The data set WORK.OSA_FINAL_PS may be incomplete. When this step was stopped there were 0 observations and 55 variables. WARNING: Data set WORK.OSA_FINAL_PS was not replaced because this step was stopped. NOTE: PROCEDURE LOGISTIC used (Total process time):       ... View more

Hi, I am doing inflation cost analysis which am new to using sas. I will like to produce an output for all cost variables but I only have output for total. Please any help with how the code can generate the outputs e.g. inf_cost_hosp, inf_cost_ed, inf_cost_rx and inf_cost_out and not only the inf_cost_total? Here is the code:   %macro cost(var1); data a2007_2011; set b2007_2011; if obsyear='2006' then inf_cost_&var1.=cost_&var1.*1.10; else if obsyear='2007' then inf_cost_&var1.=cost_&var1.*1.08; else if obsyear='2008' then inf_cost_&var1.=cost_&var1.*1.04; else if obsyear='2009' then inf_cost_&var1.=cost_&var1.*1.04; else if obsyear='2010' then inf_cost_&var1.=cost_&var1.*1.01; else inf_cost_&var1.=cost_&var1.; run; %mend cost; %cost(hosp); %cost(ed); %cost(out); %cost(rx); %cost(total); ... View more