Thank you @Quentin  and @ballardw for your inputs and suggestions regarding my issue and correct ways of quiestion publication in the forum 🙂  Using method proposed by @ballardw  helped.   I have used SERIES plot: series x=ady y=R2BASE / GROUP=usubjid GROUPORDER=ASCENDING; along with the specified values for the x-axis: values=(0 to 100 by 10); and with some additional modifications(not related with the intial issue) got this result: I have accepted @ballardw 's suggestion. Thank you Have a great weekend everyone.   ... View more

Thank you for your reply. Yes, it works on the cars dataset, the same way it works on mine, but here there are no usubjids(the colorful lines iniside each quartile). The main issue is that I am loosing that lines(see below), when I am trying to update x-axis vallues.     ... View more

This data can't be produced with a single and simple data step unfortnately. Here is the snippet of the input data. Ady is representing days, it's numeric. your provided exampe doesn't work(it creates the neccessary x-axis), and again, lead to a blank plot. ... View more

It looks like the file you are trying to copy from the SAS ODA server is not at the specified location. The error message states that the file was not found at /home/u61780777/output/person.sas7bdat , which suggests that the file is not present at that location. Make sure that the file exists at the specified location on the SAS ODA server and try the dbutils.fs.cp command again. If the file still cannot be found, you may need to check the file path and verify that it is correct. You can also try using the dbutils.fs.ls command to list the contents of the directory and verify that the file is present. The code for this would be: dbutils.fs.ls("/home/u61780777/output") This will list the contents of the /home/u61780777/output directory and you should be able to see if the file person.sas7bdat is present there. If it is not, you will need to find the correct location of the file and update the dbutils.fs.cp command accordingly.   Please let me know if it works. ... View more

Try this SELECT USERNAME, CURRENTPERM, SPOOLUSED, SPOOLQUOTA FROM dbc.dbcinfo WHERE USERNAME = 'user123'; This will return the current spool space allocation for your user account. You can then adjust the allocation as needed using the ALTER USER command mentioned above. ... View more

This might be what you want proc freq data=your_data_table; tables data1 data2 data3 / nocum; run; This will generate a frequency table that shows the number of times each value appears in each of the three columns ( data1 , data2 , and data3 ). If you want to combine the frequencies from all three columns into a single table, you can use the output out= option to write the results to a new dataset, and then use a data step to merge the results from the three columns into a single table. Here is an example of how you can do that:   /* Create a frequency table for each column */ proc freq data=your_data_table; tables data1 / nocum output out=freq1; tables data2 / nocum output out=freq2; tables data3 / nocum output out=freq3; run; /* Merge the frequency tables into a single table */ data all_data; merge freq1(in=a) freq2(in=b) freq3(in=c); by data_value; if a then freq=freq1; else if b then freq=freq2; else if c then freq=freq3; run; This will create a new dataset called all_data that contains a single table with the combined frequencies for all three columns. The data_value column will contain the unique values from all three columns, and the freq column will contain the total number of times each value appears in the table. ... View more

To fix this issue, you may need to increase the amount of space allocated to the user, or try running the query at a different time when there is less demand on the system. Additionally, you may want to try optimizing the query to reduce the amount of space it requires, or breaking it up into multiple smaller queries. Try to increase the spool space limit for your user account. This can be done by running the following SQL statement on the Teradata server: GRANT SPOOL ON user123 TO user123 WITH MAXSPOOL SIZE 100000;   ... View more

To calculate the hazard function estimate for a categorical variable using the Weibull distribution in SAS, you can use the PROC LIFEREG procedure. The PROC LIFEREG procedure allows you to fit a parametric survival model to your data, and then use the fitted model to estimate the hazard function for different groups of subjects.   In your case, you want to calculate the hazard function for patients with large tumors (tumt = 0). To do this, you can use the PROC LIFEREG statement to fit a Weibull model to your data, and then use the HAZARD option in the MODEL statement to request that the procedure estimate the hazard function for each level of the tumt variable. Here is an example of how you might do this in SAS: PROC LIFEREG DATA=Cancer; CLASS tumt; MODEL survdays*dead(0) = treat tumt / DIST=WEIBULL HAZARD; PROBPLOT; INSET; RUN; In this example, the PROC LIFEREG statement specifies that you want to fit a Weibull model to the data in the Cancer dataset. The CLASS statement indicates that the tumt variable is a categorical variable, and the MODEL statement specifies the model that you want to fit. The HAZARD option in the MODEL statement tells SAS to estimate the hazard function for each level of the tumt variable.   After running this code, you can use the PROBPLOT and INSET statements to create a probability plot that shows the estimated hazard functions for each level of the tumt variable. You can then use this plot to compare the hazard functions for different tumor types and identify any differences in the hazard of death for patients with different tumor types.   Alternatively, you can use the PROC LIFETEST procedure to calculate the hazard function for a specific group of subjects. For example, if you want to calculate the hazard function for patients with large tumors (tumt = 0), you could use the following code: PROC LIFETEST DATA=Cancer; TIME survdays*dead(0); STRATA tumt; TEST / HAZARD; RUN; In this code, the PROC LIFETEST statement specifies that you want to perform a survival analysis on the data in the Cancer dataset. The TIME statement indicates the time-to-event variable and the event variable, and the STRATA statement indicates that you want to stratify the data by the tumt variable. The TEST statement specifies that you want to calculate the hazard function for each stratum (i.e. for each level of the tumt variable). I hope this helps! Let me know if you have any other questions. ... View more

And answer to your side question. Yes, SAS Visual Analytics (VA) has a built-in option for displaying line breaks in long text fields. To enable this option, follow these steps: In SAS VA, open the Properties pane for the table or graph that contains the long text field. In the Data section, click the Edit button next to the long text field. In the Edit Field dialog box, go to the Display section. Select the "Treat long text as multiple lines" option. This option will cause SAS VA to display line breaks in the long text field as actual line breaks, rather than displaying the entire text as a single line. If you want to control the line breaks more precisely, you can use the PUT function in SAS to insert line breaks into the text at specific points. For example, if you have a character variable named mytext that contains long text, you can use the following code to insert a line break after every 50 characters:   mytext = PUT(mytext, $char50.); You can then use the mytext variable in your SAS VA table or graph, and the line breaks that you inserted with the PUT function will be displayed in the table or graph. ... View more

It sounds like you are looking for a way to create a PDF file that contains the payment details and notes for a specific set of payments based on certain filters (e.g. supplier ID and date range). In SAS, you can use the PROC REPORT procedure to create a report containing the payment details and notes, and then use the ODS PDF statement to save the report as a PDF file. Here is an example of how you might do this in SAS:   PROC REPORT DATA=mydata; WHERE supplier_id IN (123, 456, 789) AND payment_date BETWEEN '01JAN2022' AND '31DEC2022'; COLUMNS payment_id, payment_date, payment_amount, notes; DEFINE payment_id / GROUP; DEFINE payment_date / ORDER; DEFINE payment_amount / SUM; DEFINE notes / DISPLAY; BREAK AFTER payment_id / SKIP; COMPUTE after payment_id; LINE 'Notes:'; ENDCOMP; COMPUTE after notes; LINE @2 '--------------------------------'; ENDCOMP; RUN; ODS PDF FILE='payment_notes.pdf'; PROC REPORT DATA=mydata; WHERE supplier_id IN (123, 456, 789) AND payment_date BETWEEN '01JAN2022' AND '31DEC2022'; COLUMNS payment_id, payment_date, payment_amount, notes; DEFINE payment_id / GROUP; DEFINE payment_date / ORDER; DEFINE payment_amount / SUM; DEFINE notes / DISPLAY; BREAK AFTER payment_id / SKIP; COMPUTE after payment_id; LINE 'Notes:'; ENDCOMP; COMPUTE after notes; LINE @2 '--------------------------------'; ENDCOMP; RUN; ODS PDF CLOSE; In this example, the PROC REPORT statement creates a report that includes the payment details and notes for payments made by the specified suppliers within the specified date range. The ODS PDF statement is used to save the report as a PDF file named payment_notes.pdf .   If you want to pass parameters from SAS VA to SAS Portal, you can do so using the SASVA function in SAS Portal. This function allows you to access the current value of a SAS VA parameter from within a SAS Portal report. For example, if you have a SAS VA parameter named p_supplier_id that contains the ID of the selected supplier, you can use the following code in SAS Portal to access the value of that parameter:   data _null_; supplier_id = SASVA('p_supplier_id'); run; You can then use the supplier_id variable in your PROC REPORT code to filter the payment data based on the selected supplier ID. I hope this helps! If you have any other questions, please let me know. ... View more

Yes, I'd be happy to help you with your question. A competing risk analysis is used to study the impact of one or more risks on an outcome of interest, taking into account the presence of other risks that may affect the outcome. In SAS, you can use the CRCPHREG procedure to perform a competing risk analysis with time-dependent covariates. To use the CRCPHREG procedure, you will need to have your data organized in a specific way. First, you will need a variable that identifies each subject in your study. You will also need a time-variable that indicates the time at which the event of interest occurred or was censored. You will also need to have a variable that indicates the event type (e.g. the specific competing risk that occurred) and a variable that indicates whether the event was observed or censored. Once you have your data organized in this way, you can use the CRCPHREG procedure to fit a competing risk model. Here is an example of how you might do this in SAS:   PROC CRCPHREG DATA=mydata; MODEL event_time*event_type(0)=covariates; RUN; In this example, event_time is the time-variable, event_type is the variable indicating the event type, and covariates is a list of the covariates that you want to include in the model. I hope this helps! If you have any other questions, please let me know. ... View more

To fulfill the stage condition in question 3, you can add a condition to the if statement that checks for the value of stage . For example, you could do something like this:   data temp2; set temp1; by pt_id; retain lngth; if first.pt_id then lngth=0; lngth+totmnth; if last.pt_id or stage=1 then output; run; This will output the data for each patient only if they have reached the last visit in the study or if they have reached stage 1 (i.e., disease progression has been observed). You could also add an additional variable to the output data set that indicates whether disease progression has been observed for each patient. This could be done by adding a new variable called disease_progressed and setting its value to 1 if the patient has reached stage 1, and 0 otherwise. This could be done like this: data temp2; set temp1; by pt_id; retain lngth; if first.pt_id then lngth=0; lngth+totmnth; if last.pt_id or stage=1 then do; output; disease_progressed = (stage=1); end; run; This should produce the desired output data set with one row per patient, containing the patient ID, treatment group, follow-up time, and a variable indicating whether disease progression has been observed. You can then use this data set for further analysis. ... View more

You can use the %DO loop in SAS to iterate over the different groups defined by the BY statement in your PROC BGLIMM code. For each group, you can call the %postsum macro and store the results in a table. Here's an example of what that might look like:   %macro postsum_by_group(data=, var=); /* Initialize an empty table to store results */ data results; length simulation $32; length mean median stderr $32; output; /* Loop over each group defined by the BY statement */ %do i = 1 %to &data..n_classes; /* Call the %postsum macro for the current group */ %postsum(data=&data., var=&var., by=simulation, classid=&i.) /* Store the results in the table */ simulation = "Simulation &i"; mean = mean; median = median; stderr = stderr; output; end; run; %mend; /* Use the macro to compute summaries by group */ %postsum_by_group(data=sims_post, var=intercept); This code defines a %postsum_by_group macro that takes in the name of the data set containing the posterior samples and the variable of interest, and computes summaries for each group defined by the BY statement. You can then use this macro to compute summaries for the intercept variable in your example. ... View more