My guess is that the regression line in the left panel is only extending across the range of the data in the "before" period. The point on the vertical line would seem to belong to the "after" period. ... View more

  proc sql; create table want as select *, case when lowcase(mom) = lowcase(mom_new) then 'correct' else 'wrong' end as Check_mom from A;    quit; I am inferring from the example data that differences in letter case are not to be used to signify a non-match. If that is incorrect, then this code will fail. The CASE WHEN statement should illustrate how to do this for the "mom" variables, and it should be simple to add another CASE WHEN statement for the other two variables that need this.   This could also be done with a DATA step with a different syntax.   ... View more

I think you can interpret that p value to mean that there is a statistically significant effect of the clustering variable in this shared frailty model. SAS does have a worked example of a similar type of analysis: https://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_phreg_sect056.htm ... View more

If I understand your question, you want to control the output to HTML, and I'm not sure how to do that. It is possible to use the ODS tables to create output that you could print with other procedures. E.g., the following example will allow you to output the p value for a chi-square test statistic into one table (work.want1), and you could use a DATA step procedure to determine if the table outputted from the TABLES statement (work.crosstab1) should be retained. This example uses PROC FREQ, but ODS TABLE names are available in SURVEYFREQ: PROC SURVEYFREQ: ODS Table Names :: SAS/STAT(R) 9.3 User's Guide    ods tables ChisQ=want1; proc freq data=sashelp.cars ; tables type*origin / chisq out=crosstab1; run;  ... View more

Try ODS OUTPUT CLOSE; ... View more

You can use the ODS tables to obtain a variety of statistics related to the model. Putting this statement at the top of your program will export r-squared to a table: ods output RSQUARE=rsqvalue; There are a variety of things you can export with ODS tables and they are summarized here: https://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#statug_logistic_sect049.htm ... View more

Have you tried the LINELENGTH= option in the KEYLEGEND statement? https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/grstatproc/p0xmbppzx71smbn1203aaif96z86.htm#n1qt8b9hqkqwekn1o92urvr1pce8 ... View more

There is a simple way to do this as long as the non-missing values for a particular UniqueID in Table 2 ALWAYS match the non-missing values in Table 1 (and if each table only has one row per Unique_ID). This appears to be the case from the data you have shared. E.g., subject JM_909 has the same non-missing values for Var4, Var5, and Var6 in both tables. You might remember that a MERGE in a data set the values in the right-hand table overwrite the values in the left-hand table for the matched observations that are defined with the BY statement. You would first need to sort each data set by Unique_ID and then Data Want; merge Table1 Table2; /*For each value of UNIQUE_ID where the same variable exists in both tables, the value from Table2 will overwrite the value in Table1.*/ by Unique_ID; run; ... View more

Have you looked into using the counting process when you have data with more than one row per subject? Look at p. 2595 of the documentation: http://www.math.wpi.edu/saspdf/stat/chap49.pdf Using the counting process would involve change the structure of your data somewhat to be able to write the model statement (that is, you need to specify the beginning and end points of the interval). ... View more

If you are using SAS 9.4, you can use code like this in open code, but you need to use %if/%if%then syntax when you are using conditional logic with macro variables. ... View more