TSINFO Procedure

When a data table contains a time ID variable that has corrupted, missing, or duplicate values, PROC TSINFO can help isolate and identify these problematic observations. For larger data tables whose quality is unknown, it can be useful to get a general overview of the relative number of observations that have problematic time ID values. When prior knowledge of the time interval that separates observations is incomplete, PROC TSINFO can be used to infer the interval.

The following example uses the Sashelp.Air data set to illustrate how to analyze some time series information. The following DATA step loads the Air data set from the Sashelp directory to a table named mylib.air in your CAS session. This DATA step assumes that your CAS engine libref is named mylib, but you can substitute any appropriately defined CAS engine libref.

data mylib.air(replace=yes);
   set sashelp.air;
   do class=1 to 10;
      output;
   end;
run;

The following statements use the TSINFO procedure to infer the interval of the time series:

proc tsinfo data=mylib.air outintervaldetails=mylib.interval1
            nthreads=2;
   id date align=BEGIN;
   by class;
run;

PROC TSINFO requires the following inputs: