I am using the "patients" example dataset from SAS. In SAS EM I have set this data up as a data source. The variable HR (heart rate) is set up as Interval variable. I ran the node and checked the Exported data and it is VAR type (see Image1). Note, numerical summary such as Min, Max, and Mean are displayed.
Next, I connected a StatExplore to the data node and ran it. The results show the node is treating HR as a Class variable. See Image2. Why is HR, an interval variable, suddenly being treated as a Nominal variable? I tried to figure out what was going on. I checked the Import data to the StatNode and HR is shown as a VAR type node, see Image3, not CLASS. Then I checked the Variables ellipses of the StatExplore node and here HR is shown as a Nominal variable -- Image4.
To summarize, when I created the data source HR is set as Interval variable. It is exported from the data node as VAR type as opposed to CLASS. The imported data at the StatExplore node shows HR is still VAR, not CLASS. Yet, the Variable ellipses shows HR to be nominal and the StatExplore node also treats HR as Nominal.
Would someone explain to me what I am missing? Thank you.
best regards, Dileep
When you are viewing the Sample Statistics of the imported or exported data, the type "CLASS" and "VAR" is solely based on whether the variable is character or numeric. But the level of the variable (Nominal or Interval e.g.) if you have used the Advanced Advisor in the Input Data node, is determined by the number of distinct levels of the variable. So by default, if a variable has fewer than 20 levels even if it is numeric, its level will be Nominal and it will be treated as a class variable in the nodes.
When you are viewing the Sample Statistics of the imported or exported data, the type "CLASS" and "VAR" is solely based on whether the variable is character or numeric. But the level of the variable (Nominal or Interval e.g.) if you have used the Advanced Advisor in the Input Data node, is determined by the number of distinct levels of the variable. So by default, if a variable has fewer than 20 levels even if it is numeric, its level will be Nominal and it will be treated as a class variable in the nodes.
SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!
Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.
Find more tutorials on the SAS Users YouTube channel.