Which statement best describes data type requirements for independent variables in a decision tree?

• A. Only numeric types are allowed
• B. Only categorical types are allowed
• C. Any of the above types can be used
• D. No types are allowed

Answer: (C)

Decision trees work with both numeric and categorical predictors. For numeric features, the tree finds a threshold to split the data (e.g., values less than or greater than a cutoff). For categorical features, it partitions data by categories or groups of categories, depending on the algorithm. Because a tree can split on either type, any of these data types can be used for independent variables. In practice, some implementations may require encoding of categoricals, but the underlying variable types themselves can be numeric or categorical.