Choosing Profiling Statistics

Examples of categorical variables are a person's occupation or the number of inquiries made for borrowers over the last 5 months. Examples of continuous variables are a person's income or the daily temperature of the ocean.

The table details the range of statistics available to profile.

Context	Statistics Column Heading	Description
For all nodes	#T (default)	Total count.
	%T	Percentage of total count.
	W#T	Weighted total count.
	W%T (default)	Weighted percentage of total count.
	#U	Count of Unassigned Records.
	% Missing	Percent of missing values based on the total count for that node.
Continuous variables (numeric, also known as real)	% Missing	Percentage of missing values.
	% Zero	Percentage of zero values.
	Min	Number of minimum values.
	Max	Number of maximum values.
	Mean (default)	Mean value.
	StdDev	Standard deviation.
	Sum	Sum of all values.
Categorical variable (an enum, or a numeric with 10 or fewer unique values) Note In the Profile View, statistics for categorical values are only available for the 10 values with the highest number of counts. Other remaining categorical values appear, but without statistics.	# (Default)	Total number of counts for that node.
	Prob C	Probability of record being correctly assigned to the category.
	W#	Weighted total number of counts for that node.
	%	Percent of counts for that node. The total of all the top level nodes (in that column) equals 100%.
	W%	Weighted percent of counts for that node. The total of all the top level nodes (in that column) equals 100%.
	Rate (Default)	Category rate that lists the weighted percent of counts for each categorical value of that variable. The total of all the categorical values (in that row) for that variable equals 100%.

Note You can verify the data type of a variable in a decision tree by right-clicking its level and selecting Properties to open its Properties dialog box.