Difference between revisions of "Information Statistic"

From Open Risk Manual
Line 4: Line 4:
 
== Formula ==
 
== Formula ==
 
:<math>
 
:<math>
I = \sum_i ( p_b(S_i) − p_g(S_i) ) \log( \frac{ p_b(S_i) } { p_g(S_i) } )
+
I = \Sum_i ( p_b(S_i) − p_g(S_i) ) \log( \frac{ p_b(S_i) } { p_g(S_i) } )
 
</math>
 
</math>
  

Revision as of 17:31, 17 February 2022

Definition

Information Statistic (also Information Value) is a metric of the strength of a characteristic to separate a binary classification problem (such as good/bad classification in Credit Scoring).

Formula

Failed to parse (unknown function "\Sum"): I = \Sum_i ( p_b(S_i) − p_g(S_i) ) \log( \frac{ p_b(S_i) } { p_g(S_i) } )

where

  • S_i is the value of the i-th class
  • p_b(S_i) is the probability (fraction) of bads for value class i
  • p_g(S_i) is the probability (fraction) of goods for value class i