specificity: specificity

In InformationValue: Performance Analysis and Companion Functions for Binary Classification Models

Description

Calculate the specificity for a given logit model.

Usage

specificity(actuals, predictedScores, threshold = 0.5)

Arguments

actuals	The actual binary flags for the response variable. It can take a numeric vector containing values of either 1 or 0, where 1 represents the 'Good' or 'Events' while 0 represents 'Bad' or 'Non-Events'.
predictedScores	The prediction probability scores for each observation. If your classification model gives the 1/0 predcitions, convert it to a numeric vector of 1's and 0's.
threshold	If predicted value is above the threshold, it will be considered as an event (1), else it will be a non-event (0). Defaults to 0.5.

Details

For a given given binary response actuals and predicted probability scores, specificity is defined as number of observations without the event AND predicted to not have the event divided by the number of observations without the event. Specificity is particularly useful when you are extra careful not to predict a non event as an event, like in spam detection where you dont want to classify a genuine mail as spam(event) where it may be somewhat ok to occasionally classify a spam as a genuine mail(a non-event).

Value

The specificity of the given binary response actuals and predicted probability scores, which is, the number of observations without the event AND predicted to not have the event divided by the nummber of observations without the event.

Author(s)

Selva Prabhakaran [e-mail]

Examples

data('ActualsAndScores')
specificity(actuals=ActualsAndScores$Actuals, predictedScores=ActualsAndScores$PredictedScores)

InformationValue documentation built on May 1, 2019, 9:12 p.m.