domir-package {domir}R Documentation

Tools to Support Relative Importance Analysis

Description

Methods to apply dominance analysis-based relative importance analysis for predictive modeling functions.

Details

This package supports relative importance analysis by implementing several functions that compute dominance analysis (Azen & Budescu, 2004; Budescu, 1993). Dominance analysis produces the well-known Shapley value decomposition (e.g., Grömping, 2007; Lipovetsky & Conklin, 2001) as one of its methods called general dominance statistics.

Dominance analysis is a method for determining the relative importance of inputs (i.e., independent variables, predictors, features, parameter estimates) to a predictive model that evaluates how a returned value, such as a model fit metric or statistic, is associated with each input. It is also a common, and generally well accepted, method for determining the relative importance of inputs to predictive models that is effective at separating the effects of correlated inputs.

Author(s)

Joseph Luchman jluchman@gmail.com

References


[Package domir version 1.1.1 Index]