Using predictive methods to assess observation and measure importance

Abstract

Purpose

This study aims to find suitable replacements for hypothesis testing and variable-importance measures.

Design/methodology/approach

This study explores under-used predictive methods.

Findings

The study's hypothesis testing can and should be replaced by predictive methods. It is the only way to know if models have any value.

Originality/value

This is the first time predictive methods have been used to demonstrate measure and variable importance. Hypothesis testing can never prove the goodness of models. Only predictive methods can.