The weight of models and complexity

This article introduces a way of measuring the intrinsic complexity of models. Unlike complication, complexity is an irreducible indication of the innate characteristics of models. Instead of a reductionist paradigm, complexity should be measured in a holistic way. This article redefines the relationship between models and data, and proposes the concept of the weight of models, that is, how heavy a model is. Based on this concept, this article further defines the complexity of a model to be its ability to distort the space configuration. Three complexity indices are proposed to quantify the extent to which the input space is distorted by a model. It is recognized that there is a lack of widely accepted definition or measure of model complexity. The answer provided by this article is an attempt to move the inquiry a step closer to that goal. (c) 2014 Wiley Periodicals, Inc.