Kepler versus Akaike

TL;DR

This paper explains the Akaike Information Criterion using Earth's orbit as an example and clarifies that it does not inherently favor simpler models over complex ones.

Contribution

It clarifies the misconception about the Akaike criterion's model selection bias using a clear illustrative example.

Findings

AIC is based on information theory principles.

AIC does not automatically discard complex models.

Earth's orbit example demonstrates AIC's decision process.

Abstract

I use the example of the Earth's orbit to illustrate the principle behind the Akaike Information Criterion, and refute the misconception that the criterion, by definition, discards more complex models in favour of simpler ones.