Inherent Complexity: a problem for Statistical Model Evaluation

Publication Year:
2016
Usage 127
Downloads 127
Repository URL:
http://philsci-archive.pitt.edu/id/eprint/12570
Author(s):
Romeijn, Jan-Willem
conference paper description
This paper investigates a problem for statistical model evaluation, in particular for curve fitting: by employing a different family of curves we can fit a scatter plot almost perfectly at apparently minor costs in terms of model complexity. The problem is resolved by an appeal to prior probabilities. This leads to some general lessons about how to approach model evaluation.