Models with higher effective dimensions tend to produce more uncertain estimates

Arnald Puy*, Pierfrancesco Beneventano, Simon Levin, Samuele Lo Piano, Tomasso Portaluri, Andrea Saltelli

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

39 Downloads (Pure)

Abstract

Mathematical models are getting increasingly detailed to better predict phenomena or gain more accurate insights into the dynamics of a system of interest, even when there are no validation or training data available. Here, we show through ANOVA and statistical theory that this practice promotes fuzzier estimates because it generally increases the model’s effective dimensions, i.e., the number of influential parameters and the weight of high-order interactions. By tracking the evolution of the effective dimensions and the output uncertainty at each model upgrade stage, modelers can better ponder whether the addition of detail truly matches the model’s purpose and the quality of the data fed into it.
Original languageEnglish
Article numbereabn9450
Pages (from-to)eabn9450
Number of pages11
JournalScience Advances
Volume8
Issue number42
DOIs
Publication statusPublished - 19 Oct 2022

ASJC Scopus subject areas

  • General

Fingerprint

Dive into the research topics of 'Models with higher effective dimensions tend to produce more uncertain estimates'. Together they form a unique fingerprint.

Cite this