Journal
SCIENCE ADVANCES
Volume 8, Issue 42, Pages -Publisher
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/sciadv.abn9450
Keywords
-
Categories
Funding
- European Commission (Marie Sklodowska-Curie Global Fellowship) [W911NF-18-1-0325]
- Microsoft Corporation
- Army Research Office [CCF1917819]
- NSF
- C3.ai Inc.
- [792178]
Ask authors/readers for more resources
Mathematical models are becoming more detailed for better predictions and insights, even without validation or training data. However, this practice can lead to fuzzier estimates as it increases the effective dimensions of the model.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available