Models with higher effective dimensions tend to produce more uncertain estimates

HIGHLIGHTS

SUMMARY

Puy et_al, Sci. The authors show that modelers can gauge the connection between model complexity and uncertainty at all stages of model development by calculating the model`s "effective dimensions," that is, the number of influential parameters and active higher-order effects. The authors then illustrate how the concept of effective dimensions can help modelers balance model complexity with uncertainty using several increasingly complex models of the energy, agriculture, and epidemiology domain. Such breakthroughs have allowed the simple general circulation models of the 1960s to evolve into comprehensive atmosphere-ocean general circulation models, or . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or E-mail:

If you don't have an account, you can create one here.