Sentence examples for multiple nonnested models from inspiring English sources

We used information-theoretic model selection procedures that allow comparison of multiple, nonnested models.

Choosing among an array of nonnested models is carried out using a posterior predictive criterion.

In our applications we need to account for both nested and nonnested models.

Conveniently AIC and the BIC can be easily used to compare nested and nonnested models.

Nonnested models were compared using Davidson and MacKinnon's J-test [ 33], which specifies a proxy parameter in an artificial nested model combining the two nonnested models and then tests the proxy parameter.

Sun et al. (2007) implicitly used intersection unions of Vuong's tests to select among three nonnested models.

The Bayesian information criterion selects a model from a collection of possible nonnested models by maximizing the likelihood but with a penalty for higher dimensional models.

While the AIC takes into account the overall fit and the parsimony of the model, the BICadj also allows for the comparison of nonnested models.

Nonnested models are evaluated with parsimony fit indices such as the Akaike Information Criterion and the Bayesian Information Criterion (BIC) where again, lower values indicate better fit.

While the presented test corresponds to Vuong's test for strictly nonnested models, it is also valid for nested models when we adopt penalized likelihood scores (see File S1, for further details).

Third, the CMST tests can be applied to nonnested models of different dimensions and can be readily extended to incorporate a larger number of models by implementing intersection-union tests on a larger number of Vuong's tests.