Model Selection Tests for Nonlinear Dynamic Models

By Doug Rivers, Q. Vuong. 2002

375 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/3eb0033bb5eac4c00600a929039d560a83381990

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

An analysis of global warming in the Alpine region based on nonlinear nonstationary time series models (2012, methodology): “The asymptotic properties of the criteria may be evaluated basing on results of Sin and White (1996), Rivers and Vuong (2002), Marcellino and Rossi (2008) and have been derived, for the case of two regimes, in Theorem 5 of Battaglia and Protopapas (2011).”
Nonparametric likelihood ratio model selection tests between parametric likelihood and moment condition models (2007, methodology): “Our tests extend the likelihood-ratio model selection tests presented previously in Vuong (1989) for two parametric likelihood models and Kitamura (2000) for two moment-based models to the scenario where one model is parametric and the other is moment-based.”
Copulas in Econometrics (2014, methodology): “Full sample comparisons of nonnested, fully parametric, copula-based models can be conducted using the test of Vuong (1989) for i.i.d. data and Rivers & Vuong (2002) for time series data.”
Copula Methods for Forecasting Multivariate Time Series (2013, background): “Rivers and Vuong (2002) show that a simple t-statistic on the di¤erence between the sample averages of the log-likelihoods has the standard Normal distribution under the null hypothesis: p T n L1T ̂1T L2T ̂2T o ̂T d !”
Estimation and model selection of semiparametric copula-based multivariate dynamic models under copula misspecification (2006, result): “Although our testing approach is similar to those in Vuong (1989), Sin and White (1996), Rivers and Vuong (2002), Marcellino (2002) and other work following Vuong (1989), we allow for infinite-dimensional nuisance parameters (marginal distributions) in our model selection criterion.”
Dynamics of Consumer Demand for New Durable Goods (2012, positive): “Rivers and Vuong ð2002Þ derive a test statistic that has a standard normal distribution under the null hypothesis that the two models fit the data equally well ðin this case, in the sense of the GMM objective functionÞ.25 The value of the test statistic is 5.55, which strongly rejects the…”