Bayesian VARs : specification choices and forecast accuracy

By Andrea Carriero, Todd E. Clark, Massimiliano Marcellino. 2011

265 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/0ed2152ed4f19c0056458c920893ada40a4d7d99

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 Management Science and Operations Research

Citations in the corpus

Bayesian forecasting in economics and finance: A modern review (2022, methodology): “As a remedy, Carriero et al. (2016) propose a simple common stochastic volatility (CSV) specification that assumes the shock variances to be driven by a single common volatility factor, maintaining conjugacy and thus leading to computationally efficient MCMC algorithms. They acknowledge that this mo”
Adaptive Shrinkage in Bayesian Vector Autoregressive Models (2019, methodology): “Most prominently, Litterman (1979, 1986) and Doan et al. (1984) advocate a set of prior distributions that center the whole system on a multivariate random walk process.”
Forecasting with Bayesian Vector Autoregression (2013, unknown): “Carriero et al. (2012) considers two different trading strategies.”
Common Drifting Volatility in Large Bayesian VARs (2012, unknown): “2 and ε = 1000, and we set the scale parameters σ(2)i at estimates of residual variances from AR(4) models from the estimation sample.”
Large time-varying parameter VARs (2013, methodology): “Following, e.g., Stock andWatson (2008) and recommendations in Carriero et al. (2011) we transform all variables to stationarity.”
Energy Markets and Global Economic Conditions (2020, methodology): “To ensure their reliability, we evaluate the joint performance of the density forecasts for price and consumption by computing the log predictive score as in Carriero et al. (2015). The average log score is negative and a less negative value indicates that the model provides a better characterizatio”
Bayesian nonparametric vector autoregressive models (2018, unknown): “Hansen (1992), Chib (1996), Chauvet (1998), Kim and Nelson (1999), Kim et al. (2005), and Sims and Zha (2006).”
Prior Selection for Vector Autoregressions (2015, unknown): “We consider a combination of the conjugate priors most commonly used in the literature (the Minnesota, sum-of-coefficients, and dummy-initial-observation priors), and document that this estimation strategy generates accurate out-of-sample predictions in terms of both point and density forecasts.”
A quasi-Bayesian local likelihood approach to time varying parameter VAR models (2019, background): “To this end, Carriero et al. (2012, 2015) maximise the marginal likelihood of the data, given by p(Y ) = Z Z p(Y j ;R)p( jR)p(R)d dR over a ne grid of points for the overall prior tightness (or the lag order).”