Forecasting with Medium and Large Bayesian VARs

By Gary Koop. 2013

408 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/0892cec21405630e010c0246e644fff93e5023e4

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): “We refer the reader to Raftery et al. (2010) for the initial proposal of DMA, Koop and Korobilis (2012) for the application of the method to forecasting inflation, and Nonejad (2021) for a recent review of the methodology, with a focus on applications in economics and finance.10”
Prior Selection for Vector Autoregressions (2015, positive): “In the context of VARs, for example, Litterman (1980) and Doan, Litterman, and Sims (1984) set the tightness of the prior by maximizing the out-of-sample forecasting performance of the model.”
Bayesian VARs : specification choices and forecast accuracy (2011, positive): “In light of recent evidence on the success of larger models relative to smaller ones and interest in large datasets (e.g. Banbura et al., 2010; Koop, 2013), we focus on mid-size models applied to monthly data: 18-variable BVARs for US macroeconomic and financial data.”
Measuring Uncertainty and Its Impact on the Economy (2016, neutral): “…of the information set matters and can reduce forecast errors and their volatility, even though there is a debate on how large “large” is; studies such as Koop (2013) and Carriero, Clark and Marcellino (2015) suggest that about 20 selected macroeconomic and ﬁnancial variables could be suﬃcient.”
High‐dimensional macroeconomic forecasting and variable selection via penalized regression (2019, methodology): “A Bayesian VAR in high dimension is investigated by Banbura, Giannone and Reichlin (2010), Koop (2013) and Gefang (2014). Kock (2016) considers adaptive lasso in not only stationary but also nonstationary autoregressions.”
Large time-varying parameter VARs (2013, methodology): “β0 and possibly Σ0 and Q0) and a prior for any remaining parameters of the model, then Bayesian statistical inference can proceed in a straightforward fashion (see, for instance, Koop and Korobilis (2009) for a textbook-level treatment) using MCMC methods.”
Adaptive Shrinkage in Bayesian Vector Autoregressive Models (2019, background): “Another strand of the literature proposes double exponential priors on the coefficients, leading to the Bayesian variant of the LASSO (Park and Casella 2008). Gefang (2014) proposed a Bayesian LASSO for VAR models, showing that forecast results tend to be similar to the ones obtained from standard M”
Reducing the state space dimension in a large TVP-VAR (2020, methodology): “They (and other authors such as Carriero, Kapetanios and Marcellino (2011), Giannone, Lenza, Momferatou and Onorante (2014), Koop (2013) and Koop and Korobilis (2013)), point out that forecasts, policy advice and analysis of structure suffer problems resulting from omitted variable bias from using t”
Common Drifting Volatility in Large Bayesian VARs (2012, positive): “Finally, by comparing the BVAR results in Tables 6 and 7, it is clear that the use of the larger dataset generally improves the density forecasts, a result in line with Carriero, Clark, and Marcellino (2013), Giannone, Lenza, and Primiceri (2015), and Koop (2013).”
Conditional Forecasts and Scenario Analysis with Vector Autoregressions for Large Cross-Sections (2015, neutral): “1See e.g. Koop (2013), Giannone, Lenza, Momferatou, and Onorante (2013), Giannone, Lenza, and Reichlin (2012), Paciello (2011).”
Macroeconomic forecast accuracy in a data‐rich environment (2019, neutral): “See (Banbura, Giannone & Reichlin 2010), (Koop 2013), (Carriero, Clark & Marcellino 2015) and (Giannone, Lenza & Primiceri 2015), among others.”
Reconciling Output Gaps: Unobserved Components Model and Hodrick-Prescott Filter (2017, background): “Many recent papers, including Carriero, Kapetanios, and Marcellino (2009), Banbura, Giannone, and Reichlin (2010) and Koop (2013), have demonstrated the gains of incorporating the information content in a large number of macroeconomic variables.”
Bayesian Model Comparison for Time-Varying Parameter VARs with Stochastic Volatility (2018, positive): “In particular, one can consider a constant coefficients VAR with constant impact matrix and shrinkage priors as in Banbura et al. (2010) and Koop (2013), but extend the diagonal covariance matrix to allow for stochastic volatility; see Carriero et al. (2016) for such a modeling approach.”
Now-Casting and the Real-time Data Flow (2013, positive): “Either the forecasts from many smaller systems could be combined or Bayesian shrinkage could be employed to avoid over-fitting in a large system, see Bańbura, Giannone, and Reichlin (2010), Giannone, Lenza, and Primiceri (2012) or Koop (2013) (see also Karlsson, 2012).”