Fast and Flexible Bayesian Inference in Time-varying Parameter Regression Models

Hauzenberger, Niko; Huber, Florian; Koop, Gary; Onorante, Luca

doi:10.1080/07350015.2021.1990772

Cited by 25 publications

(22 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been an explosion of interest in carrying out structural analysis and forecasting with time-varying parameter (TVP) regressions and Vector Autoregressions (TVP-VARs) in recent years, with many of the papers employing Bayesian methods. An incomplete survey of significant recent Bayesian contributions includes Cogley and Sargent (2005), Primiceri (2005), Chan et al (2012), Dangl and Halling (2012), Koop and Korobilis (2012), Korobilis (2013), D'Agostino et al (2013), Groen et al (2013), Nakajima and West (2013), Belmonte et al (2014), Kalli and Griffin (2014), Feldkircher et al (2017), Kowal et al (2017), Uribe and Lopes (2017), Koop and Korobilis (2018), Ročková and McAlinn (2018), Bitto and Frühwirth-Schnatter (2019), Hauzenberger et al (2019), Korobilis (2019), Paul (2019) and Huber et al (forthcoming).…”

Section: Introductionmentioning

confidence: 99%

Bayesian Inference in High-Dimensional Time-varying Parameter Models using Integrated Rotated Gaussian Approximations

Huber,

Koop,

Pfarrhofer

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Researchers increasingly wish to estimate time-varying parameter (TVP) regressions which involve a large number of explanatory variables. Including prior information to mitigate over-parameterization concerns has led to many using Bayesian methods. However, Bayesian Markov Chain Monte Carlo (MCMC) methods can be very computationally demanding. In this paper, we develop computationally efficient Bayesian methods for estimating TVP models using an integrated rotated Gaussian approximation (IRGA). This exploits the fact that whereas constant coefficients on regressors are often important, most of the TVPs are often unimportant. Since Gaussian distributions are invariant to rotations we can split the the posterior into two parts: one involving the constant coefficients, the other involving the TVPs. Approximate methods are used on the latter and, conditional on these, the former are estimated with precision using MCMC methods. In empirical exercises involving artificial data and a large macroeconomic data set, we show the accuracy and computational benefits of IRGA methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Bayesian Inference in High-Dimensional Time-varying Parameter Models using Integrated Rotated Gaussian Approximations

Huber,

Koop,

Pfarrhofer

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The resulting model can be interpreted as a regime switching model with an unknown number of regimes and a diagonal transition probability matrix. This specification is closely related to the TVP regression model developed in Hauzenberger et al (2022), which uses sparse finite mixtures to model the time variation in the coefficients.…”

Section: How Bart Can Approximate Tvps: An Illustrationmentioning

confidence: 99%

“…Structural break models, Markov switching models (see Sims and Zha, 2006), and time-varying parameter (TVP) models are some prominent examples. TVP regressions and TVP-VARs, in particular, have been highly successful for structural macroeconomic analysis and forecasting (see, for example, Dangl and Halling, 2012;D'Agostino et al, 2013;Koop and Korobilis, 2013;Belmonte et al, 2014;Bitto and Frühwirth-Schnatter, 2019;Korobilis, 2021;Huber et al, 2021;Hauzenberger et al, 2022). In the TVP-VAR literature, parameters are assumed to evolve according to random walks or autoregressive processes.…”

Section: Introductionmentioning

confidence: 99%

Bayesian modeling of time-varying parameters using regression trees

Hauzenberger

Huber

Koop

et al. 2023

Working Paper (Federal Reserve Bank of Cleveland)

Self Cite

View full text Add to dashboard Cite

In light of widespread evidence of parameter instability in macroeconomic models, many time-varying parameter (TVP) models have been proposed. This paper proposes a nonparametric TVP-VAR model using Bayesian additive regression trees (BART). The novelty of this model stems from the fact that the law of motion driving the parameters is treated nonparametrically. This leads to great flexibility in the nature and extent of parameter change, both in the conditional mean and in the conditional variance. In contrast to other nonparametric and machine learning methods that are black box, inference using our model is straightforward because, in treating the parameters rather than the variables nonparametrically, the model remains conditionally linear in the mean. Parsimony is achieved through adopting nonparametric factor structures and use of shrinkage priors. In an application to US macroeconomic data, we illustrate the use of our model in tracking both the evolving nature of the Phillips curve and how the effects of business cycle shocks on inflationary measures vary nonlinearly with movements in uncertainty.

show abstract

“…Fortunately, there exist algorithms which allow us to avoid computing Cholesky factors altogether. The algorithm we use is based on Cong, Chen, and Zhou (2017), which has recently been applied to economic data in Hauzenberger, et al (2021).…”

Section: Fast Sampling Using Singular Value Decompositionsmentioning

confidence: 99%

Forecasting euro area inflation using a huge panel of survey expectations

Huber¹,

Onorante²,

Pfarrhofer³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we forecast euro area inflation and its main components using an econometric model which exploits a massive number of time series on survey expectations for the European Commission's Business and Consumer Survey.To make estimation of such a huge model tractable, we use recent advances in computational statistics to carry out posterior simulation and inference. Our findings suggest that the inclusion of a wide range of firms and consumers' opinions about future economic developments offers useful information to forecast prices and assess tail risks to inflation. These predictive improvements do not only arise from surveys related to expected inflation but also from other questions related to the general economic environment. Finally, we find that firms' expectations about the future seem to have more predictive content than consumer expectations.

show abstract

Fast and Flexible Bayesian Inference in Time-varying Parameter Regression Models

Cited by 25 publications

References 65 publications

Bayesian Inference in High-Dimensional Time-varying Parameter Models using Integrated Rotated Gaussian Approximations

Bayesian Inference in High-Dimensional Time-varying Parameter Models using Integrated Rotated Gaussian Approximations

Bayesian modeling of time-varying parameters using regression trees

Forecasting euro area inflation using a huge panel of survey expectations

Contact Info

Product

Resources

About