Numerical Methods for Estimation and Inference in Bayesian Var-Models

Kadiyala, K. Rao; Karlsson, Sune

doi:10.1002/(sici)1099-1255(199703)12:2<99::aid-jae429>3.0.co;2-a

Cited by 478 publications

(373 citation statements)

References 25 publications

(31 reference statements)

Supporting

Mentioning

359

Contrasting

Unclassified

Order By: Relevance

“…, ψ mk ) and conditional on H, the corresponding hyperparameters carry no additional information. The posterior mean α and variance V α take standard forms (Kadiyala et al, 1997;Karlsson, 2013),…”

Section: Posterior Distributionsmentioning

confidence: 99%

Adaptive Shrinkage in Bayesian Vector Autoregressive Models

Huber

Feldkircher

2017

Journal of Business & Economic Statistics

101

105

View full text Add to dashboard Cite

Vector autoregressive (VAR) models are frequently used for forecasting and impulse response analysis. For both applications, shrinkage priors can help improving inference. In this paper we derive the shrinkage prior of Griffin et al. (2010) for the VAR case and its relevant conditional posterior distributions. This framework imposes a set of normally distributed priors on the autoregressive coefficients and the covariances of the VAR along with Gamma priors on a set of local and global prior scaling parameters. This prior setup is then generalized by introducing another layer of shrinkage with scaling parameters that push certain regions of the parameter space to zero. A simulation exercise shows that the proposed framework yields more precise estimates of the model parameters and impulse response functions. In addition, a forecasting exercise applied to US data shows that the proposed prior outperforms other specifications in terms of point and density predictions.

show abstract

Section: Posterior Distributionsmentioning

confidence: 99%

Adaptive Shrinkage in Bayesian Vector Autoregressive Models

Huber

Feldkircher

2017

Journal of Business & Economic Statistics

101

105

View full text Add to dashboard Cite

show abstract

“…Several priors have been used in the econometrics literature to estimate the Bayesian VAR models, including Minnesota prior and NormalWishart prior (e.g., Banbura, Giannone and Reichlin 2010;Ciccarelli and Rebucci 2003;Kadiyala and Karlsson 1997;Sims and Zha 1998). Recently, Banbura, Giannone and Reichlin (2010), using more than 100 variables, showed that the Minnesota prior leads to improved forecasting performance compared to factor models.…”

Section: Bayesian Vector Autoregressive Modelsmentioning

confidence: 99%

The impact of brand familiarity on online and offline media synergy

Pauwels

Demirci

Yıldırım

et al. 2016

International Journal of Research in Marketing

View full text Add to dashboard Cite

Rooted in the Integrated Marketing Communication framework, this paper conceptualizes how brand familiarity affects online and cross-channel synergies. The empirical analysis uses Bayesian Vector Autoregressive models to estimate long-term elasticities for four brands. The authors distinguish customer-initiated communication (typically online) from firm-initiated communication (typically offline). Their results indicate that within-online synergy is higher than online-offline synergy for both familiar brands but not for both unfamiliar brands. Managers of unfamiliar brands may obtain substantial synergy from offline marketing spending, even though its direct elasticity pales in comparison with that of online media while managers of familiar brands can generate more synergy by investing in different online media.

show abstract

“…In work nµ is 3 (that is two (2) time series variables plus 1(one)). Our choice of Normal-Inverse Wishart prior for the BVAR models follow the work of Kadiyala & Karlsson, [17] that Normal Wishart prior tends to performed better when compared to other priors. In addition Sims and Zha, [12] proposed Normal-Inverse Wishart prior because of its suitability for large systems while Breheny, [18] reported that the most advantage of wishart distribution is that it guaranteed to produce positive definite draws.…”

Section: Model Specificationmentioning

confidence: 99%