Abstract
In 1980ies Bayesian ARX models became an important instrument in economic forecasting (see e.g. Litterman 1986). This so-called Minnesota or Litterman prior consists of a hierarchical tightness structure, where 2 hyperparameters have to be specified by the user: λ, which controls the tightness of the own past of a time series and θ which controls the tightness of the past of all other time series. The ARX model for the multivariate time series {(y 1t ,…,y kt ), t = 1,…,T} explains one time series by the own history and the present and the past of the other time series. The ARX model we are analyzing consists of the following equations for a T x 1 vector y 1:
with the T x p’ K regressor matrix X = [X 1 : X 2 :…: X K ], where p’ = p + 1. The first T x p’ block X 1 = [1n: y 1,‒1:…: y 1,‒p] consists of the constant and the past of the left hand variable. Each Tx(p+1) block X k represents the current and the past of the time series yk = {y kt } t =1,…,T . Thus, the multiple tightness model with normal errors can be formulated as a linear regression model of the standard form y ~ N(Xb,σ 2 I T ), and b = vecB = (b 1:…: b K ) is the stacked coefficient vector for K time series responses, where B is a p’ x K coefficient matrix. Note that all the K columns of B are b’ k = (b 0k , b 1k ,…, b pk ), k = 1,…, K. The first row of B, i.e. α’ = (b 01 , b 02 ,…, b 0K ) contains the constant b01, and all other contemporaneous coefficients starting with the response of y 2 on y 1.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Gelfand, A.E., Smith, A.F.M.: Sampling based approaches to calculating marginal densities. JASA 85 (1990) 398–409
Littermann, R.B.: A statistical approach to economic forecasting J. of Business and Ec. Stat. 4 (1986) 1–24
Polasek, W.: Gibbs sampling in VAR models with smoothness prior. mimeo, University of Basel (1994)
Polasek, W., Jin, S.: Gibbs sampling in AR models with random walk prior. mimeo, University of Basel (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Polasek, W., Jin, S. (1996). Gibbs Sampling in ARX Models with the “Minnesota” Prior. In: Kleinschmidt, P., Bachem, A., Derigs, U., Fischer, D., Leopold-Wildburger, U., Möhring, R. (eds) Operations Research Proceedings 1995. Operations Research Proceedings, vol 1995. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-80117-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-80117-4_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60806-6
Online ISBN: 978-3-642-80117-4
eBook Packages: Springer Book Archive