Angela Bitto (Vienna University of Economics and Business, Institute for Statistics and Mathematics): Time-Varying Parameter Models — Achieving Shrinkage and Variable Selection

The present paper contributes to the literature in two ways. First, we investigate shrinkage for Time-Varying Parameter (TVP) models based on the Normal-Gamma prior which has been introduced by Griffin and Brown (2010) for standard regression models. Our approach extends Belmonte, Koop, and Korobilis (2011) who considered the Bayesian LASSO prior, a special case of the Normal Gamma prior. While both priors reduce the risk of over fitting and increase statistical efficiency, they do not allow for variable selection. Hence, as a second contribution, we follow Frühwirth-Schnatter and Wagner (2010) and consider TVP models with spike-and-slab priors which explicitly incorporate variable selection both with respect to the initial parameters as well as their variances. Following Belmonte et al. (2011) we choose EU area inflation modelling based on the generalized Phillips curve as our application. Comparing the predictive evaluation, the Normal Gamma prior significantly outperforms the Bayesian LASSO prior.

Time-varying parameter model; Hierarchical Shrinkage; Spike-and-slab; Normal-Gamma prior.


M. A. G. Belmonte, G. Koop and D. Korobilis. Hierarchical shrinkage in time varying parameter models. Technical Report, University of Strathclyde, Glasgow; 2011.

J. E. Griffin and P. J. Brown. Inference with normal-gamma prior distributions
in regression problems. Bayesian Analysis 5; 2010; pp. 151-170.

S. Frühwirth-Schnatter and H. Wagner. Stochastic model specification search for Gaussian and
partially non-Gaussian state space models. Journal of Econometrics 154; 2010; pp. 85-100.