EconBase
← All papers

The Dynamic Triple Gamma Prior as a Shrinkage Process Prior for Time-Varying Parameter Models

Peter Knaus, Sylvia Frühwirth-Schnatter

arXiv 16 Dec 2023 · Econometrics · 1 citations (OpenAlex)

arXiv:2312.10487 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Many existing shrinkage approaches for time-varying parameter (TVP) models assume constant innovation variances across time points, inducing sparsity by shrinking these variances toward zero. However, this assumption falls short when states exhibit large jumps or structural changes, as often seen in empirical time series analysis. To address this, we propose the dynamic triple gamma prior -- a stochastic process that induces time-dependent shrinkage by modeling dependence among innovations while retaining a well-known triple gamma marginal distribution. This framework encompasses various special and limiting cases, including the horseshoe shrinkage prior, making it highly flexible. We derive key properties of the dynamic triple gamma that highlight its dynamic shrinkage behavior and develop an efficient Markov chain Monte Carlo algorithm for posterior sampling. The proposed approach is evaluated through sparse covariance modeling and forecasting of the returns of the EURO STOXX 50 index, demonstrating favorable forecasting performance.

Citation extraction

32
references
60
in-text mentions
32
distinct cited
2
self-citations
11,116
main-text words

appendix boundary found by appendix_command · 58% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Kowal, D. R., D. S. Matteson, and D. Ruppert (2019) Dynamic shrinkage processes1.00093100%
2Cadonna, A., S. Frühwirth-Schnatter, and P. Knaus (2020) Triple the gamma – A unifying shrinkage prior for variance and variable selection in sparse state space and TVP models0.92810780%
3Bitto, A. and S. Frühwirth-Schnatter (2019) Achieving shrinkage in a time-varying parameter model framework0.8434375%
4Kalli, M. and J. E. Griffin (2014) Time-varying sparsity in dynamic regression models0.73732100%
5Gourieroux, C. and J. Jasiak (2006) Autoregressive gamma processes0.6443267%
6Carvalho, C. M., N. G. Polson, and J. G. Scott (2010) The horseshoe estimator for sparse signals0.64422100%
7Frühwirth-Schnatter, S. and H. Wagner (2010) Stochastic model specification search for Gaussian and partially non-Gaussian state space models0.64422100%
8Kastner, G. and S. Frühwirth-Schnatter (2014) Ancillarity-sufficiency interweaving strategy (ASIS) for boosting MCMC estimation of stochastic volatility models0.5853333%
9Frühwirth-Schnatter, S (2006) Finite Mixture and Markov Switching Models0.40511100%
10George, E. I. and R. McCulloch (1993) Variable selection via Gibbs sampling0.40511100%

Showing the top 10 of 32 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1A New Perspective of the Meese-Rogoff Puzzle: Application of Sparse Dynamic Shrinkage0.40511
2Flexible Bayesian Models for Time-Varying Income Distributions0.40511