Dynamic shrinkage processes
From MaRDI portal
Abstract: We propose a novel class of dynamic shrinkage processes for Bayesian time series and regression analysis. Building upon a global-local framework of prior construction, in which continuous scale mixtures of Gaussian distributions are employed for both desirable shrinkage properties and computational tractability, we model dependence among the local scale parameters. The resulting processes inherit the desirable shrinkage behavior of popular global-local priors, such as the horseshoe prior, but provide additional localized adaptivity, which is important for modeling time series data or regression functions with local features. We construct a computationally efficient Gibbs sampling algorithm based on a P'olya-Gamma scale mixture representation of the proposed process. Using dynamic shrinkage processes, we develop a Bayesian trend filtering model that produces more accurate estimates and tighter posterior credible intervals than competing methods, and apply the model for irregular curve-fitting of minute-by-minute Twitter CPU usage data. In addition, we develop an adaptive time-varying parameter regression model to assess the efficacy of the Fama-French five-factor asset pricing model with momentum added as a sixth factor. Our dynamic analysis of manufacturing and healthcare industry data shows that with the exception of the market risk, no other risk factors are significant except for brief periods.
Recommendations
Cited in
(43)- Dynamic regression models for time-ordered functional data
- Dynamic variable selection with spike-and-slab process priors
- Modeling tail risks of inflation using unobserved component quantile regressions
- A Bayesian model of dose-response for cancer drug studies
- Parsimony inducing priors for large scale state-space models
- Horseshoe shrinkage methods for Bayesian fusion estimation
- A unified view on Bayesian varying coefficient models
- Lasso meets horseshoe: a survey
- Shrinkage strategies in some multiple multi-factor dynamical systems
- scientific article; zbMATH DE number 7370554 (Why is no real title available?)
- Bayesian Function-on-Scalars Regression for High-Dimensional Data
- Bayesian Approaches to Shrinkage and Sparse Estimation
- Local shrinkage rules, Lévy processes and regularized regression
- Horseshoe Regularisation for Machine Learning in Complex and Deep Models1
- BAYESIAN DYNAMIC VARIABLE SELECTION IN HIGH DIMENSIONS
- Fast and locally adaptive Bayesian quantile smoothing using calibrated variational approximations
- Shrinkage with shrunken shoulders: Gibbs sampling shrinkage model posteriors with guaranteed convergence rates
- Bayesian Change Point Detection with Spike-and-Slab Priors
- Bayesian Trend Filtering via Proximal Markov Chain Monte Carlo
- Locally adaptive Bayesian isotonic regression using half shrinkage priors
- Social distancing merely stabilized COVID-19 in the United States
- Time-dependent shrinkage of time-varying parameter regression models
- High-Dimensional Macroeconomic Forecasting Using Message Passing Algorithms
- Modeling basal body temperature data using horseshoe process regression
- Detecting Changes in Covariance via Random Matrix Theory
- Dynamic shrinkage priors for large time-varying parameter regressions using scalable Markov chain Monte Carlo methods
- Logistic-beta processes for dependent random probabilities with beta marginals
- Objective Bayesian trend filtering via adaptive piecewise polynomial regression
- Correction to: dynamic shrinkage processes
- Trend and Variance Adaptive Bayesian Changepoint Analysis and Local Outlier Scoring
- Locally Adaptive Shrinkage Priors for Trends and Breaks in Count Time Series
- Drift versus Shift: Decoupling Trends and Changepoint Analysis
- Dynamic functional variable selection for multimodal mHealth data
- Markov switching multiple-equation tensor regressions
- Locally time-varying parameter regression
- Group inverse-gamma gamma shrinkage for sparse linear models with block-correlated regressors
- Dynamic graphical models with variable selection for effective connectivity
- Flexible Bayesian MIDAS: Time-Variation, Group-Shrinkage and Sparsity
- Dynamic sparsity on dynamic regression models
- Flexible yet sparse Bayesian survival models with time-varying coefficients and unobserved heterogeneity
- Dynamic count models with flexible innovation processes for irregular maritime migration
- Informative co-data learning for high-dimensional Horseshoe regression
- Achieving shrinkage in a time-varying parameter model framework
This page was built for publication: Dynamic shrinkage processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5204364)
