Bayesian Approaches to Shrinkage and Sparse Estimation

Korobilis, Dimitris; Shimizu, K.

doi:10.2139/ssrn.3971832

Cited by 2 publications

(1 citation statement)

References 196 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Bayesian LASSO places priors on the regression coefficients which is shown to be equivalent to the frequentist version of the LASSO estimator. In a recent paper, (Korobilis & Shimizu, 2021) illustrate Bayesian approaches to shrinkage and sparse estimation. This paper surveys modern shrinkage and variable selection algorithms and methodologies and compares different types of priors and their associated costs and benefits.…”

Section: Econometric Techniquementioning

confidence: 99%

What are the determinants of financial well‐being? A Bayesian LASSO approach

Lacombe

Khatun

2022

American J Econ Sociol

View full text Add to dashboard Cite

The financial well-being (FWB) of individuals is a topic that is becoming increasingly important across a multitude of disciplines. In this study, we use the 2016 National Financial Well-Being Survey administered by the Consumer Financial Protection Bureau to assess the determinants of an individual's FWB. We identify 144 potential covariates that could explain variation in the FWB score of individuals. The statistical methodology of choice is the Bayesian LASSO, which is a covariate selection algorithm that also allows for the importance ranking of covariates. Out of the 144 potential covariates, we find that 26 have 95% credible intervals that do not contain zero. Broadly speaking, the results show that objective measures of financial competency and psychological and sociological factors contribute the bulk of the explanatory power that help explain an individual's FWB score.

show abstract

Section: Econometric Techniquementioning

confidence: 99%

What are the determinants of financial well‐being? A Bayesian LASSO approach

Lacombe

Khatun

2022

American J Econ Sociol

View full text Add to dashboard Cite

show abstract

Bayesian Dynamic Variable Selection in High Dimensions

Korobilis

Koop

2023

Int Economic Review

Self Cite

View full text Add to dashboard Cite

This article addresses the issue of inference in time-varying parameter regression models in the presence of many predictors and develops a novel dynamic variable selection strategy. The proposed variational Bayes dynamic variable selection algorithm allows for assessing at each time period in the sample which predictors are relevant (or not) for forecasting the dependent variable. The algorithm is used to forecast inflation using over 400 macroeconomic, financial, and global predictors, many of which are potentially irrelevant or short-lived. The new methodology is able to ensure parsimonious solutions to this high-dimensional estimation problem, which translate into excellent forecast performance.

show abstract

Bayesian Approaches to Shrinkage and Sparse Estimation

Cited by 2 publications

References 196 publications

What are the determinants of financial well‐being? A Bayesian LASSO approach

What are the determinants of financial well‐being? A Bayesian LASSO approach

Bayesian Dynamic Variable Selection in High Dimensions

Contact Info

Product

Resources

About