A Mass-Shifting Phenomenon of Truncated Multivariate Normal Priors
From MaRDI portal
Publication:6154016
Abstract: We show that lower-dimensional marginal densities of dependent zero-mean normal distributions truncated to the positive orthant exhibit a mass-shifting phenomenon. Despite the truncated multivariate normal density having a mode at the origin, the marginal density assigns increasingly small mass near the origin as the dimension increases. The phenomenon accentuates with stronger correlation between the random variables. A precise quantification characterizing the role of the dimension as well as the dependence is provided. This surprising behavior has serious implications towards Bayesian constrained estimation and inference, where the prior, in addition to having a full support, is required to assign a substantial probability near the origin to capture at parts of the true function of interest. Without further modification, we show that truncated normal priors are not suitable for modeling at regions and propose a novel alternative strategy based on shrinking the coordinates using a multiplicative scale parameter. The proposed shrinkage prior is empirically shown to guard against the mass shifting phenomenon while retaining computational efficiency.
Cites work
- A variable selection approach to monotonic regression with Bernstein polynomials
- Approximating the inverse of banded matrices by banded matrices with applications to probability and statistics
- Asymptotic Statistics
- BART: Bayesian additive regression trees
- Bayesian analysis of shape-restricted functions using Gaussian process priors
- Bayesian constraint relaxation
- Bayesian estimation and inference for generalised partial linear models using shape-restricted splines
- Bayesian Isotonic Regression and Trend Analysis
- Bayesian linear regression with sparse priors
- Bayesian monotone regression using Gaussian process projection
- Bayesian Multivariate Isotonic Regression Splines
- Bayesian Nonparametric Estimation of Continuous Monotone Functions with Applications to Dose–Response Analysis
- Bayesian Semiparametric Isotonic Regression for Count Data
- Bayesian sparse multiple regression for simultaneous rank reduction and variable selection
- Bayesian variable selection with shrinking and diffusing priors
- Concentration inequalities. A nonasymptotic theory of independence
- Concentration of measure and isoperimetric inequalities in product spaces
- Contraction properties of shrinkage priors in logistic regression
- Convergence rates for Bayesian estimation and testing in monotone regression
- Convergence rates of posterior distributions.
- Efficient Bayesian shape-restricted function estimation with constrained Gaussian process priors
- Gaussian process emulators for computer experiments with inequality constraints
- Needles and straw in a haystack: posterior concentration for possibly sparse sequences
- Nonparametric function estimation subject to monotonicity, convexity and other shape constraints
- On estimation of isotonic piecewise constant signals
- On risk bounds in isotonic and other shape restricted regression problems
- On the half-Cauchy prior for a global scale parameter
- One-dimensional marginal density functions of a truncated multivariate normal density function
- Posterior contraction in sparse Bayesian factor models for massive covariance matrices
- Reference priors with partial information
- Regularized estimation of large covariance matrices
- Spike-and-Slab Group Lassos for Grouped Regression and Sparse Generalized Additive Models
- Stable signal recovery from incomplete and inaccurate measurements
- Sub-optimality of some continuous shrinkage priors
- Supremum norm posterior contraction and credible sets for nonparametric multivariate regression
- The horseshoe estimator for sparse signals
- The multivariate skew-normal distribution
- The normal law under linear restrictions: simulation and estimation via minimax tilting
Cited in
(4)
This page was built for publication: A Mass-Shifting Phenomenon of Truncated Multivariate Normal Priors
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6154016)
