Evading the curse of dimensionality in nonparametric density estimation with simplified vine copulas
From MaRDI portal
Publication:93079
DOI10.1016/J.JMVA.2016.07.003zbMATH Open1346.62071arXiv1503.03305OpenAlexW2467760016MaRDI QIDQ93079FDOQ93079
Publication date: October 2016
Published in: Journal of Multivariate Analysis (Search for Journal in Brave)
Abstract: Practical applications of nonparametric density estimators in more than three dimensions suffer a great deal from the well-known curse of dimensionality: convergence slows down as dimension increases. We show that one can evade the curse of dimensionality by assuming a simplified vine copula model for the dependence between variables. We formulate a general nonparametric estimator for such a model and show under high-level assumptions that the speed of convergence is independent of dimension. We further discuss a particular implementation for which we validate the high-level assumptions and establish its asymptotic normality. Simulation experiments illustrate a large gain in finite sample performance when the simplifying assumption is at least approximately true. But even when it is severely violated, the vine copula based approach proves advantageous as soon as more than a few variables are involved. Lastly, we give an application of the estimator to a classification problem from astrophysics.
Full work available at URL: https://arxiv.org/abs/1503.03305
Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Characterization and structure theory for multivariate probability distributions; copulas (62H05)
Cites Work
- Pair-copula constructions of multiple dependence
- Selecting and estimating regular vine copulae and application to financial returns
- D-vine copula based quantile regression
- Dependence Modeling with Copulas
- Asymptotic Statistics
- Rates of strong uniform consistency for multivariate kernel density estimators. (Vitesse de convergence uniforme presque sûre pour des estimateurs à noyaux de densités multivariées)
- Probability density decomposition for conditionally dependent random variables modeled by vines
- Estimating copula densities through wavelets
- Nonparametric density estimation for multivariate bounded data
- Simulation methodology - an introduction for queueing theorists
- Strong uniform consistency rates for estimators of conditional functionals
- Optimal rates of convergence for nonparametric estimators
- Evaluation of Trace Evidence in the Form of Multivariate Data
- Nonparametric estimation of pair-copula constructions with the empirical pair-copula
- Vines -- a new graphical model for dependent random variables.
- Parameter estimation for pair-copula constructions
- Flexible pair-copula estimation in D-vines using bivariate penalized splines
- Flexible copula density estimation with penalized hierarchical B-splines
- Estimating the density of a copula function
- Remarks on Some Nonparametric Estimates of a Density Function
- Estimation of a Copula when a Covariate Affects only Marginal Distributions
- UNIFORM CONVERGENCE RATES FOR KERNEL ESTIMATION WITH DEPENDENT DATA
- Title not available (Why is that?)
- Simplified pair copula constructions -- limitations and extensions
- Statistical testing of covariate effects in conditional copula models
- On Locally Adaptive Density Estimation
- Beyond simplified pair-copula constructions
- THE BERNSTEIN COPULA AND ITS APPLICATIONS TO MODELING AND APPROXIMATIONS OF MULTIVARIATE DISTRIBUTIONS
- Title not available (Why is that?)
- Probit transformation for nonparametric kernel estimation of the copula density
- Copula-Based Regression Estimation and Inference
- On Estimation of a Probability Density Function and Mode
- Multivariate plug-in bandwidth selection with unconstrained pilot bandwidth matrices
- Inverse beta transformation in kernel density estimation
- On the simplified pair-copula construction -- simply useful or too simplistic?
Cited In (29)
- Estimation of high-order moment-independent importance measures for Shapley value analysis
- About tests of the ``simplifying assumption for conditional copulas
- Estimating non-simplified vine copulas using penalized splines
- Prediction based on conditional distributions of vine copulas
- Generalized signed-rank estimation for regression models with non-ignorable missing responses
- Solving Estimating Equations With Copulas
- Model distances for vine copulas in high dimensions
- How simplifying and flexible is the simplifying assumption in pair-copula constructions -- analytic answers in dimension three and a glimpse beyond
- A fast and objective multidimensional kernel density estimation method: fastKDE
- Nonparametric estimation of simplified vine copula models: comparison of methods
- Explaining predictive models using Shapley values and non-parametric vine copulas
- On classification with nonignorable missing data
- Model selection for discrete regular vine copulas
- Robust estimation of single index models with responses missing at random
- On copula-based conditional quantile estimators
- Model selection in sparse high-dimensional vine copula models with an application to portfolio risk
- Generalized Additive Models for Pair-Copula Constructions
- Dependence structure estimation using copula recursive trees
- kdevine
- D-vine copula based quantile regression
- A generic approach to nonparametric function estimation with mixed data
- Testing the simplifying assumption in high-dimensional vine copulas
- Approximate Bayesian conditional copulas
- Modelling credit card exposure at default using vine copula quantile regression
- On copula-based collective risk models: from elliptical copulas to vine copulas
- The bivariate K-finite normal mixture ‘blanket’ copula
- The locally Gaussian density estimator for multivariate data
- Testing bivariate independence based on α -divergence by improved probit transformation method for copula density estimation
- Varying coefficient single-index regression model with missing responses under rank-based modelling
Uses Software
This page was built for publication: Evading the curse of dimensionality in nonparametric density estimation with simplified vine copulas
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q93079)
