Nonparametric C- and D-vine-based quantile regression
From MaRDI portal
Publication:2667760
DOI10.1515/DEMO-2022-0100zbMATH Open1480.62069arXiv2102.04873OpenAlexW4220850245MaRDI QIDQ2667760FDOQ2667760
Gerda Claeskens, Claudia Czado, Jing Zhou, Marija Tepegjozova
Publication date: 1 March 2022
Published in: Dependence Modeling (Search for Journal in Brave)
Abstract: Quantile regression is a field with steadily growing importance in statistical modeling. It is a complementary method to linear regression, since computing a range of conditional quantile functions provides a more accurate modelling of the stochastic relationship among variables, especially in the tails. We introduce a non-restrictive and highly flexible nonparametric quantile regression approach based on C- and D-vine copulas. Vine copulas allow for separate modeling of marginal distributions and the dependence structure in the data, and can be expressed through a graph theoretical model given by a sequence of trees. This way we obtain a quantile regression model, that overcomes typical issues of quantile regression such as quantile crossings or collinearity, the need for transformations and interactions of variables. Our approach incorporates a two-step ahead ordering of variables, by maximizing the conditional log-likelihood of the tree sequence, while taking into account the next two tree levels. Further, we show that the nonparametric conditional quantile estimator is consistent. The performance of the proposed methods is evaluated in both low- and high-dimensional settings using simulated and real world data. The results support the superior prediction ability of the proposed models.
Full work available at URL: https://arxiv.org/abs/2102.04873
Nonparametric estimation (62G05) Nonparametric regression and quantile regression (62G08) Characterization and structure theory for multivariate probability distributions; copulas (62H05)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- D-vine copula based quantile regression
- Generalized random forests
- Probit transformation for kernel density estimation on the unit interval
- Estimating the dimension of a model
- Dependence Modeling with Copulas
- Regression Quantiles
- Strictly Proper Scoring Rules, Prediction, and Estimation
- Statistics for high-dimensional data. Methods, theory and applications.
- Prediction based on conditional distributions of vine copulas
- Bayesian quantile regression
- Vines -- a new graphical model for dependent random variables.
- \(\ell_1\)-penalized quantile regression in high-dimensional sparse models
- Estimating the density of a copula function
- Simplified pair copula constructions -- limitations and extensions
- 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
- On the simplified pair-copula construction -- simply useful or too simplistic?
- Analyzing dependent data with vine copulas. A practical guide with R
- Quantile regression for longitudinal data
- Conditional quantiles and tail dependence
- Conditional Quantile Estimation for Generalized Autoregressive Conditional Heteroscedasticity Models
- Identifying Risk Factors for Severe Childhood Malnutrition by Boosting Additive Quantile Regression
- Copula-based nonlinear quantile autoregression
- Local Linear Quantile Regression
- Probability
- Additive models for quantile regression: model selection and confidence bands
- The Focused Information Criterion
- Weak and strong uniform consistency of the kernel estimate of a density and its derivatives
- Consistency of the kernel density estimator: a survey
- The Copula Information Criteria
- On Strong Consistency of Density Estimates
- Bootstrapping quantiles in a fixed design regression model with censored data
- Nonparametric estimation of simplified vine copula models: comparison of methods
- Simplified R-vine based forward regression
- Uniform consistency of generalized kernel estimators of quantile density
- The Preservation of Convergence of Measurable Functions Under Composition
- Parametric or nonparametric: The FIC approach
- Study of partial and average conditional Kendall's tau
- An Improved Transformation-Based Kernel Estimator of Densities on the Unit Interval
- Focused information criteria for copulas
Cited In (2)
Uses Software
This page was built for publication: Nonparametric C- and D-vine-based quantile regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2667760)
