Bayesian spectral density estimation using P-splines with quantile-based knot placement
From MaRDI portal
Publication:2667015
Abstract: This article proposes a Bayesian approach to estimating the spectral density of a stationary time series using a prior based on a mixture of P-spline distributions. Our proposal is motivated by the B-spline Dirichlet process prior of Edwards et al. (2019) in combination with Whittle's likelihood and aims at reducing the high computational complexity of its posterior computations. The strength of the B-spline Dirichlet process prior over the Bernstein-Dirichlet process prior of Choudhuri et al. (2004) lies in its ability to estimate spectral densities with sharp peaks and abrupt changes due to the flexibility of B-splines with variable number and location of knots. Here, we suggest to use P-splines of Eilers and Marx (1996) that combine a B-spline basis with a discrete penalty on the basis coefficients. In addition to equidistant knots, a novel strategy for a more expedient placement of knots is proposed that makes use of the information provided by the periodogram about the steepness of the spectral power distribution. We demonstrate in a simulation study and two real case studies that this approach retains the flexibility of the B-splines, achieves similar ability to accurately estimate peaks due to the new data-driven knot allocation scheme but significantly reduces the computational costs.
Recommendations
- Bayesian nonparametric spectral density estimation using B-spline priors
- Bayesian inference with \(M\)-splines on spectral measure of bivariate extremes
- A computational Bayesian method for estimating the number of knots in regression splines
- Bayesian analysis for quantile smoothing spline
- scientific article; zbMATH DE number 270266
- Bayesian nonparametric quantile regression using splines
- On multiple spline approximations for Bayesian computations
- Simultaneous fitting of Bayesian penalised quantile splines
Cites work
- A generalized Fellner-Schall method for smoothing parameter optimization with application to Tweedie location, scale and shape models
- AdaptSPEC: Adaptive spectral estimation for nonstationary time series
- Archimedean copula estimation using Bayesian splines smoothing techniques
- Asymptotic spectral theory for nonlinear time series
- Bayesian decision theoretic scale-adaptive estimation of a log-spectral density
- Bayesian density estimation using bernstein polynomials
- Bayesian Estimation of the Spectral Density of a Time Series
- Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
- Bayesian inference on periodicities and component spectral structure in time series
- Bayesian mixture modeling for spectral density estimation
- Bayesian nonparametric analysis of multivariate time series: a matrix gamma process approach
- Bayesian nonparametric modeling using mixtures of triangular distributions
- Bayesian nonparametric spectral density estimation using B-spline priors
- Beyond Whittle: nonparametric correction of a parametric likelihood with a focus on Bayesian time series analysis
- Data-driven selection of the spline dimension in penalized spline regression
- Estimating the term structure of interest rates using penalized splines
- Estimation of spectral density of a stationary time series via an asymptotic of the periodogram
- Flexible estimation in cure survival models using Bayesian P-splines
- Flexible smoothing with B-splines and penalties. With comments and a rejoinder by the authors
- Forecasting in nonlinear univariate time series using penalized splines
- scientific article; zbMATH DE number 3146409 (Why is no real title available?)
- scientific article; zbMATH DE number 1086083 (Why is no real title available?)
- scientific article; zbMATH DE number 774881 (Why is no real title available?)
- Nonparametric Spectral Density Estimation Using Penalized Whittle Likelihood
- ON SEMIPARAMETRIC REGRESSION WITH O'SULLIVAN PENALIZED SPLINES
- On the estimation of variance parameters in non-standard generalised linear mixed models: application to penalised smoothing
- P-splines with derivative based penalties and tensor product smoothing of unevenly distributed data
- Random Bernstein Polynomials
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- Robust specification of the roughness penalty prior distribution in spatially adaptive Bayesian P-splines models
- Simultaneous probability statements for Bayesian P-splines
- Time series: theory and methods.
- Twenty years of P-splines (invited article)
Cited in
(8)- Bayesian copula spectral analysis for stationary time series
- Optimally adaptive Bayesian spectral density estimation for stationary and nonstationary processes
- Bayesian nonparametric spectral density estimation using B-spline priors
- A nonparametrically corrected likelihood for Bayesian spectral analysis of multivariate time series
- Asymptotic considerations in a Bayesian linear model with nonparametrically modelled time series innovations
- An algorithm for a constrained P-spline
- A new approach to nonparametric estimation of multivariate spectral density function using basis expansion
- Nonparametric Bayesian inference for the spectral density based on irregularly spaced data
This page was built for publication: Bayesian spectral density estimation using P-splines with quantile-based knot placement
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2667015)
