Optimal sampling for density estimation in continuous time
Let a stationary process \(X(t)\in R^d\), \(t\in R\), be observed at points \(t_{i,n}\): \(t_{i,0}=0\), \(t_{k+1,n}=t_{k,n}+l_n\delta_n\), where \(\delta_n\to 0\), and \(l_n\) are predefined real numbers with \(1\leq l_n\leq l^*\). A kernel density estimator for the marginal density of \(X(t)\) is considered of the form \[ \hat f_n(x)=(n h_n^d)^{-1} \sum_{i=1}^n K\left((x-X(t_{i,n})h_n^{-1}\right). \] The authors seek for the minimal possible \(\delta_n\) under which \(\hat f_n\) has \(L_2\) convergence rate equal to the i.i.d. case rate. The case is considered where observations are of the form \(X(t)+\varepsilon_t\), where \(\varepsilon_t\) is some noise process. A deconvolution kernel-type estimator is proposed for \(f\) in the case where the marginal density of \(\varepsilon_t\) is known. Usual kernel estimators are considered in the case of ``small noise: \(\varepsilon_t=\sigma_n\varepsilon_t^0\) with \(\sigma_n\to 0\) as \(n\to\infty\).
- Accurate rates of density estimators for continuous-time processes
- Asymptotically optimal bandwidth selection rules for the kernel density estimator with dependent observations
- Estimation of local smoothness coefficients for continuous time processes
- Estimation of the asymptotic variance of kernel density estimators for continuous time processes
- scientific article; zbMATH DE number 54145 (Why is no real title available?)
- scientific article; zbMATH DE number 3563431 (Why is no real title available?)
- Multivariate probability density deconvolution for stationary random processes
- Nonparametric curve estimation. Methods, theory, and applications
- Nonparametric statistics for stochastic processes. Estimation and prediction.
- On bandwidth choice for density estimation with dependent data
- On the asymptotic variance of the continuous-time kernel density estimator
- Strong consistency and rates for deconvolution of multivariate densities of stationary processes
- The asymptotic variance of the continuous-time kernel estimator with applications to bandwidth selection
- Improving density estimators of discretely observed processes by interpolation
- On when to stop sampling for the maximum
- Adaptive estimation of density with sampled observations.
- Finite sample performance of density estimators from unequally spaced data
- Asymptotic normality of kernel density function estimator from continuous time stationary and dependent processes
- Asymptotics for function derivatives estimators based on stationary and ergodic discrete time processes
- Optimal L^2-approximation of occupation and local times for symmetric stable processes
- Some asymptotic properties of kernel regression estimators of the mode for stationary and ergodic continuous time processes
- Piecewise linear density estimation for sampled data
- Optimal asymptotic MSE of kernel regression estimate for continuous time processes with missing at random response
- Super optimal rates for nonparametric density estimation via projection estimators
- Adaptive sampling schemes for density estimation
- Asymptotic normality of kernel type regression estimators for random fields
- Sampling at a random time with a heavy-tailed distribution
- Testing the null hypothesis of nonstationary long memory against the alternative hypothesis of a nonlinear ergodic model
- Estimation for the invariant law of an ergodic diffusion process based on high-frequency data
- OPTIMUM DESIGN OF SAMPLING TIMES FOR INFERENCE OF COMPARTMENT MODELS BASED ON CURVATURE
- Optimal sampling schemes for the Gaussian hypothesis testing problem
- Optimal sampling schedule for parameter estimation of linear models with unknown but bounded measurement errors
- Optimal sampling from sliding windows
- Exact Sampling from a Continuous State Space
- scientific article; zbMATH DE number 559135 (Why is no real title available?)
- A family of minimax rates for density estimators in continuous time
- Local Hölder exponent estimation for multivariate continuous time processes
- scientific article; zbMATH DE number 802862 (Why is no real title available?)
- scientific article; zbMATH DE number 845760 (Why is no real title available?)
- scientific article; zbMATH DE number 1410195 (Why is no real title available?)
- Some results about kernel estimators for function derivatives based on stationary and ergodic continuous time processes with applications
- A note on wavelet density deconvolution for weakly dependent data
- Frequency polygons for continuous random fields
- Asymptotic normality of kernel type density estimators for random fields
- The ARHD model
- Sample paths adaptive density estimation
- Kernel regression estimation for continuous spatial processes
- Assessing the number of mean square derivatives of a Gaussian process
This page was built for publication: Optimal sampling for density estimation in continuous time
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4431625)
