Weighted Dickey-Fuller processes for detecting stationarity
From MaRDI portal
Publication:2455422
Abstract: Aiming at monitoring a time series to detect stationarity as soon as possible, we introduce monitoring procedures based on kernel-weighted sequential Dickey-Fuller (DF) processes, and related stopping times, which may be called weighted Dickey-Fuller control charts. Under rather weak assumptions, (functional) central limit theorems are established under the unit root null hypothesis and local-to-unity alternatives. For gen- eral dependent and heterogeneous innovation sequences the limit processes depend on a nuisance parameter. In this case of practical interest, one can use estimated control limits obtained from the estimated asymptotic law. Another easy-to-use approach is to transform the DF processes to obtain limit laws which are invariant with respect to the nuisance pa- rameter. We provide asymptotic theory for both approaches and compare their statistical behavior in finite samples by simulation.
Recommendations
- Monitoring procedures to detect unit roots and stationarity
- Sequential monitoring for changes from stationarity to mild non-stationarity
- Fourier-type monitoring procedures for strict stationarity
- Sequentially Updated Residuals and Detection of Stationary Errors in Polynomial Regression Models
- Detecting relevant changes in the mean of nonstationary processes -- a mass excess approach
Cites work
- scientific article; zbMATH DE number 4102349 (Why is no real title available?)
- scientific article; zbMATH DE number 3550005 (Why is no real title available?)
- A CUSUM test for cointegration using regression residuals
- A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix
- Asymptotic distribution of an estimator of the boundary parameter of an unstable process
- Asymptotic inference for nearly nonstationary AR(1) processes
- Co-Integration and Error Correction: Representation, Estimation, and Testing
- Distribution of the Estimators for Autoregressive Time Series With a Unit Root
- Gradual changes versus abrupt changes.
- Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimation
- Limiting distributions of least squares estimates of unstable autoregressive processes
- Moment bounds for stationary mixing sequences
- Monitoring procedures to detect unit roots and stationarity
- Nonparametric detection of changepoints for sequentially observed data
- Nonparametric tests for nonstandard change-point problems
- On detecting jumps in time series: nonparametric setting
- On the Absolute Continuity of Distributions of Functionals of Random Processes
- Optimal sequential kernel detection for dependent processes
- Permutation tests for multiple changes.
- Random Walks with Drift – A Sequential Approach
- STATIONARY ARCH MODELS: DEPENDENCE STRUCTURE AND CENTRAL LIMIT THEOREM
- Sequential control of time series by functionals of kernel-weighted empirical processes under local alternatives
- Testing the null hypothesis of stationarity against the alternative of a unit root. How sure are we that economic time series have a unit root?
- The Limiting Distribution of the Serial Correlation Coefficient in the Explosive Case
- The calculation of the limiting distribution of the least squares estimator of the parameter in a random walk model
- Time Series Regression with a Unit Root
- Weak convergence and empirical processes. With applications to statistics
Cited in
(8)- Sequentially Updated Residuals and Detection of Stationary Errors in Polynomial Regression Models
- Sequential control of time series by functionals of kernel-weighted empirical processes under local alternatives
- Detection of stationary errors in multiple regressions with integrated regressors and cointegration
- Sequential Estimation and Control of Time-Varying Unit Root Processes with an Application to S&P Stock Price
- A surveillance procedure for random walks based on local linear estimation
- Monitoring procedures to detect unit roots and stationarity
- Robust Sign Test for the Unit Root Hypothesis of Autoregression
- Weighted simulated integrated conditional moment tests for parametric conditional distributions of stationary time series processes
This page was built for publication: Weighted Dickey-Fuller processes for detecting stationarity
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2455422)
