Issues in the estimation of mis-specified models of fractionally integrated processes

DOI10.1016/J.JECONOM.2019.09.007zbMATH1456.62212OpenAlexW2989078620MaRDI QIDQ2182145FDOQ2182145

Authors Gael M. Martin, K. Nadarajah, D. S. Poskitt

Publication date 21 May 2020

Published in Journal of Econometrics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1407.1347

zbMATH Keywords

ARFIMAlong memory modelsfrequency domain estimatorsmis-specified short memory dynamicspseudo-true parametertime domain estimators

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Applications of statistics to economics (62P20) Asymptotic distribution theory in statistics (62E20) Nonparametric statistical resampling methods (62G09) Inference from stochastic processes and spectral analysis (62M15)

Abstract: We provide a comprehensive set of new results on the impact of mis-specifying the short run dynamics in fractionally integrated processes. We show that four alternative parametric estimators - frequency domain maximum likelihood, Whittle, time domain maximum likelihood and conditional sum of squares - converge to the same pseudo-true value under common mis-specification, and that they possess a common asymptotic distribution. The results are derived assuming a completely general parametric specification for the short run dynamics of the estimated (mis-specified) fractional model, and with long memory, short memory and antipersistence in both the model and the true data generating process accommodated. As well as providing new theoretical insights, we undertake an extensive set of numerical explorations, beginning with the numerical evaluation, and implementation, of the (common) asymptotic distribution that holds under the most extreme form of mis-specification. Simulation experiments are then conducted to assess the relative finite sample performance of all four mis-specified estimators, initially under the assumption of a known mean, as accords with the theoretical derivations. The importance of the known mean assumption is illustrated via the production of an alternative set of bias and mean squared error results, in which the estimators are applied to demeaned data. The paper concludes with a discussion of open problems.

Recommendations

• Estimation of mis-specified long memory models
• (MIS)SPECIFICATION OF LONG MEMORY IN SEASONAL TIME SERIES
• The estimation of misspecified long memory models
• Estimating the fractionally integrated process in the presence of measurement errors
• Local Whittle estimation of fractional integration for nonlinear processes

Cites work

• scientific article; zbMATH DE number 218722 (Why is no real title available?)
• scientific article; zbMATH DE number 795280 (Why is no real title available?)
• scientific article; zbMATH DE number 847242 (Why is no real title available?)
• scientific article; zbMATH DE number 6193733 (Why is no real title available?)
• (MIS)SPECIFICATION OF LONG MEMORY IN SEASONAL TIME SERIES
• A central limit theorem for quadratic forms in strongly dependent linear variables and its application to asymptotical normality of Whittle's estimate
• A necessary and sufficient condition for asymptotic independence of discrete Fourier transforms under short- and long-range dependence
• Broadband log-periodogram regression of time series with long-range dependence
• Efficient parameter estimation for self-similar processes
• Estimating Long Memory in Volatility
• Estimation and information in stationary time series
• Estimation of mis-specified long memory models
• Fractionally integrated generalized autoregressive conditional heteroskedasticity
• Gaussian Semiparametric Estimation of Non-stationary Time Series
• Gaussian pseudo-maximum likelihood estimation of fractional time series models
• Gaussian semiparametric estimation of long range dependence
• Large-sample properties of parameter estimates for strongly dependent stationary Gaussian time series
• Long memory in continuous-time stochastic volatility models
• Long memory processes and fractional integration in econometrics
• Modeling and Forecasting Realized Volatility
• Modeling and pricing long memory in stock market volatility
• ON THE LOG PERIODOGRAM REGRESSION ESTIMATOR OF THE MEMORY PARAMETER IN LONG MEMORY STOCHASTIC VOLATILITY MODELS
• Quasi-maximum likelihood estimation and bootstrap inference in fractional time series models with heteroskedasticity of unknown form
• Stationary persistent time series misspecified as nonstationary arima
• THE NONSTATIONARY FRACTIONAL UNIT ROOT
• Table of integrals, series, and products. Translated from the Russian. Translation edited and with a preface by Alan Jeffrey and Daniel Zwillinger. With one CD-ROM (Windows, Macintosh and UNIX)
• The asymptotic theory of linear time-series models
• The detection and estimation of long memory in stochastic volatility
• The estimation of misspecified long memory models
• Whittle Pseudo-Maximum Likelihood Estimation for Nonstationary Time Series

Cited in

(4)

• Estimation of mis-specified long memory models
• Bias Correction of Persistence Measures in Fractionally Integrated Models
• Optimal bias correction of the log-periodogram estimator of the fractional parameter: a jackknife approach
• Fractional integration with Bloomfield exponential spectral disturbances: a Monte Carlo experiment and an application

Describes a project that uses

Uses Software

• longmemo

This page was built for publication: Issues in the estimation of mis-specified models of fractionally integrated processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2182145)