Show simple item record

dc.contributor.authorSørbye, Sigrunn Holbek
dc.contributor.authorNicolau, Pedro G.
dc.contributor.authorRue, Haavard
dc.date.accessioned2021-11-15T06:08:36Z
dc.date.available2021-11-15T06:08:36Z
dc.date.issued2021-12-05
dc.identifier.citationSørbye, S. H., Nicolau, P. G., & Rue, H. (2021). Finite-sample properties of estimators for first and second order autoregressive processes. Statistical Inference for Stochastic Processes. doi:10.1007/s11203-021-09262-4
dc.identifier.issn1572-9311
dc.identifier.issn1387-0874
dc.identifier.doi10.1007/s11203-021-09262-4
dc.identifier.urihttp://hdl.handle.net/10754/673392
dc.description.abstractThe class of autoregressive (AR) processes is extensively used to model temporal dependence in observed time series. Such models are easily available and routinely fitted using freely available statistical software like R. A potential problem is that commonly applied estimators for the coefficients of AR processes are severely biased when the time series are short. This paper studies the finite-sample properties of well-known estimators for the coefficients of stationary AR(1) and AR(2) processes and provides bias-corrected versions of these estimators which are quick and easy to apply. The new estimators are constructed by modeling the relationship between the true and originally estimated AR coefficients using weighted orthogonal polynomial regression, taking the sampling distribution of the original estimators into account. The finite-sample distributions of the new bias-corrected estimators are approximated using transformations of skew-normal densities, combined with a Gaussian copula approximation in the AR(2) case. The properties of the new estimators are demonstrated by simulations and in the analysis of a real ecological data set. The estimators are easily available in our accompanying R-package for AR(1) and AR(2) processes of length 10–50, both giving bias-corrected coefficient estimates and corresponding confidence intervals.
dc.description.sponsorshipOpen Access funding provided by UiT The Arctic University of Norway
dc.publisherSpringer Science and Business Media LLC
dc.relation.urlhttps://link.springer.com/10.1007/s11203-021-09262-4
dc.rightsArchived with thanks to Statistical Inference for Stochastic Processes
dc.titleFinite-sample properties of estimators for first and second order autoregressive processes
dc.typeArticle
dc.contributor.departmentStatistics Program
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.identifier.journalStatistical Inference for Stochastic Processes
dc.eprint.versionPublisher's Version/PDF
dc.contributor.institutionUiT The Arctic University of Norway, Tromsø, Norway
kaust.personRue, Haavard
dc.date.accepted2021-11-12
dc.identifier.eid2-s2.0-85120684784
refterms.dateFOA2021-12-14T03:12:15Z


Files in this item

Thumbnail
Name:
s11203-021-09262-4.pdf
Size:
1.406Mb
Format:
PDF
Description:
Publisher's Version/PDF

This item appears in the following Collection(s)

Show simple item record