On trend estimation under monotone Gaussian subordination with long-memory: application to fossil pollen series

Menendez, Patricia; Ghosh, Sucharita; Kuensch, Hans R.; Tinner, Willy (2013). On trend estimation under monotone Gaussian subordination with long-memory: application to fossil pollen series. Journal of Nonparametric Statistics, 25(4), pp. 765-785. Taylor & Francis 10.1080/10485252.2013.826357

[img] Text
trend estimation.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (411kB) | Request a copy

Fossil pollen data from stratigraphic cores are irregularly spaced in time due to non-linear age-depth relations. Moreover, their marginal distributions may vary over time. We address these features in a nonparametric regression model with errors that are monotone transformations of a latent continuous-time Gaussian process Z(T). Although Z(T) is unobserved, due to monotonicity, under suitable regularity conditions, it can be recovered facilitating further computations such as estimation of the long-memory parameter and the Hermite coefficients. The estimation of Z(T) itself involves estimation of the marginal distribution function of the regression errors. These issues are considered in proposing a plug-in algorithm for optimal bandwidth selection and construction of confidence bands for the trend function. Some high-resolution time series of pollen records from Lago di Origlio in Switzerland, which go back ca. 20,000 years are used to illustrate the methods.

Item Type:

Journal Article (Original Article)

Division/Institute:

10 Strategic Research Centers > Oeschger Centre for Climate Change Research (OCCR)
08 Faculty of Science > Department of Biology > Institute of Plant Sciences (IPS) > Palaeoecology
08 Faculty of Science > Department of Biology > Institute of Plant Sciences (IPS)

UniBE Contributor:

Tinner, Willy

Subjects:

500 Science > 580 Plants (Botany)

ISSN:

1048-5252

Publisher:

Taylor & Francis

Language:

English

Submitter:

Peter Alfred von Ballmoos-Haas

Date Deposited:

17 Feb 2014 10:11

Last Modified:

08 Sep 2015 11:49

Publisher DOI:

10.1080/10485252.2013.826357

Uncontrolled Keywords:

continuous time, latent Gaussian process, nonparametric regression, palaeoclimate, palaeoecology

BORIS DOI:

10.7892/boris.40905

URI:

https://boris.unibe.ch/id/eprint/40905

Actions (login required)

Edit item Edit item
Provide Feedback