Bandwidth selection for the Local Polynomial Double Conditional Smoothing under Spatial ARMA Errors*
Additional contact information
Bastian Schäfer: Paderborn University
No 146, Working Papers CIE from Paderborn University, CIE Center for International Economics
Nonparametric estimation of the mean surface of spatial data usually depends on a bivariate regressor, which is an ineffective estimation method for large data sets. The Double Conditional Smoothing (DCS) increases computational efficiency by reducing the regression problem to one dimension. We apply the DCS scheme to two-dimensional functional or spatial time series and use local polynomial regression for estimation of the regression surface and its derivatives. Asymptotic formulas for expectation and variance are given and formulas for the asymptotic optimal bandwidth derived. We propose a iterative plug-in algorithm for estimation of these optimal bandwidths under dependent errors. Spatial ARMA processes are used to model the error sequece parametrically and some estimation procedures for spatial ARMA processes are suggested. The proposed methods are assessed via a simulation study and applied to high-freqency financial data.
Keywords: Semiparametric regression; functional double conditional smoothing; bandwidth selection; iterative plug-in; dependent errors (search for similar items in EconPapers)
Pages: 45 pages
New Economics Papers: this item is included in nep-ecm and nep-ore
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed
Downloads: (external link)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:pdn:ciepap:146
Access Statistics for this paper
More papers in Working Papers CIE from Paderborn University, CIE Center for International Economics Contact information at EDIRC.
Bibliographic data for series maintained by WP-WiWi-Info () and ().