Ekström, Magnus and SjöstedtdeLuna, Sara
(2001).
Estimation of the variance of sample means based on nonstationary spatial data with varying expected values.
Umeå:
(S) > Dept. of Forest Resource Management
(NL, NJ) > Dept. of Forest Resource Management, Sveriges lantbruksuniversitet.
Arbetsrapport / Sveriges lantbruksuniversitet, Institutionen för skoglig resurshushållning och geomatik
; 90
[Report]

PDF
1MB 
Abstract
Subsampling and block resampling methods have been suggested in the literature to
nonparametrically estimate the variance of some statistic computed from spatial data.
Usually stationary data are required. However, in empirical applications, the assump
tion of stationarity can often be rejected. This paper proposes nonparametric methods to
estimate the variance of sample means based on nonstationary spatial data using subsam
pling. It is assumed that data is observed on a rectangular lattice in some subregion of
R 2. The kind of data we consider is of the following type: The information in the different
picture elements (pixels) of the lattice are allowed to come from different distributions,
with smoothly varying expected values, or with expected values decomposed additively
into directional components. Furthermore, pixels are assumed to be locally dependent,
and the dependence structure is allowed to differ over the lattice. Consistent variance esti
mators for sample means, and convergence rates in mean square, are provided under these
assumptions. An example with applications to forestry, using satellite data, is discussed.
Authors/Creators:  Ekström, Magnus and SjöstedtdeLuna, Sara 

Title:  Estimation of the variance of sample means based on nonstationary spatial data with varying expected values 
Series/Journal:  Arbetsrapport / Sveriges lantbruksuniversitet, Institutionen för skoglig resurshushållning och geomatik (14011204) 
Year of publishing :  2001 
Number:  90 
Number of Pages:  18 
Place of Publication:  Umeå 
Publisher:  Institutionen för skoglig resurshushållning, Sveriges lantbruksuniversitet 
ISSN:  14011204 
Language:  English 
Publication Type:  Report 
Full Text Status:  Public 
Agris subject categories.:  U Auxiliary disciplines > U10 Mathematical and statistical methods 
Subjects:  (A) Swedish standard research categories 2011 > 1 Natural sciences > 101 Mathematics > 10106 Probability Theory and Statistics (A) Swedish standard research categories 2011 > 4 Agricultural Sciences > 401 Agricultural, Forestry and Fisheries > Forest Science 
Agrovoc terms:  statistical methods, linear models, data analysis, sampling 
Keywords:  bootstrap, nonidentically distributed variables, nonindependent variables, resampling, subsampling 
URN:NBN:  urn:nbn:se:slu:epsilone518 
Permanent URL:  http://urn.kb.se/resolve?urn=urn:nbn:se:slu:epsilone518 
ID Code:  8831 
Department:  (S) > Dept. of Forest Resource Management (NL, NJ) > Dept. of Forest Resource Management 
Deposited By:  Bo Jonsson 
Deposited On:  24 May 2012 08:05 
Metadata Last Modified:  02 Dec 2014 10:50 
Repository Staff Only: item control page