Abstract

This paper considers conditioning on the size of the samples observed in post-strata following a two-stage sampling design. We argue that it is reasonable to do so despite the complexity of the design. We derive an expression for the covariances among post-strata estimates resulting from secondary sampling units on the same primary sampling unit which reside in different post-strata. To motivate both issues we describe a two-stage LiDAR-assisted sample for aboveground biomass that was reported in Gregoire et al. (Can J For Res 41: 83-95, 2011).

Keywords

Biomass; Configuration; Hedmark County; LiDAR

Published in

Environmental and Ecological Statistics
2016, Volume: 23, number: 1, pages: 141-154
Publisher: SPRINGER

SLU Authors

• Hedström Ringvall, Anna

  • Department of Forest Resource Management, Swedish University of Agricultural Sciences
    

• Ståhl, Göran

  • Department of Forest Resource Management, Swedish University of Agricultural Sciences
    

UKÄ Subject classification

Probability Theory and Statistics


Publication identifier

DOI: https://doi.org/10.1007/s10651-015-0332-9

Permanent link to this page (URI)

https://res.slu.se/id/publ/82843