Forest inventory inference with spatial model strata
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Forest inventory inference with spatial model strata. / Magnussen, Steen; Nord-Larsen, Thomas.
In: Scandinavian Journal of Forest Research, Vol. 36, No. 1, 2021, p. 43-54.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Forest inventory inference with spatial model strata
AU - Magnussen, Steen
AU - Nord-Larsen, Thomas
PY - 2021
Y1 - 2021
N2 - In design-based model assisted inference from data gathered in a large area forest inventory under a probability sampling design, one should anticipate spatial heterogeneity in the regression coefficients of an assisting model. The consequence of such heterogeneity is that a global estimate of a root mean squared error (RMSE) becomes unsuited for local predictions. With data from the Danish National Forest Inventory, we demonstrate how to: obtain an assisting model with the lasso method; test for spatial stationarity in regression coefficients of the assisting model; and identify spatial model strata for a post-stratification with either a finite mixture modeling or a lasso spatial clustered coefficients method. Spatial model strata apply to any domain and small area estimation problem without the need for complex modeling when domains or small area changes with shifting user needs. One should not à priori expect a spatial model stratification to improve design-based population and strata estimates of precision, but the reliability of domain and small area RMSEs will improve in presence of statistically significant spatial model strata.
AB - In design-based model assisted inference from data gathered in a large area forest inventory under a probability sampling design, one should anticipate spatial heterogeneity in the regression coefficients of an assisting model. The consequence of such heterogeneity is that a global estimate of a root mean squared error (RMSE) becomes unsuited for local predictions. With data from the Danish National Forest Inventory, we demonstrate how to: obtain an assisting model with the lasso method; test for spatial stationarity in regression coefficients of the assisting model; and identify spatial model strata for a post-stratification with either a finite mixture modeling or a lasso spatial clustered coefficients method. Spatial model strata apply to any domain and small area estimation problem without the need for complex modeling when domains or small area changes with shifting user needs. One should not à priori expect a spatial model stratification to improve design-based population and strata estimates of precision, but the reliability of domain and small area RMSEs will improve in presence of statistically significant spatial model strata.
KW - design based
KW - Finite mixture model
KW - geographically weighted regression
KW - lasso
KW - post-stratification
KW - spatial stationarity
U2 - 10.1080/02827581.2020.1852309
DO - 10.1080/02827581.2020.1852309
M3 - Journal article
AN - SCOPUS:85097068482
VL - 36
SP - 43
EP - 54
JO - Scandinavian Journal of Forest Research
JF - Scandinavian Journal of Forest Research
SN - 0282-7581
IS - 1
ER -
ID: 259834618