Sampling and geostatistics for spatial data

AbstractThe goals of classical statistical sampling (e.g. estimation of population means using simple random sampling stratified random sampling etc.) geostatistics (e.g. estimation of population means using block kriging) can be identical. For example both can be used to estimate the average value or total amount of a variable of interest in some area. The most fundamental difference between classical sampling geostatistics is that classical sampling relies on design-based inference while geostatistics relies on model-based inference. These differences are illustrated with ex mples. Classical sampling usually considers sampling for finite populations but in the spatial context it is easily adapted to infinite populations. Geostatistics has only considered infinite populations but methods for finite populations have been developed recently. To compare classical sampling to geostatistics for both infinite finite populations I consider the following data sets: 1) a fabricated fixed spatial pattern from an i...

[1]  H. D. Patterson,et al.  Recovery of inter-block information when block sizes are unequal , 1971 .

[2]  Noel A Cressie,et al.  Asymptotics for REML estimation of spatial covariance parameters , 1996 .

[3]  G. Robertson.  Geostatistics in Ecology: Interpolating With Known Variance , 1987 .

[4]  Noel A Cressie,et al.  Statistics for Spatial Data, Revised Edition. , 1994 .

[5]  Peter K. Kitanidis,et al.  Statistical estimation of polynomial generalized covariance functions and hydrologic applications , 1983 .

[6]  C. Heyde.  A quasi-likelihood approach to the REML estimating equations , 1994 .

[7]  C. Braak,et al.  Model-free estimation from spatial samples: A reappraisal of classical sampling theory , 1990 .

[8]  Don L. Stevens,et al.  VARIABLE DENSITY GRID‐BASED SAMPLING DESIGNS FOR CONTINUOUS SPATIAL POPULATIONS , 1997 .

[9]  N. Cressie.  The origins of kriging , 1990 .

[10]  A. McBratney,et al.  DPTIMAL INTERPOLATION AND ISARITHMIC MAPPING OF SOIL PROPERTIES. IV SAMPLING STRATEGY , 1981 .

[11]  Dale L. Zimmerman,et al.  Computationally efficient restricted maximum likelihood estimation of generalized covariance functions , 1989 .

[12]  G. Matheron.  Principles of geostatistics , 1963 .

[13]  D. Brus,et al.  Design‐based versus model‐based estimates of spatial means: Theory and application in environmental soil science , 1993 .

[14]  D. Horvitz,et al.  A Generalization of Sampling Without Replacement from a Finite Universe , 1952 .

[15]  Alex B. McBratney,et al.  HOW MANY OBSERVATIONS ARE NEEDED FOR REGIONAL ESTIMATION OF SOIL PROPERTIES? , 1983 .

[16]  Clifford B. Cordy,et al.  An extension of the Horvitz—Thompson theorem to point sampling from a continuous universe , 1993 .

[17]  C. E. Särndal.  TWO MODEL-BASED INFERENCE ARGUMENTS IN SURVEY SAMPLING , 1980 .

[18]  J. Davidson.  Stochastic Limit Theory , 1994 .

[19]  K. Mardia,et al.  Maximum likelihood estimation of models for residual covariance in spatial regression , 1984 .

[20]  Michael L. Stein,et al.  Asymptotically Efficient Prediction of a Random Field with a Misspecified Covariance Function , 1988 .

[21]  J. W. van Groenigen,et al.  The influence of variogram parameters on optimal sampling schemes for mapping by kriging , 2000 .

[22]  Noel A. C. Cressie,et al.  Statistics for Spatial Data: Cressie/Statistics , 1993 .

[23]  C. L. Kucera,et al.  Vegetation and Soil Relationships in the Glade Region of the Southwestern Missouri Ozarks , 1957 .

[24]  N. Cressie.  Fitting variogram models by weighted least squares , 1985 .

[25]  J. W. Groenigen,et al.  Constrained optimisation of soil sampling for minimisation of the kriging variance , 1999 .

[26]  J. Chilès,et al.  Geostatistics: Modeling Spatial Uncertainty , 1999 .