1. Strength of Spatial Correlation and Spatial Designs: Effects on Covariance Estimation Kathryn M. Irvine Oregon State University Alix I. Gitelman Sandra E. Thompson

2. The research described in this presentation has been funded by the U.S. Environmental Protection Agency through the STAR Cooperative Agreement CR82-9096-01 Program on Designs and Models for Aquatic Resource Surveys at Oregon State University. It has not been subjected to the Agency's review and therefore does not necessarily reflect the views of the Agency, and no official endorsement should be inferred R82-9096-01

3. Talk Outline Stream Sulfate Concentration –Geostatistical Model –Preliminary Findings Simulations Results –Parameter Estimation Discussion

4. Study Objective: Model the spatial heterogeneity of stream sulfate concentration in streams in the Mid- Atlantic U.S.

5. Why stream sulfate concentration? –Indirectly toxic to fish and aquatic biota Decrease in streamwater pH Increase in metal concentrations (AL) –Observed positive spatial relationship with atmospheric SO 4 -2 deposition (Kaufmann et al. 1991)

6. The Data EMAP water chemistry data –322 stream locations Watershed variables: –% forest, % agriculture, % urban, % mining –% within ecoregions with high sulfate adsorption soils National Atmospheric Deposition Program

7. EMAP and NADP locations EMAP NADP

8. Geostatistical Model Where Y(s) is a vector of observed ln(SO 4 -2 ) concentration at stream locations (s) X(s) is a matrix of watershed explanatory variables   is a vector of unknown regression coefficients   (s) is the spatial error process Where D is matrix of pairwise distances,  is 1/range,   is the partial sill   is the nugget (1)

9. Effective Range Definition: 1) Distance beyond which the correlation between observations is less than or equal to 0.05. 2) Distance where the semi-variogram reaches 95% of the sill.

10. Semi-Variogram Nugget Partial Sill Effective Range 197 km 272 km

11. Interpretations of Spatial Covariance Parameters Patch Characteristics (Rossi et al. 1992; Robertson and Gross 1994; Dalthorp et al. 2000; Schwarz et al. 2003 and more) –Effective Range ~ Size of Patch –Nugget ~ Tightness of Patches Sample Design Modifications –Effective Range: Independent Samples –Nugget: Measurement Error

12. Why Are the Estimates Different? Simulation Study Strength of Spatial Correlation? –Nugget:Sill ratio and/or Range Parameter Mardia & Marshall (1984): measurement error increases variability of ML estimates of range Zimmerman & Zimmerman (1991): REML and ML better when spatial signal weak (short range) Lark (2000): ML better compared to MOM when short range and large nugget:sill ratio Thompson (2001): estimation for Matern with 20% and 50% nugget under different spatial designs

13. Is the spatial correlation too weak? Effective Range Values for Simulations EMAP Estimates Re-Scaled: Range Parameter ~1.5 Nugget-to-Sill Ratio ~0.50

14. Is it the spatial sample design? - Cluster design optimal for covariance parameter estimation (Pettitt and McBratney 1993; Muller and Zimmerman 1999; Zhu and Stein 2005; Xia et al. 2006; Zimmerman 2006; Zhu and Zhang 2006)

15. Is it the spatial sample design? Zimmerman (2006) and Thompson (2001)

16. Simulation Study Spatial Designs: Lattice, Random, Cluster Range Parameter = 1 and 3 Nugget/Sill Ratio: 0.10, 0.33, 0.50, 0.67, 0.90 n=144 and n=361 (In-fill Asymptotics) 100 realizations per combination RandomFields in R Estimation using R code (Ver Hoef 2004)

17. 1.Estimation of Covariance Parameters The Effective Range

18. Range Parameter = 1 Range Parameter = 3 Results for Estimation of Effective Range Estimation Error = estimate - truth

19. Range Parameter = 1 Range Parameter = 3 Results for Estimation of Effective Range

20. Range Parameter = 1 Range Parameter = 3 Results for Estimation of Effective Range

21. Range Parameter = 1 Range Parameter = 3 Results for Estimation of Effective Range

22. Summary Covariance Parameter Estimation Effective Range : –ML under-estimate the truth –REML more skewed in 90th percentile (large nugget- to-sill and range parameter) Partial Sill: –ML under-estimate the truth –REML more skewed in 90th percentile Nugget: –estimated well; particularly with cluster design

23. Discussion –Which estimation method to use? –Consistency Results:     Chen et al. 2000, Zhang and Zimmerman 2005) –Uncertainty estimates for REML and ML REML: Increasing Domain (Cressie and Lahiri 1996) ML: Increasing Domain and Infill Asymptotics (Zhang and Zimmerman 2005)

24. Acknowledgements Co-Authors Jay Ver Hoef, Alan Herlihy, Andrew Merton, Lisa Madsen

25. Questions

26. Results 1. Estimation of Covariance Parameters 2. Estimation of Autocorrelation Function

27. Results: 2. Estimation of Autocorrelation Function

28. Estimation of Autocorrelation Function Cluster Design

29. Summary: Estimation of Autocorrelation Function Overall Patterns: –ML and REML poor performance with stronger spatial correlation (larger effective ranges) –REML large variability –ML under-estimation –‘BEST’ case: Cluster Design with range parameter = 1 and n=361

30. Wet Atmospheric Sulfate Deposition http://www.epa.gov/airmarkets/cmap/mapgallery/mg_wetsulfatephase1.html

31. Estimated Auto-correlation Function for ln(SO 4 -2 )

32. Sketch of watershed with overlaid landcover map

33. 2. Estimation of Autocorrelation Function Lattice Design

34. Estimation of Autocorrelation Function Lattice Design

35. 2. Estimation of Autocorrelation Function Random Design

36. Estimation of Autocorrelation Function Random Design

37. 2. Estimation of Autocorrelation Function Cluster Design