Advertisement

Environmental and Ecological Statistics

, Volume 13, Issue 4, pp 449–464 | Cite as

Spatial statistical models that use flow and stream distance

  • Jay M. Ver HoefEmail author
  • Erin Peterson
  • David Theobald
Original Article

Abstract

We develop spatial statistical models for stream networks that can estimate relationships between a response variable and other covariates, make predictions at unsampled locations, and predict an average or total for a stream or a stream segment. There have been very few attempts to develop valid spatial covariance models that incorporate flow, stream distance, or both. The application of typical spatial autocovariance functions based on Euclidean distance, such as the spherical covariance model, are not valid when using stream distance. In this paper we develop a large class of valid models that incorporate flow and stream distance by using spatial moving averages. These methods integrate a moving average function, or kernel, against a white noise process. By running the moving average function upstream from a location, we develop models that use flow, and by construction they are valid models based on stream distance. We show that with proper weighting, many of the usual spatial models based on Euclidean distance have a counterpart for stream networks. Using sulfate concentrations from an example data set, the Maryland Biological Stream Survey (MBSS), we show that models using flow may be more appropriate than models that only use stream distance. For the MBSS data set, we use restricted maximum likelihood to fit a valid covariance matrix that uses flow and stream distance, and then we use this covariance matrix to estimate fixed effects and make kriging and block kriging predictions.

Keywords

Stream networks Valid autocovariances Geostatistics Variogram Block kriging 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Akaike H (1973) Information theory and an extension of the maximum likelihood principle. In: Petrov BN, Csaki F (eds) Second International Symposium on Information Theory. Akademiai Kiado, Budapest, pp 267–281Google Scholar
  2. Barry, RP, Ver Hoef, JM 1996Blackbox kriging: spatial prediction without specifying the variogramJ Agricult Biol Environ Stat1297322CrossRefGoogle Scholar
  3. Chiles, J-P, Delfiner, P 1999Geostatistics: modeling spatial uncertaintyJohn Wiley and SonsNew York695Google Scholar
  4. Cressie, N 1993Statistics for spatial data, revised editionJohn Wiley and SonsNew York900Google Scholar
  5. Cressie, N, Majure, JJ 1997Spatio-temporal statistical modeling of livestock waste in streamsJ Agricult Biol Environ Stat22447CrossRefGoogle Scholar
  6. Cressie, N, Pavlicova, M 2002Calibrated spatial moving average simulationsStat Model2267279CrossRefGoogle Scholar
  7. Curriero F (1996) The use of non-euclidean distance in geostatistics. Ph.D. Thesis, Kansas State UniversityGoogle Scholar
  8. Dent, CL, Grimm, NB 1999Spatial heterogeneity of stream water nutrient concentrations over successional timeEcology8022832298CrossRefGoogle Scholar
  9. Fuentes, M 2002Spectral methods for nonstationary spatial processesBiometrika89197210CrossRefGoogle Scholar
  10. Gardner, B, Sullivan, PJ, Lembo, AJ,Jr 2003Predicting stream temperatures: geostatistical model comparison using alternative distance metricsCan J Fish Aquat Sci60344351CrossRefGoogle Scholar
  11. Higdon, D 1998A process-convolution approach to modelling temperatures in the North Atlantic OceanEnviron Ecol Stat5173190CrossRefGoogle Scholar
  12. Higdon D, Swall J, Kern J (1999) Non-stationary spatial modeling. In Bayesian statistics 6, Oxford Univ Press, Oxford 761–768Google Scholar
  13. Littell, RC, Milliken, RC, Stroup, WW, Wolfinger, R 1996SAS system for mixed modelsSAS publishingCary, NC656Google Scholar
  14. Little, LS, Edwards, D, Porter, DE 1997Kriging in estuaries: as the crow flies, or as the fish swimsJ Exp Mar Biol Ecol213111CrossRefGoogle Scholar
  15. Rathbun, SL 1998Spatial modeling in irregularly shaped regions: kriging estuariesEnvironmetrics9109129CrossRefGoogle Scholar
  16. Schwarz, G 1978Estimating the dimension of a modelAnn Stat6461464Google Scholar
  17. Smith, RA, Schwarz, GE, Alexander, RB 1997Regional interpretation of water-quality monitoring dataWater Resour Res3327812798CrossRefGoogle Scholar
  18. Torgersen CE, Gresswell RE, Bateman DS (2004) Pattern detection in stream networks: quantifying spatial variability in fish distribution. In: Nishida, T. (ed), Proceedings of the Second Annual International Symposium on GIS/Spatial Analyses in Fishery and Aquatic Sciences. Fishery GIS Research Group, Saitama, JapanGoogle Scholar
  19. Hoef, JM, Barry, RP 1998Constructing and fitting models for cokriging and multivariable spatial predictionJ Stat Planning Inference69273294Google Scholar
  20. Hoef, JM, Cressie, N, Barry, RP 2004Flexible spatial models for kriging and cokriging using moving averages and the fast Fourier transform (FFT)J Comput Graphical Stat13265282CrossRefGoogle Scholar
  21. Yuan, LL 2004Using spatial interpolation to estimate stressor levels in unsampled streamsEnviron Monit Assess942338PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2006

Authors and Affiliations

  • Jay M. Ver Hoef
    • 1
    • 4
    Email author
  • Erin Peterson
    • 2
  • David Theobald
    • 3
  1. 1.Alaska Department of Fish and GameFairbanksUSA
  2. 2.Department of GeosciencesColorado State UniversityFort CollinsUSA
  3. 3.Natural Resources Ecology LabColorado State UniversityFort CollinsUSA
  4. 4.National Marine Mammal LaboratorySeattleUSA

Personalised recommendations