Skip to main content

Advantages of Geographically Weighted Regression for Modeling Benthic Substrate in Two Greater Yellowstone Ecosystem Streams

Abstract

Stream habitat assessments are commonplace in fish management, and often involve nonspatial analysis methods for quantifying or predicting habitat, such as ordinary least squares regression (OLS). Spatial relationships, however, often exist among stream habitat variables. For example, water depth, water velocity, and benthic substrate sizes within streams are often spatially correlated and may exhibit spatial nonstationarity or inconsistency in geographic space. Thus, analysis methods should address spatial relationships within habitat datasets. In this study, OLS and a recently developed method, geographically weighted regression (GWR), were used to model benthic substrate from water depth and water velocity data at two stream sites within the Greater Yellowstone Ecosystem. For data collection, each site was represented by a grid of 0.1 m2 cells, where actual values of water depth, water velocity, and benthic substrate class were measured for each cell. Accuracies of regressed substrate class data by OLS and GWR methods were calculated by comparing maps, parameter estimates, and determination coefficient r 2. For analysis of data from both sites, Akaike’s Information Criterion corrected for sample size indicated the best approximating model for the data resulted from GWR and not from OLS. Adjusted r 2 values also supported GWR as a better approach than OLS for prediction of substrate. This study supports GWR (a spatial analysis approach) over nonspatial OLS methods for prediction of habitat for stream habitat assessments.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. 1.

    Ian, M. (1999). The importance of physical habitat assessment for evaluating river health. Fresh Water Biology, 41(2), 373–391.

    Article  Google Scholar 

  2. 2.

    Aadland, L. P. (1993). Stream habitat types: their fish assemblages and relationship to flow. North American Journal of Fisheries Management, 13(4), 790–806.

    Article  Google Scholar 

  3. 3.

    Lazorchak, J.M., et al. (2000) Environmental monitoring and assessment program surface waters: Field operations and methods for measuring the ecological condition of non-wadeable rivers and streams: US Environmental Protection Agency, Office of Research and Development.

  4. 4.

    Lazorchak, J.M., et al. (1998) Field operations and methods for measuring the ecological condition of wadeable streams, E.P. Agency, Editor, US EPA. p. 270.

  5. 5.

    Sheppard, J. D., & Johnson, J. H. (1985). Probability-of-use for depth, velocity, and substrate by subyearling coho salmon and steelhead in Lake Ontario tributary streams. North American Journal of Fisheries Management, 5(2b), 277–282.

    Article  Google Scholar 

  6. 6.

    Legendre, P. (1993). Spatial autocorrelation: trouble or new paradigm? Ecology, 74(6), 1659–1673.

    Article  Google Scholar 

  7. 7.

    Sheehan, K. R., & Welsh, S. A. (2009). An interpolation method for stream habitat assessments. North American Journal of Fisheries Management, 29(1), 1–9.

    Article  Google Scholar 

  8. 8.

    González-Megías, A., Gómez, J. M., & Sánchez-Piñero, F. (2005). Consequences of spatial autocorrelation for the analysis of metapopulation dynamics. Ecology, 86(12), 3264–3271.

    Article  Google Scholar 

  9. 9.

    Charlton, M., Fotheringham, S. and Brunsdon, C.(2005) Geographically weighted regression. NCRM Methods Review Papers (NCRM/006).

  10. 10.

    Fotheringham, A. S., Charlton, M., & Brunsdon, C. (1996). The geography of parameter space: an investigation of spatial non-stationarity. International Journal of Geographical Information Science, 10(5), 605–627.

    Google Scholar 

  11. 11.

    Kupfer, J., & Farris, C. (2007). Incorporating spatial non-stationarity of regression coefficients into predictive vegetation models. Landscape Ecology, 22(6), 837–852.

    Article  Google Scholar 

  12. 12.

    Austin, M. (2007). Species distribution models and ecological theory: a critical assessment and some possible new approaches. Ecological Modelling, 200(1–2), 1–19.

    Article  Google Scholar 

  13. 13.

    Wang, L., et al. (2006) Effects of levels of human disturbance on the influence of catchment, riparian, and reach-scale factors on fish assemblages. American Fisheries Society.

  14. 14.

    Windle, M. J. S., et al. (2009). Exploring spatial non-stationarity of fisheries survey data using geographically weighted regression (GWR): an example from the Northwest Atlantic. ICES Journal of Marine Science, 67(1), 145–154.

    Article  Google Scholar 

  15. 15.

    Ali, K., Partridge, M. D., & Olfert, M. R. (2007). Can geographically weighted regressions improve regional analysis and policy making? International Regional Science Review, 30(3), 300.

    Article  Google Scholar 

  16. 16.

    Gao, X., Asami, Y., & Chung, C. J. F. (2006). An empirical evaluation of spatial regression models. Computers and Geosciences, 32(8), 1040–1051.

    Article  Google Scholar 

  17. 17.

    LeSage, J. P. (2001). A family of geographically weighted regression models. In L. Anselin, R. J. Florax, & S. J. Rey (Eds.), Advances in spatial econometrics (pp. 241–263). Berlin, Germany: Springer.

    Google Scholar 

  18. 18.

    Lo, C. P. (2008). Population estimation using geographically weighted regression. GIScience & Remote Sensing, 45(2), 131–148.

    Article  Google Scholar 

  19. 19.

    Mennis, J. (2006). Mapping the results of geographically weighted regression. The Cartographic Journal, 43(2), 171–179.

    Article  Google Scholar 

  20. 20.

    Zimmerman, D. (2003). Geographically weighted regression. Journal of the American Statistical Association, 98(463), 765–767.

    Article  Google Scholar 

  21. 21.

    Poole, G. C., Frissell, C. A., & Ralph, S. C. (1997). In-stream habitat unit classification: inadequacies for monitoring and some consequences for management. Journal of the American Water Resources Association, 33(4), 879–896.

    Article  Google Scholar 

  22. 22.

    Caddy, J. F. (1999). Fisheries management in the twenty-first century: will new paradigms apply? Reviews in Fish Biology and Fisheries, 9(1), 1–43.

    Article  Google Scholar 

  23. 23.

    Minns, C. K. (2001). Science for freshwater fish habitat management in Canada: current status and future prospects. Aquatic Ecosystem Health & Management, 4(4), 423–436.

    Article  Google Scholar 

  24. 24.

    Stephenson, R. L., & Lane, D. E. (1995). Fisheries management science: a plea for conceptual change. Canadian Journal of Fisheries and Aquatic Sciences, 52(9), 2051–5056.

    Article  Google Scholar 

  25. 25.

    Moran, P. A. P. (1950). Notes on continuous stochastic phenomena. Biometrika, 37(1–2), 17.

    CAS  Google Scholar 

  26. 26.

    Moran, P. A. P. (1953). The statistical analysis of the Canadian lynx cycle. I. Structure and prediction. Australian Journal of Zoology, 1(1), 163–173.

    Article  Google Scholar 

  27. 27.

    Jarque, C. M., & Bera, A. K. (1980). Efficient tests for normality, homoscedasticity and serial independence of regression residuals. Economics Letters, 6(3), 255–259.

    Article  Google Scholar 

  28. 28.

    Agresti, A. (2002). Categorical data analysis (Vol. 359). New York: Wiley.

    Book  Google Scholar 

  29. 29.

    Koenker, R. (1981). A note on studentizing a test for heteroscedasticity. Journal of Econometrics, 17(1), 107–112.

    Article  Google Scholar 

  30. 30.

    Charlton, M., Fotheringham, S. and Brunsdon, C. (2005) Geographically weighted regression. ESRC National Centre for Research Methods NCRM Methods Review Papers NCRM/006.

  31. 31.

    Burnham, K. P., & Anderson, D. R. (2002). Model selection and multimodel inference: a practical information–theoretic approach. New York: Springer.

    Google Scholar 

  32. 32.

    Brunsdon, C., Fotheringham, S. and Charlton, M. (2000) Geographically weighted regression as a statistical model. In Unpublished working paper, Department of Geography, University of Newcastle: Newcastle, UK.

  33. 33.

    Fotheringham, S., Brundson, C., & Charlton, M. (2002). Geographically weighted regression and associated techniques. England: Wiley.

    Google Scholar 

  34. 34.

    Meaden, G.J. (2000) Application of GIS to fisheries management. Marine and Coastal Geographical information Systems: p. 205–226.

  35. 35.

    Meaden, G.J. (2001) GIS in fisheries science: foundations for the new millennium. In First International Symposium on GIS in Fishery Science. Saitama, Japan: Fisheries Research Group.

  36. 36.

    Winemiller, K. O., Flecker, A. S., & Hoeinghaus, D. J. (2010). Patch dynamics and environmental heterogeneity in lotic ecosystems. Journal of the North American Benthological Society, 29(1), 84–99.

    Google Scholar 

  37. 37.

    Fisher, W. L. (2004). Future of geographic information systems in fisheries. In W. L. Fisher & F. J. Rahel (Eds.), Geographic information systems in fisheries (pp. 259–266). Bethesda, MD: American Fisheries Society.

    Google Scholar 

  38. 38.

    Fisher, W. L., & Rahel, F. J. (2004). Geographic information systems applications in stream and river fisheries. In W. L. Fisher & F. J. Rahel (Eds.), Geographic information systems in fisheries (pp. 49–84). Bethesda, MD: American Fisheries Society.

    Google Scholar 

  39. 39.

    Graham, M. H. (2003). Confronting multicollinearity in ecological multiple regression. Ecology, 84(11), 2809–2815.

    Article  Google Scholar 

  40. 40.

    Rosenfeld, J. (2003). Assessing the habitat requirements of stream fishes: an overview and evaluation of different approaches. Transactions of the American Fisheries Society, 132(5), 953–968.

    Article  Google Scholar 

  41. 41.

    Beisel, J. N., et al. (1998). Stream community structure in relation to spatial variation: the influence of mesohabitat characteristics. Hydrobiologia, 389(1), 73–88.

    Article  Google Scholar 

  42. 42.

    Gorman, O. T., & Karr, J. R. (1978). Habitat structure and stream fish communities. Ecology, 59(3), 507–515.

    Article  Google Scholar 

  43. 43.

    Gido, K.B., et al. (2006) Fish–habitat relations across spatial scales in prairie streams. In American Fisheries Society Symposium 48. Bethesda, Maryland: American Fisheries Society.

  44. 44.

    Robertson, G. P. (1987). Geostatistics in ecology; interpolating with known variance. Ecology (Durham), 68(3), 744–748.

    Article  Google Scholar 

  45. 45.

    Rosgen, D. L. (1994). A classification of natural rivers. Catena, 22(3), 169–199.

    Article  Google Scholar 

  46. 46.

    Rosgen, D.L., et al. (1985) A stream classification system. In: First North American Riparian Conference: Rocky Mountain Forest and Range Experiment Station. p. 91–95.

  47. 47.

    Montgomery, D. R., & Buffington, J. M. (1997). Channel-reach morphology in mountain drainage basins. Bulletin of the Geological Society of America, 109(5), 596.

    Article  Google Scholar 

  48. 48.

    Wintle, B. A., & Bardos, D. C. (2006). Modeling species–habitat relationships with spatially autocorrelated observation data. Ecological Applications, 16(5), 1945–1958.

    Article  CAS  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Kenneth R. Sheehan.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Sheehan, K.R., Strager, M.P. & Welsh, S.A. Advantages of Geographically Weighted Regression for Modeling Benthic Substrate in Two Greater Yellowstone Ecosystem Streams. Environ Model Assess 18, 209–219 (2013). https://doi.org/10.1007/s10666-012-9334-2

Download citation

Keywords

  • Geographically weighted regression
  • Ordinary least squares regression
  • Stream
  • River
  • Modeling
  • Regression fit
  • Stream management
  • Stream habitat assessment