HR: 0800h
AN: H11C-0652    [Abstracts]
TI: Comparing Least Squares and Robust Methods in Linear Regression Analysis of the Discharge of the Flathead River, Northwestern Montana.
AU: * Bell, A L
EM: angie.bell@umontana.edu
AF: Geosciences Department, University of Montana, 32 Campus Drive, Missoula, MT 59812, United States
AU: Moore, J N
EM: johnnie.moore@umontana.edu
AF: Geosciences Department, University of Montana, 32 Campus Drive, Missoula, MT 59812, United States
AU: Greenwood, M C
EM: greenwood@math.montana.edu
AF: Department of Mathematical Sciences, Montana State University-Bozeman, PO Box 17200, Bozeman, MT 59717, United States
AB: The Flathead River in Northwestern Montana drains the relatively pristine, high-mountain watersheds of Glacier- Waterton national parks and large wilderness areas making it an excellent test-bed for hydrologic response to climate change. Flows in the North Fork and Middle Fork of the Flathead River are relatively unmodified by humans, whereas the South Fork has a large hydroelectric reservoir (Hungry Horse) in the lower end of the basin. USGS stream gage data for the North, Middle and South forks from 1940 to 2006 were analyzed for significant trends in the timing of quantiles of flow to examine climate forcing vs. direct modification of flow from the dam. The trends in timing were analyzed for climate change influences using the PRISM model output for 1940 to 2006 for the respective basin. The analysis of trends in timing employed two linear regression methods, typical least squares estimation and robust estimation using weighted least squares. Least squares estimation is the standard method employed when performing regression analysis. The power of this method is sensitive to the violation of the assumptions of normally distributed errors with constant variance (homoscedasticity). Considering that violations of these assumptions are common in hydrologic data, robust estimation was used to preserve the desired statistical power because it is not significantly affected by non-normality or heteroscedasticity. Least squares estimated trends that were found to be significant, using a 10% significance level, were typically not significant using a robust estimation method. This could have implications for interpreting the meaning of significant trends found using the least squares estimator. Utilizing robust estimation methods for analyzing hydrologic data may allow investigators to more accurately summarize any trends.
DE: 1805 Computational hydrology
DE: 1807 Climate impacts
DE: 1808 Dams
DE: 1834 Human impacts
SC: Hydrology [H]
MN: 2007 Fall Meeting