Corrected prediction intervals for change detection in paired watershed studies |
| |
Authors: | Nicholas A Som Nicolas P Zégre Lisa M Ganio Arne E Skaugset |
| |
Institution: | 1. Department of Forest Ecosystems and Society , Oregon State University , Corvallis , Oregon , 97331 , USA somn@onid.orst.edu;3. Division of Forestry and Natural Resources, West Virginia University , Morgantown , West Virginia , 26506 , USA;4. Department of Forest Ecosystems and Society , Oregon State University , Corvallis , Oregon , 97331 , USA;5. Department of Forest Engineering , Resources and Management, Oregon State University , Corvallis , Oregon , 97331 , USA |
| |
Abstract: | Abstract Hydrological data may be temporally autocorrelated requiring autoregressive process parameters to be estimated. Current statistical methods for hydrological change detection in paired watershed studies rely on prediction intervals, but the current form of prediction intervals does not include all appropriate sources of variation. Corrected prediction intervals for the analysis of paired watershed study data that include variation associated with covariance and linear model parameter estimation are presented. We provide an example of their application to data from the Hinkle Creek Paired Watershed Study located in the western Cascade foothills of Southern Oregon, USA. Research implications of using the correct prediction limits and incorporating the estimation uncertainty of autoregressive process parameters are discussed. Editor D. Koutsoyiannis Citation Som, N.A., Zégre, N.P., Ganio, L.M. and Skaugset, A.E., 2012. Corrected prediction intervals for change detection in paired watershed studies. Hydrological Sciences Journal, 57 (1), 134–143. |
| |
Keywords: | paired watershed study generalized least squares Prasad-Rao mean-squared error estimator stream discharge time series |
|
|