On the application of the Bootstrap to assess the risk of deficient annual inflows to a reservoir
- 36 Downloads
The paper considers the problem of univariate model selection in order to assess the risk of sequences of deficient annual inflow sums to a reservoir. A selection criterion is proposed which emphasises the fit of a model to the lower tail of the empirical distribution function. The expectation of the discrepancy between the operating and approximating models is estimated using the Bootstrap algorithm. The Bootstrap is also used to estimate confidence intervals about an estimated percentile and these are compared to those found using conventional asymptotic estimators. Applications are given for three South African reservoirs.
Key wordsDeficient annual inflows univariate model selection bootstrap confidence intervals
Unable to display preview. Download preview PDF.
- Efron, B., 1982, The jackknife, the bootstrap and other resampling plans, CBMS-NSF Regional Conference Series in Applied Mathematics, Monograph 38, Society for Industrial and Applied Mathematics, Philadelphia.Google Scholar
- Efron, B., 1986, Better bootstrap confidence intervals, JASA 82, No. 397, 171–185.Google Scholar
- Linhart, H. and Zucchini, W., 1986, Model Selection, J. Wiley, New York.Google Scholar
- McMahon, T. A. and Srikanthan, R., 1982, Probability of extreme low flows of various durations, Proceedings of the Exeter Symposium. Optimal Allocation of Water Resources. IAHS Publications No. 135. pp 31–35.Google Scholar
- Stedinger, J., 1983, Confidence intervals for design events J. Hydraul. Eng. Div., ASCE 109, 13–27.Google Scholar
- Zucchini, W. and Adamson, P. T., 1988, Bootstrap confidence intervals for design storms from exceedance series, Hydrological Sciences Journal, in press.Google Scholar