THE MOVING BLOCKS BOOTSTRAP VERSUS PARAMETRIC TIME-SERIES MODELS

The application of a parametric time series model to a water resources problem involves selecting a model and estimating its parameters, bot h steps adding uncertainty to the analysis. The moving blocks bootstra p is a simple resampling algorithm which can replace parametric time s eries models, avoiding model selection and only requiring an estimate of the moving block length. The moving blocks bootstrap resamples the observed time series;using approximately independent moving blocks. A Monte Carlo experiment is performed involving the use of a time series model to estimate the storage capacity S of a surface water reservoir . Our results document that the bootstrap always produced storage esti mates with lower root-mean-square-error than a parametric alternative, even when no model error is introduced into the parametric scheme. Th ese results suggest that the moving blocks bootstrap can provide a sim ple and attractive alternative to more complex multivariate ARMA model s.