Linear Parametric Models Applied to Daily Hydrological Series

Abstract

The aim of this paper is to describe, and solve in same cases, the problems that arise in hydrological daily time series modeling developed via linear parametric models. The preliminary analysis, the identification, and the simulation steps of the standard procedure are thoroughly studied. The effects of Box and Cox transformation are commented on, a procedure to smooth the seasonal component is described, and a new technique for the initial parameter estimation of fractional models is introduced and tested. The revised procedure was applied to the time series of Tevere daily flows.