Modelos para Datos de la Economía Canaria en los Dominios del Tiempo y de la Frecuencia

Abstract

The use of numerical algorithms related to rational approximation of functions and the Fourier and wavelets transforms have focused our research. In this paper we present a summary with the main results from the methodological approach in time series models. They are illustrated for economic data series in the Canary Islands in two relevant sectors for the insular economy, namely, the banana crop, with suffers a worrying decline in the entire region, and the water consumption, a scarce resource in the city of Santa Cruz de Tenerife. In the first case, models in the time domain are considered, in particular, Transfer Functions models in the context of the Box-Jenkins approach, that are also extended to include input expectations. In the second case, , the wavelets transform is considered to identify the frequency indexes in the series. This tool allows us to obtain both properties in the time domain and the frequency domain, thus enriching the findings obtained using the Fourier transform.