This paper examines and compares analytical tools in analysis of economic statistical data, econometric modeling, and neural network, soft-computing modeling, as representation models for time series processing in forecasting, decision and control. In addition, a novel forecasting model using Elman networks is proposed. A comprehensive experiment in applying the latter modeling has been carried out, some specific applications software developed, and a number of benchmark series from the literature processed. This paper reports on comparison findings as well on the use of our application software package which encompasses routines for regression, ARIMA and NN analysis of time series. The comparison analysis is illustrated by a sample example known as difficult to model via any technique. Copyright - World Automation Congress (WAC) 2006.