Linear signal extraction with intervention techniques in non‐linear time series

Abstract

Seasonal adjustment is performed in some data-producing agencies according to the ARIMA-model-based signal extraction theory. A stochastic linear process parametrized in terms of an ARIMA model is ®rst ®tted to the series, and from this model the models for the trend, cycle, seasonal, and irregular component can be derived. A spectrum is associated to every component model and is used to compute the optimal Wiener± Kolmogorov ®lter. Since the modelling is linear, prior linearization of the series with intervention techniques is performed. This paper discusses the performance of linear signal extraction with intervention techniques in nonlinear processes. In particular, the following issues are discussed: (1) the ability of intervention techniques to linearize time series which present nonlinearities; (2) the stability of the linear projection giving the components estimators under non-linear misspeci®cations; (3) the capacity of the WK ®lter to preserve the linearity in some components and the non-linearities in others. #

Seasonal Adjustment of Bank Deposits and Loans

“…Tuttavia, gli effetti di regressione deterministici, tra i quali gli outlier rimossi da TRAMO, vengono reincorporati nelle componenti di ciclo-trend, stagionale e irregolare stimate da SEATS. In particolare, i cambiamenti di livello sono assegnati alla componente di trend, mentre i valori anomali additivi e le rampe temporanee sono allocate nella componente irregolare (Planas, 1998).…”

Bias Reduction for Linearized Nonlinear Regression Models by Simulation Estimations

“…Some works that investigate linearized nonlinear regression equations include Butler and Schachter (1986), Byron and Bera (1983), Lee (1989a), Nguyen (1984), Planas (1998), Protopapadakis (1983), and Srivastaba and Singh (1989) for various topics. Many nonlinear models are, however, commonly linearized by using a Taylor series expansion to obtain linear regression models.…”