Applying and Interpreting Model-Based Seasonal Adjustment

Abstract Bell (2012) catalogued unit root factors contained in linear filters used in seasonal adjustment (model-based or from the X-11 method) but noted that, for model-based seasonal adjustment, special cases could arise where filters could contain more unit root factors than was indicated by the general results. This article reviews some special cases that occur with canonical ARIMA model based adjustment in which, with some commonly used ARIMA models, the symmetric seasonal filters contain two extra nonseasonal differences (i.e., they include an extra (1 - B)(1 - F)). This increases by two the degree of polynomials in time that are annihilated by the seasonal filter and reproduced by the seasonal adjustment filter. Other results for canonical ARIMA adjustment that are reported in Bell (2012), including properties of the trend and irregular filters, and properties of the asymmetric and finite filters, are unaltered in these special cases. Special cases for seasonal adjustment with structural ARIMA component models are also briefly discussed.

Download Full-text

Illuminating ARIMA model-based seasonal adjustment with three fundamental seasonal models

SERIEs ◽

10.1007/s13209-016-0139-4 ◽

2016 ◽

Vol 7 (1) ◽

pp. 11-52 ◽

Cited By ~ 2

Author(s):

David F. Findley ◽

Demetra P. Lytras ◽

Agustin Maravall

Keyword(s):

Arima Model ◽

Seasonal Adjustment ◽

Model Based

Download Full-text

Enhanced Methods of Seasonal Adjustment

Econometrics ◽

10.3390/econometrics9010003 ◽

2021 ◽

Vol 9 (1) ◽

pp. 3

Author(s):

D. Stephen G. Pollock

Keyword(s):

Fourier Transform ◽

Computer Program ◽

High Frequency ◽

Seasonal Adjustment ◽

Frequency Noise ◽

Conventional Model ◽

High Frequency Noise ◽

Model Based ◽

At Will

The effect of the conventional model-based methods of seasonal adjustment is to nullify the elements of the data that reside at the seasonal frequencies and to attenuate the elements at the adjacent frequencies. It may be desirable to nullify some of the adjacent elements instead of merely attenuating them. For this purpose, two alternative sets of procedures are presented that have been implemented in a computer program named SEASCAPE. In the first set of procedures, a basic seasonal adjustment filter is augmented by additional filters that are targeted at the adjacent frequencies. In the second set of procedures, a Fourier transform of the data is exploited to allow the elements in the vicinities of the seasonal frequencies to be eliminated or attenuated at will. The question is raised of whether an estimated trend-cycle trajectory that is devoid of high-frequency noise can serve in place of the seasonally adjusted data.

Download Full-text