One of the tasks of the Statistical Of®ce of the European Communities (EUROSTAT) consists in making available information on the Member States' economies. That information is subject to a statistical treatment in respect to some particular features of economic time series. Namely, the trading days rhythm, the Easter recess effect, some data irregularities, the series growth, and some unobserved movements like trend and seasonality are of main interest. In some units, all the related analysis is performed in a model-based framework through the use of the programs TRAMO-SEATS (see Gomez and Maravall 1996). The methodology implemented is that of univariate regression with time series of the ARIMA-type (see for example Bell 1995; Fuller 1996; Tsay 1984), plus some developments related to outlier detection and correction and to a full automised model identi®cation procedure (see Gomez 1997). These last two advances were crucial for a massive model-based treatment of time series. The Statistical Of®ce of the European Communities (EUROSTAT) publishes information on the economies of the Member States using, for some units, some model-based procedures to treat several features of economic time series. The quality of the information published is thus related to the capacity of these models, namely univariate ARIMA models with exogenous regressors, to adequately describe a vast majority of economic time series. We evaluate that capacity on a set of 13,238 monthly series. The results of our experiment give several messages: 1) the sensitivity of different economic indicators to calendar events can be quanti®ed; 2) the occurrences and the typology of outliers found in practice are detailed; 3) information is obtained about the stationary behavior of the series; 4) the practical relevance of several model speci®cations can be evaluated; 5) the type of misspeci®cations found is detailed, yielding for example an indication on nonlinear patterns actually encountered in monthly series.
[1]
Gabriele Fiorentini,et al.
Unobserved components in ARCH models: An application to seasonal adjustment
,
1996
.
[2]
G. C. Tiao,et al.
Estimation of time series parameters in the presence of outliers
,
1988
.
[3]
David F. Findley,et al.
New Capabilities and Methods of the X-12-ARIMA Seasonal-Adjustment Program
,
1998
.
[4]
W. Fuller,et al.
Introduction to Statistical Time Series (2nd ed.)
,
1997
.
[5]
E. Hannan,et al.
Recursive estimation of mixed autoregressive-moving average order
,
1982
.
[6]
Andrew Harvey,et al.
Forecasting, Structural Time Series Models and the Kalman Filter.
,
1991
.
[7]
R. Tsay.
Time Series Model Specification in the Presence of Outliers
,
1986
.
[8]
Richard A. Davis,et al.
Time Series: Theory and Methods
,
2013
.
[9]
Víctor Gómez,et al.
Programs tramo and seats: instructions for the user (Beta version, September 1996)
,
1996
.
[10]
A. I. McLeod,et al.
DIAGNOSTIC CHECKING ARMA TIME SERIES MODELS USING SQUARED‐RESIDUAL AUTOCORRELATIONS
,
1983
.
[11]
Gwilym M. Jenkins,et al.
Time series analysis, forecasting and control
,
1971
.
[12]
R. Fildes,et al.
The Impact of Empirical Accuracy Studies On Time Series Analysis and Forecasting
,
1995
.
[13]
Anton Schick,et al.
Regression Models with Time Series Errors
,
1999
.
[14]
D. A. Pierce.
Seasonal adjustment when both deterministic and stochastic seasonality are present
,
1978
.
[15]
V. M. Reyes Gomez,et al.
AUTOMATIC MODEL IDENTIFICATION IN THE PRESENCE OF MISSING OBSERVATIONS AND OUTLIERS
,
1998
.
[16]
G. Box,et al.
On a measure of lack of fit in time series models
,
1978
.
[17]
G. C. Tiao,et al.
Consistency Properties of Least Squares Estimates of Autoregressive Parameters in ARMA Models
,
1983
.