TERMIUM Plus^®

Fiche 1,  Justifications,  Anglais

Record number: 1, Textual support number: 1 DEF

A modeling process by which variation in a time series are assumed to be explained wholly by the historical trends of the data itself. In essence, the ARIMA modeling process consists of the autoregressive and moving average processes of the Auto-Regressive Moving Average (ARMA) Model process on data that have been Differenced to render them Stationary. The process uses variations of differencing and transformations to describe historical patterns in the data. Like the simpler ARMA model, forecasts made by an ARIMA modeling process consist of only a mathematical process of projecting inherent characteristics of trend, cycles, and seasonality into the future and incorporate no economic relatinships. Consequently, such models are not appropriate for impact analysis or for incorporating random "shocks", but may prove an effective estimation process when the trends in the historical data are relatively stable and well-behaved.  1, fiche 1, Anglais, - auto%2Dregressive%20integrated%20moving%20average%20process

Record number: 1, Textual support number: 1 OBS

The X-11 ARIMA process is used to detect and remove the seasonality from the original data.  4, fiche 1, Anglais, - auto%2Dregressive%20integrated%20moving%20average%20process

Fiche 1,  Justifications,  Français

Record number: 1, Textual support number: 1 OBS

Dans divers travaux d'économétrie on fait [...] usage de processus mixtes, dits «autorégressifs de moyennes mobiles» [...].  2, fiche 1, Français, - processus%20autor%C3%A9gressif%20de%20moyennes%20mobiles%20int%C3%A9gr%C3%A9es

Fiche 1,  Justifications,  Espagnol