Nowcasting Austrian Short Term Statistics
-
Fröhlich, Markus [1]
-
[1] Statistics Austria
-
- Localización: Journal of official statistics, ISSN 0282-423X, Vol. 34, Nº. 2, 2018, págs. 503-522
- Idioma: inglés
- Enlaces
-
Resumen
Early estimates for Austrian short term indices were produced using multivariate time-series models. The article presents a simulation study with different models (vector error correction models, vector autoregressive models in levels – both with unadjusted and seasonally adjusted time-series) used for estimating total turnover, production, etc. In a preliminary step, before time-series were provided for nowcasting, the data had to undergo an editing process. In this case a time-series approach was selected for data-editing as well, because of the very specific structure of Austrian enterprises. For this task basically the seasonal adjustment program X13Arima-Seats was used for identifying and replacing outlying observations, imputation of missing values and generating univariate forecasts for every single time series.
