Econometric software for seasonal adjustment and other time series methods (JDemetra+)
JDemetra+ is a new tool for seasonal adjustment (SA) developed by the National Bank of Belgium (NBB) in cooperation with the Deutsche Bundesbank and Eurostat in accordance with the Guidelines of the European Statistical System (ESS).
Besides seasonal adjustment, JDemetra+ bundles other time series models that are useful in the production or analysis of economic statistics, including for instance outlier detection, nowcasting, temporal disaggregation or benchmarking.
From a technical point of view, JDemetra+ is a collection of reusable and extensible Java components, which can be easily accessed through a rich graphical interface. The software is a free and open-source software (FOSS) developed under the EUPL licence.
JDemetra+ has been officially recommended, since 2 February 2015, to the members of the ESS and the European System of Central Banks as software for seasonal and calendar adjustment of official statistics.
Seasonal adjustment (SA) is a widely used technique for estimating and removing seasonal and calendar-related movements from time series in order to provide users with data enabling a clear understanding of economic phenomena.
The functionalities of JDemetra+ include:
- SA with TRAMO/SEATS and X-12-ARIMA
- Structural models and other advanced model-based SA methods
- Facilities for regular data production, like define, save and refresh SA processing
- Definition and handling of specific calendars
- Efficient processing of large datasets in batch mode
The Eurostat-ECB Seasonal Adjustment Expert Group (SAEG) plays a key role in the governance structure of JDemetra+ through the development of coordinated activities that guarantee compliance with the EES Guidelines for Seasonal Adjustment. This is done in close cooperation with the Seasonal Adjustment Centre of Excellence (SACE), which is a consortium of experts from National Statistical Institutes, and with the developers of the software. The SACE provides methodological and technical support through the ESS Seasonal Adjustment Helpdesk and collaborates with Eurostat in the organisation of training courses for users as well as for developers.
The JDemetra+ environment bundles alternative methods for time series analysis. They are available in separate modules (plugins) that can be added to the core application.
Temporal disaggregation and benchmarking
Temporal disaggregation methods disaggregate low-frequency (annual) series to high frequency (quarterly, monthly) series using some high-frequency information. Benchmarking methods adjust data in order to take into account some constraints while preserving the main statistical properties of the initial data. Both statistical methods use very similar techniques and are widely used in the compilation of the Quarterly National Accounts.
Nowcasting is often defined as the prediction of the present, the very near future and the very recent past. The plugin developed at the NBB helps to operationalise the process of nowcasting. It can be used to specify and estimate dynamic factor models and visualise how the real-time dataflow updates expectations, as for instance in Banbura and Modugno (2010). The software can also be used to perform pseudo out-of-sample forecasting evaluations that consider the calendar of release dates for all variables, contributing to the formalisation of the nowcasting problem originally proposed by Giannone, et al. (2008) or Evans (2005).
JDemetra+ can run on multiple platforms such as Windows, Mac OS X and Linux (Java SE is required to run it).
To install, download the latest version, unzip it somewhere and launch the executable in "/bin".
The SACE has elaborated an extensive documentation, available through the CROS - PORTAL:
- Quick start is an introduction to the JDemetra+ functions for seasonal adjustment, including details regarding installation. (PDF version)
- User guide includes step-by-step descriptions of how to perform a typical analysis of seasonal data and useful tips that facilitate replication of the results with the user’s own data and working instructions. (PDF version)
- Reference manual covers all available JDemetra+ functionalities, options and functions available through the interface. (PDF version)