JDemetra+
JDemetra+ implements the main seasonal adjustment methods: TRAMO-SEATS and X13-ARIMA-SEATS, in addition offers several other procedures to analyse time series data (benchmarking, temporal disaggregation, nowcasting). It is an open-source Java application, also available through R APIs, and provides both a command line interface (CLI), and graphical interface (GUI). JDemetra+ is also extensible with custom Java plugins.
Istat uses version 2 and collaborates on the development of version 3.
JDemetra+ allows to:
- import time series data from a wide range of sources;
- Process the data using advanced seasonal adjustment techniques;
- Visualize time series and analysis outputs: seasonally adjusted series and the trend, seasonal, and irregular components; view frequency domain charts such as spectra and periodograms;
- Examine the parameters of seasonal adjustment models in detail;
- Evaluate the seasonal adjustment process through appropriate diagnostic tools.
Internal users in Istat can use JDemetra+ (v2) in statistical production processes through the following platforms:
- Cruncher (CLI) (links: https://github.com/jdemetra/jwsacruncher and https://cran.r-project.org/web/packages/rjwsacruncher);
- RJDemetra (R);
- RJDProcessor (R with advanced diagnostics);
- SINTESI Platform (Java-based web application) with JSON input produced by RJDProcessor, coming soon.
In addition, the graphical user interface (GUI, available at https://github.com/jdemetra/jdemetra-app) can also be used for model selection.
Users external to the Institute, can use JDemetra+ in either version 2 or 3 via the graphical interface (GUI) and through the following platforms:
- Cruncher (CLI) (links: https://github.com/jdemetra/jwsacruncher and https://cran.r-project.org/web/packages/rjwsacruncher);
- RJDemetra (v2, R);
- RJDProcessor (v2, R with advanced diagnostics);
- Java (v2), compatible with JSON input from the SINTESI platform;
- rjdverse libraries (v3). Available from CRAN:
Status: Validated
Author: National Bank of Belgium, INSEE, INE, Bundesbank
License: EUPL-1.2
GSBPM codes: 6.1 (5.7)
Programming Language: Java, R
GUI Language Version: ENG
Keywords: Seasonal adjustment, benchmarking, time series
Contact: Name: Alessandro Piovani, email: alessandro.piovani@istat.it – Name: Giancarlo Lutero, email: lutero@istat.it
Technical requirements
JDemetra+ version 2: Java 8 (JRE) or higher, R environment, and rJava library for RJDemetra. If you wish to compile the Java code, a Java Development Kit (JDK) is required in addition to the Java Runtime Environment (JRE).
JDemetra+ version 3: Java 17 (JRE) or higher, R environment, and rJava library for rjdverse libraries. If you wish to compile the Java code, a Java Development Kit (JDK) is required in addition to the Java Runtime Environment (JRE).
Copyright
National Bank of Belgium (2016), EUPL license.
The work may not be used except in compliance with the License. A copy of the License can be obtained at: http://ec.europa.eu/idabc/eupl.html.
Unless otherwise required by applicable law or agreed to in writing, software distributed under the License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and limitations under the terms of the License.
Disclaimer
Istat does not assume responsibility for results deriving from a use of the tool that is not consistent with the methodological indications contained in the available documentation.
Download
- JDemetra+
- RJDemetra CRAN
- rjdverse R packages (v3), available from CRAN:
Technical and methodological documentation
https://jdemetra-new-documentation.netlify.app/
https://github.com/jdemetra (Wiki section of the various repositories)