Work Package 2

Work Package 2 - Extended set of information

Lead participant: CBS


Start month: May 2018

End month: October 2019


The work package objective is to extend the actual set of information available on well-being and sustainability to include new data sources (eg big data) able to derive coherent indicators for local analysis and disaggregation for other domain.
The big data sources can provide useful data to estimate statistics of living conditions and poverty at local level. The overall aim of the work package is to study the usefulness of various non-traditional sources of data, `big data’ for improving the timeliness and accuracy of the measurement of the key SDGs indicators. Here we aim at considering the multidimensional aspects of sustainability, trying to go beyond the classical viewpoint on sustainability based on a large number of juxtaposed indicators to monitor the development of countries and of areas. The various kinds of data used in the work package include satellite data, mobile phone data, data from retail on prices and goods purchases (via scanners and customer cards), Internet via web scrapping, transaction level data from commercial banks, data on road toll payments, data on the use of energy and on the structure of establishments and firms.
The over-arching goal through the specific tasks is to investigate the transferability and applicability of good practices developed in particular countries to the other national data collection contexts. The statistical quality of the direct estimates of poverty, inequality and living conditions indicators can be reinforced using small area estimation techniques and model based estimates.
High-resolution satellite imagery and remote-sensing data are potential data sources for crop estimations and other statistics related to land use, land cover and agriculture all of significant impact on sustainability. Therefore, these sources can potentially provide useful information related to the measurement of well-being and sustainability.
This concerns indicators for achieving sustainable goals like
- healthy lives and promote well-being;
- inclusive and equitable quality education;
- gender equality;
- sustained, inclusive and sustainable economic growth;
- sustainable consumption and production patterns;
- combat climate change and its impacts.
The indicators from ‘big data’ sources will be validated against the more traditional ones from national statistical authorities. Working in cooperation with the providers and users of data will insure the usefulness and dissemination of the elaborated practices.

Description of work:

The main specific tasks within WP2 aimed at achieving the objectives are the followings:

Task T2.1: Methodological development using new data sources (e.g. big data) and integration of data and small area estimation of SDGs indicators (data linking, metadata, reconciliation of multiple datasets, visualisation, mapping).

Task T2.2: The purpose of this task is to construct indicators based on big data sources to complement the framework for well-being and sustainability indicators defined in WP1. This will be done carrying out an analysis of relevant data on social dynamic and wellbeing – pointing out critical aspects on timeliness analysis, quality aspects of data and data disaggregation and overview of the various non-traditional sources of data, their needs, collection of good practices, and implementation recommendations.
Statistics Netherlands’ Centre for Big Data Statistics (CBDS), which will participate in this project, has experience with constructing and deriving statistical indicators from data sources not primarily designed for statistical purposes, e.g.: a sentiments index derived from social media messages to supplement the consumer confidence index.

Task T2.3: Destatis uses multispectral satellite images from the European Copernicus earth for the classification of land cover and land use and for updating the register of addresses and buildings for the next census. Within this task, remote sensing data and - if applicable - complementary data sources will be assessed for their use for the construction of (composite) land and agriculture related wellbeing and sustainability indicators.


D2.1: Report on aspects of existing database and traditional and non-traditional data sources and collection of good practices and recommendation.

D2.2: Report on methodological aspects for using big data.

D2.3: Report on identification of future research needs in terms of statistical methodologies and new data.


Events calendar