Page 351 - Contributed Paper Session (CPS) - Volume 4

CPS2259 Florabela Carausu et al.
Big Data can directly or indirectly benefit policy making, if the associated
risks are adequately prevented, by:
- answering new questions and producing new indicators;
- bridging time lags in the availability of official statistics and supporting
the timelier forecasting of indicators;
- providing an innovative data source in the production of official
13
statistics.
Mobile positioning data, a Big Data source, can offer the possibility to detect
daily commuting flows, allowing for the delineation of LMAs or offers the
possibility for population estimates.
Other statistical techniques may include the downscaling of socio
economic indicators based on grid cells and GIS opportunities; see
ESPON(2011): Disaggregation of socioeconomic data into a regular grid and
combination with other types of data.

At European level, Eurostat promotes and finances exploratory analyses of
functional areas, such as the Labour Market Areas (LMA); see
https://ec.europa.eu/eurostat/cros/content/labour-market-areas_en

More recently, Eurostat has entrusted to the consulting company GOPA
Luxembourg S.a r.l in collaboration with the University of Trier, a study on
‘Small Area Estimation (SAE) for city statistics and other functional areas (part
II)’. The objective of the study is to test more sophisticated Small Area
Estimation (SAE) methods and to produce guidelines to Eurostat and the NSIs
on how to estimate data from social surveys such as the Survey on Income
and Living Conditions (SILC) and the Labour Force Survey (LFS) at city and
Functional Urban Area (FUA) level. The main outcome will be a set of
guidelines proposing a sound methodology using SAE (and other method
such as cluster analysis and probability statistics) to calculate variables and
indicators of interest. The guidelines should be applicable to all kind of social
surveys, not only the SILC. The guidelines will be finalised by mid-2019.
The study is a continuation of ‘Small Area Estimation (SAE) for city
14
statistics and other functional areas (part I)’ which tested the application of
SAE methods on the Urban Audit city data collection on the basis of the
indicator Share of Persons at Risk of Poverty or Social Exclusion.

13 See IMF Staff Discussion Note: ‘Big Data: Potential Challenges and Statistical Implications’,
SDN/17/06, September 2017
14
https://circabc.europa.eu/webdav/CircaBC/ESTAT/regstat/Library/Working%20Group%20Meet
ing%202017/Documents/9.3%20E4_REG_2017_93_Annex_SAE%20for%20City%20statistics.pdf
340 | I S I W S C 2 0 1 9