Page 294 - Special Topic Session (STS) - Volume 2

STS493 Sofie d.B. et al.
It is likely that from the big data perspective, survey data may be used as
complementary data in some settings. In the near future, the two starting
points may, in fact, lead to similar hybrid forms of data collection.
The most promising combinations of sensor data and survey data are those
that score well on all criteria. For the two examples, we found pairs of survey
topics and sensor measurements that potentially have a positive business case.
We make two recommendations: First, we advise to replicate our assessments
of the various criteria with experts in mobile device and wearable sensors,
especially for quality. Second, we propose to empirically test respondent
willingness to provide sensor data and to consent to linkage to existing
secondary data. Such experiments have emerged, but are yet at early stages.
Statistics Netherlands has defined an innovation strategy with a clear focus
on making policy relevant statistics based on new methods and new secondary
data sources. Sensor data offer great potential, but for an NSI the challenge
lies in data access (as data are often in the hands of private partners), concept
validation (do the sensor data measure the same as the survey data) and data
quality. In order for sensor data to be of any use for end users (and to become
part of an official statistical process), these issues still need to be addressed in
order to use sensor data as a secondary data for official business statistics. To
some extent NSIs lose control over the data collection. In order to gain some
control and address the challenges, we foresee another business model for
NSIs like Statistics Netherlands: Be a stakeholder and partner in emerging data
hubs from the very start, and be in close communication with the end-user.
The role of an NSI in these data hubs should be to enrich these data with
relevant statistical information, and assist in the use of statistical information.

References
1. De Vlieg, J. (2018), ‘A huge push in technology is coming’ (in Dutch: ‘Er is
een enorme push in technologie in aantocht’). Boerderij, 03: 19 (februari
2018).
2. Thomas, R., and P. McSharry (2015), Big Data Revolution: What Farmers,
Doctors, and Insurance Agents teach us about discovering Bog Data
Patterns. Wiley, Chichester, West Sussex, UK.
3. Van Dijk, C., and C. Kempenaar (2016), Open data for precision farming in
the Netherlands (in Dutch: Open data voor precisielandbouw in
Nederland). Wageningen Univeristy & Research, report 662. Wageningen,
Netherlands.
4. Vonder, M. (2017), Sensors going smart. Presentation at ‘Big Data Matters’
Seminar, Statistics Netherlands, 27 September 2017, Heerlen, Netherlands.
(TNO Netherlands)

283 | I S I W S C 2 0 1 9