Topic (iv)

Title: Big Data (and official statistics)

Author: Piet Daas

In our modern world more and more data is generated on the web and produced by sensors in the ever increasing number of electronic equipment surrounding us. The amount and frequency at which these data are produced is commonly referred to as ‘Big Data’. The latter are data characterized by increasing volume, velocity and variety. Apart from being a engender of new opportunities in the private/commercial sector, Big Data is also a very interesting data source for official statistics; either on its own or as an additional source of information. However, harvesting the information from Big Data sources and incorporating it into a statistical production process is not an easy task. In this presentation the potential of Big Data for statistics is discussed and illustrated with examples of pioneering work in this area; particularly findings and experiences of analysing Dutch traffic loop detection data and social media messages are presented. Both Big Data sources provide rapidly available information on (potentially) important phenomena for statistics in the Netherlands.