Data Collection surrounds our modern lives. From sensors in smartphones to connected cars linking with roadside monitors to read air pollution, data is everywhere. There are over 20 billion devices currently connected to the internet. Cisco predicts this will be 500 billion by 2030. We recognise the challenge this poses for modern Statistical methods. They are poor and outdated. They cannot analyse the data effectively and most of this streamed data which could be used for societal and economical good, is simply being lost.
The ‘StatScale: Statistical Scalability for Streaming Data’ programme worked to develop new ways to interpret this data. A collaboration between both Lancaster University and University of Cambridge, it involved research with industrial partners including AstraZeneca, BT and Shell UK. The programme included £2.8m funding from EPSRC. StatScale benefitted from its significant partnerships with industry and these collaborations. These helped inform StatScale's research agenda and supported the research to make a direct economic and societal benefit.
StatScale’s theoretical and methodological work forms the basis of the next generation of scalable statistical algorithms. This is essential to ensure the UK’s competitive edge in science and technological industries. From smart watches to instrumented oil fields, StatScale has had individual, national and global effects. The programme is led by Professors Idris Eckley and Paul Fearnhead from Lancaster University, and Professor Richard Samworth and Dr Rajen Shah at the University of Cambridge.