Location Matters: Techniques for exploring geographic variation in survey data

Monday 27th June 2016 5pm

Northampton Suite, City University London, EC1V 0HB

Geography – and particularly where people live – matters and can have a profound effect on people’s attitudes, behaviour and outcomes. However, all too often, analyses of survey data ignore this geographic variation and are restricted to ‘one size fits all’ global models. This event introduced several techniques – including geographically weighted regression, small-area estimation and visualization – which can be used to explore low level geographic variation in survey data. Presentations demonstrated how these techniques can be used to address a range of methodological and substantive research questions relevant to social scientists.

The event was jointly organised  by the Royal Statistical Society Social Statistics Section and City University London.

Programme

Chris Brunsdon, NUI Maynooth ‘Why geography matters’

Kaisa Lahtinen, University of Liverpool ‘Using geographically weighted regression to explore spatial variation in survey non-response’

Nikos Tzavidis, University of Southampton ‘The role of geography in small area estimation’

Aidan Slingsby, City University London ‘Exploring survey results with visualization’