Inter-relationships between geographical scale, socio-economic data suppression and population homogeneity

Over time, technology has greatly enhanced access to vast amounts of public data in government datasets. At the same time there been an increase ‘neighbourhood’ level research, which researchers typically select administrative unit for their analysis. As demand driven insights and decision making continues rise, face a tradeoff between suppression (to protect privacy citizens) homogeneity (the similarity individuals within area given characteristics). In this paper, we explore extent that different scales geography impact spatial using intra-class correlation D-Statistic. We use age, sex, ethnicity, education income from 2013 New Zealand Census assess a) are suppressed, b) these variables across 5 ‘small area’ available NZ. The used paper was accessed via Integrated Data Infrastructure (IDI), large repository de-identified, linked microdata obtained agencies, nationally representative surveys. study Meshblock, Statistical Area 1, Zone, 2 Unit, each can be analyse patterns at scale. found Zones suitable choice undertaking analyses census as they represent a’medium’ scale designed reduce while maintaining reasonable levels population homogeneity. policy implications research relate zone design decisions relating definition ‘a small cell count’ dissemination users sociodemographic data.