The Bayesian Spatial Bradley–Terry Model: Urban Deprivation Modeling in Tanzania
share
Finding the deprived areas in any country or city can allow policy makers to design interventions which support citizens in these areas. Locating these areas is often challenging in developing countries where official statistics may not be collected or are unreliable. Comparative judgement models, such as the Bradley–Terry model, offer a solution leveraging local knowledge by comparing different areas based on affluence. Existing comparative judgement methods require a large amount of data to be collected, which can be expensive and time consuming, particularly in developing countries. In this article we develop the Bayesian Spatial Bradley–Terry model, which substantially decreases the amount of data that needs to be collected. We do this by constructing a network representation of the city and incorporating an assumption of spatial smoothness, meaning we can learn about the level of deprivation in one area from neighbouring areas. We demonstrate our method on a novel comparative judgement data set collected in Dar es Salaam, Tanzania, where we are able to identify several slums and the level of deprivation of each slum.
READ FULL TEXT
