Skip to Content
Use COVID-19 Alert Level 2 contact tracing form when on campus.
Doctor of Philosophy, (Science)
Study Completed: 2016
College of Sciences
Tree based models for poverty estimation
Small area estimation techniques are used to estimate poverty across small geographic domains within a country. These estimates are then displayed on a poverty map and used by the World Food Programme and other aid organisations for efficient allocation of resources. Current methodology for poverty estimation employs a regression modelling approach. Mrs Bilton developed an alternative technique based on classification and regression trees. She amalgamated probability-based predictions from the tree-based models to provide small area estimates of poverty, and developed a method for calculating standard errors for these estimates when the survey data has a complex design structure. Her research findings showed that the tree-based methodology is easier to automate and gives results comparable to the standard method.
Professor Geoff Jones
Dr Siva Ganesh
Page authorised by Web Content Manager
Last updated on Tuesday 04 April 2017