 2011 Royal Statistical Society 0964–1998/11/174931 J. R. Statist. Soc. A (2011) 174, Part 4, pp. 931–951 Small area estimation using a reweighting algorithm Robert Tanton,Yogi Vidyattama, Binod Nepal and Justine McNamara University of Canberra, Australia [Received June 2009. Final revision January 2011] Summary. The paper describes a method of small area estimation which uses a reweighting algorithm to reweight survey data to a number of known totals (benchmarks) for small areas. The method has so far been used to estimate small area poverty rates and housing stress. The method gives poverty rates for small areas that are similar to those available from the 2006 Australian census, when the same definition of poverty was used.Various methods of validating the poverty rates have been used, including aggregating the poverty rates to a larger area and comparing them with official Australian Bureau of Statistics estimates from a survey, and apply- ing the spatial microsimulation to larger areas and comparing with official Australian Bureau of Statistics survey results. Both these tests show that the estimates are comparable and fairly robust for most states in Australia. Keywords: Poverty; Small area estimation; Spatial microsimulation 1. Introduction In recent years, many international statistical agencies have used sample surveys to enable richer data to be obtained at a cheaper cost, and with less total respondent burden, than using a cen- sus of the whole population. Since the 1960s, they have been used extensively by the Australian Bureau of Statistics (ABS) to gather information on a range of topics. One of the problems with official sample surveys from the ABS is that the samples are designed to provide estimates for Australian states and territories, but not for many areas that are smaller than these. In particular, in the less populous states of Australia, like the Northern Territory and Tasmania, sample surveys do not provide reliable estimates below state level. Small area estimation techniques overcome this limitation to a large extent. A summary of the small area estimation literature (Pfeffermann, 2002) outlines statistical methods being used to calculate small area estimates from survey data. Work has been done at the ABS in Australia on small area estimation (Australian Bureau of Statistics, 2005, 2006a), a small area estimation technique is used by an Australian Government department to produce small area estimates of labour force status (Department of Education Employment and Workplace Relations, 2009) and the Office for National Statistics in the UK has also produced results from small area estimation models (Bates, 2006). This paper illustrates a method for small area estimation using spatial microsimulation. The general method used is a reweighting technique, which reweights a sample survey file. There are various ways of doing this including combinatorial optimization (Voas and Williamson, 2000), iterative proportional fitting (Birkin and Clarke, 1989) and generalized regression (Tanton, 2007). One of the advantages of spatial microsimulation using a reweighting technique is Address for correspondence: Robert Tanton, National Centre for Social and Economic Modelling, University of Canberra, University South Drive, Canberra, ACT 2601, Australia. E-mail: Robert.Tanton@natsem.canberra.edu.au