Online Program

Sampling Subpopulations using Partial Lists, Imperfect Census Data and Rough Screening Questions

*Robert Graham Clark, University of Wollongong 

Keywords: sampling HTR populations, disproportionate sampling, multi-stage surveys, dual frames, sample design

The Maori peoples are the indigenous population of New Zealand (NZ), and as such are important for social, political and historical reasons. Comprising 14% of of NZ adults, they have higher rates of economic disadvantage and illness than the general population and so are a particular priority in public health planning. For all these reasons, many surveys in NZ aim to over-sample Maori, to give more precise statistics than would be produced by an untargeted survey of the population. This population shares some characteristics with other hard to reach populations: it is relatively rare, over-surveyed, and geographically dispersed, and there is no adequate population frame. There are some unique features as well: Maori are less rare than many indigenous populations, and have a special status in the NZ electoral system, so that the Electoral Roll provides a useful partial frame. A combination of strategies to oversample Maori in the NZ Health Survey is found to work well. A novel approach to setting the large number of design parameters required by this design is described, based on numerical optimization using a training and validation dataset.