Page 75 - Special Topic Session (STS) - Volume 4
P. 75
STS563 Patrick Graham et al.
survey inclusion probability can be estimated within the model (Zhang, 2015).
However, introducing a second administrative list raises the very real possibility of
linkage error between the two lists. The methodology outlined here also needs to be
extended to cope with measurement error or misclassification of list variables, as well
other practical challenges. We are currently investigating these issues.
References
1. Bryant, J., Dunstan, K., Graham, P., Matheson-Dunning, N., Shrosbee, E.,
Spiers, R. (2016) Measuring Uncertainty in the 2013 Base Estimated
Resident Population. Statistics New Zealand Working Paper No 16-04.
Statistics New Zealand, Wellington NZ.
2. Bycroft, C. (2015) Census Transformation in New Zealand: Using
administrative data without a population register. Statistical Journal of
the IAOS, 31(3), 401-411.
3. Carpenter, B., Gelman, A., Hoffman, M.D., Lee, D., Goodrich, B., Betancourt, M.,
Brubaker, M., Guo, J. Li,P., and Riddell, A. (2017) Stan: A probabilistic
programming language. Journal of Statistical Software 76(1). DOI
10.18637/jss.v076.i01.
4. Graham, P., Lin, A. (2019) Bayesian and approximate Bayesian methods for small
domain population estimation from an administrative list subject to underand
over-coverage. Unpublished manuscript available on request from the authors.
5. Zhang, L.C. (2015) On modelling register coverage errors. Journal of
Official Statistics, 31(3), 381-396.
64 | I S I W S C 2 0 1 9