Multiple system estimation using covariates having missing values and measurement error: Estimating the size of the M?ori population in New Zealand

Abstract We investigate the use of two or more linked lists, for both population size estimation and relationship between variables appearing on all only some lists. This is usually not fully known because individuals appear in are any list. These problems have been solved simultaneously using EM algorithm. extend this approach to estimate indigenous M?ori New Zealand, leading several innovations: (1) extended four lists (including census), where reporting status differs registers; (2) one missing ethnicity, we adapt handle additional missingness; (3) cover subsets by design. discuss under which assumptions such structural undercoverage can be ignored provide a general result; (4) treat indicator each list as variable measured with error, embed latent class model multiple system variable, interpreted true status. Finally, estimating from administrative data only. Supplementary materials our article available online.