Premium
Methods for capture–recapture analysis when cases lack personal identifiers
Author(s) -
Cadwell Betsy L.,
Smith Philip J.,
Baughman Andrew L.
Publication year - 2005
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.2081
Subject(s) - identifier , mark and recapture , computer science , statistics , estimator , estimation , matching (statistics) , population , unique identifier , medicine , mathematics , environmental health , management , economics , programming language
Methods for estimating the size of a closed population from a capture–recapture study require the availability of unique identifiers on each of two lists. These identifiers are used to identify the number of individuals appearing on both lists. When the number of individuals appearing on both lists cannot be determined with certainty from the data, matching between the lists is problematic. In this paper, we develop a weighted estimator to account for all possible matches between two lists. A bootstrap procedure is proposed for estimation. To illustrate the methods, we used two lists that recorded New York State (NYS) hospitalizations due to pertussis in 1996 to estimate the number of persons hospitalized for pertussis in NYS that year. Published in 2005 by John Wiley & Sons, Ltd.