Premium
Multi‐List Methods Using Incomplete Lists in Closed Populations
Author(s) -
Sutherland Jason,
Schwarz Carl James
Publication year - 2005
Publication title -
biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.298
H-Index - 130
eISSN - 1541-0420
pISSN - 0006-341X
DOI - 10.1111/j.0006-341x.2005.021126.x
Subject(s) - human immunodeficiency virus (hiv) , computer science , mark and recapture , population , statistics , data mining , econometrics , medicine , mathematics , virology , environmental health
Summary Multi‐list methods have become a common application of capture–recapture methodology to estimate the size of human populations, and have been successfully applied to estimating prevalence of diabetes, human immunodeficiency virus (HIV), and drug abuse. A key assumption in multi‐list methods is that individuals have a unique “tag” that allows them to be matched across all lists. This article develops multi‐list methodology that relaxes the assumption of a single tag common to all lists. Estimates are found using estimating functions. An example illustrates its application for estimating the prevalence of diabetes, and a simulation study investigates conditions under which the methodology is robust to different list and population sizes.