Open Conference Systems, ITACOSM 2019 - Survey and Data Science

Font Size: 
Use of latent class models for estimating population size in multiple record systems in presence of missing data
Davide Di Cecco

Building: Learning Center Morgagni
Room: Aula 210
Date: 2019-06-07 12:00 PM – 01:30 PM
Last modified: 2019-05-06

Abstract


We consider the problem of estimating the size of a population of interest, by integrating a set of administrative sources to be used as capturing lists in a  capture-recapture setting. In this setting, we address the presence of lists which target a subset of our population by means of an inferential approach developed in the context of inference with missing data. We present the use of an extended family of latent class models which relaxes the conditional indipendence assumption, in presence of missing data.


Full Text: SLIDES