Pseudo-Bayes Estimation of Emigration and Return Migration Flows between all Pairs of Countries
报告人：Adrian E. Raftery
地点：Room 1303, Sciences Building No. 1
Abstract: Estimating migration flows between any two periods for a given time period is hard. Official data souces such as visa counts and passenger surveys can be subject to massive errors, and reported values of the same flow from different countries can differ greatly. For this reason, the UN's reports on migration focus on total stocks of migrants (i.e. the number of foreign-born people living in a country), for which much better data are available, rather than flows in specific time periods. We propose a new statistical method for estimating migration flows between all pairs of countries, based on migrant stocks. The method decomposes migration into emigration, return migration and transit migration. Current state-of-the-art estimates of bilateral migration flows rely on the assumption that the number of global migrants is as small as possible. We relax this assumption, developing a pseudo-Bayes estimation method inspired by a mover-stayer mixture model. This yields complete estimates of all between-country migration flows with genuine estimates of total global migration.
About the speaker: Adrian is the Boeing International Professor of Statistics and Sociology and a faculty affiliate of the Center for Statistics and the Social Sciences and the Center for Studies in Demography and Ecology at the University of Washington. He works on the development of new statistical methods for the social, environmental and health sciences. An elected member of the U.S. National Academy of Sciences, he was identified as the world's most cited researcher in mathematics for the decade 1995-2005 by Thomson-ISI.