Probabilistic Method for Combining Internal Migration Data
Posted: 4/29/2018 ()
Guy Abel, Asian Demographic Research Institute and the Vienna Institute of Demography
An Earl and Edna Stice Memorial Lecture
In order to fully understand the causes and consequences of population migration, researchers and policy makers require timely and consistent data. Migration data are commonly obtained from censuses, registers or surveys. Each of these data sources can vary in their measurement of accuracy, coverage of population, undercount and definitions of a migration event. This paper proposes a Bayesian probabilistic methodology to harmonize migration data from different sources. In particular, we build a hierarchical model for combining migration data sources in the USA between 1980 and 2016. The model allows for estimates of true migration flows that explicitly compensates for the inadequacies in each data source and provides one-step ahead forecasts of bilateral migration patterns.
Time: 12:30-1:30 PM
Location: 121 Raitt Hall