The principal aim of this research project is to develop a formal model-based approach for inferring migration flows in settings where such data are inadequate, incomplete, or unavailable by combining and borrowing information from several geographical areas, time periods, and data sources. To accomplish this, the project will draw on work carried out in four areas: indirect estimation methods in demography, spatial interaction modeling in geography, model-based approaches to analyses with missing data in statistics, and mathematical representations of regularities in the age profiles of migration rates. The inferential methods developed by this project will be tested on known migration data drawn from the censuses of 1960, 1970, 1980, and 1990, and then they will be applied to the American Community Survey Data on migration, and comparable data for two additional nations: Canada and Indonesia. These latter data will be assembled and analyzed with the help of unpaid national demographers (consultants) in those countries.