Home > Publications . Search All . Browse All . Country . Browse PSC Pubs . PSC Report Series

PSC In The News

RSS Feed icon

Elliott co-PI on new study examining how early environment impacts children's health

Levy says ACA has helped increase rates of insured, but rates still lowest among poor

Bruch reveals key decision criteria in making first cuts on dating sites

More News

Highlights

U-M ranked #4 in USN&WR's top public universities

Frey's new report explores how the changing US electorate could shape the next 5 presidential elections, 2016 to 2032

U-M's Data Science Initiative offers expanded consulting services via CSCAR

Elizabeth Bruch promoted to Associate Professor

Next Brown Bag

Mon, Oct 3 at noon:
Longevity, Education, & Income, Hoyt Bleakley

George C. Alter photo

Completing Life Histories with Imputed Exit Dates: A Method for Historical Data from Passive Registration Systems

Publication Abstract

Alter, George C., Isabelle Devos, and Alison Kvetko. 2009. "Completing Life Histories with Imputed Exit Dates: A Method for Historical Data from Passive Registration Systems." Population, 64(2): 293-318.

Using family reconstitution methods, historical demographers are able to reconstruct life histories with data from vital records. In countries where they exist and where data are of good quality (notably in the Nordic countries, Belgium and the Netherlands), population registers can be used to describe the fertility and mortality of historical populations. A major problem with these data sources, however, is the under-reporting of information on migration. The presence of individuals remains certain so long as the events concerning them (or their family) are registered, but if no further information is recorded, there is no way of knowing whether they have migrated or not.

2 In this article, George Alter, Isabelle Devosand and Alison Kvetko estimate the migration probability of each subject "lost to observation" on the basis of his or her individual characteristics, then randomly impute an exit date. Bias due to missing data can thus be corrected by assigning an exit date to each subject. Classic event history analysis methods can then be used, as if individual records were complete up to the exit date.

3 Using a nineteenth-century population register of a Belgian municipality in which emigrants are identified and their exit date is known, the authors test their method and confirm its robustness, adding a simple and effective new instrument to the demographer's toolbox.

Country of focus: Belgium.

Browse | Search : All Pubs | Next