Project Summary

Some of the most important questions in social science and public policy relate to how individuals' lives, health, and experiences have changed across time. But most 20th century data spanning are cross-sectional-large sets of individuals at one point in time.

The LIFE-M project is transforming vital records data (birth, marriage, death certificates) and census information into the first longitudinal and intergenerational micro-database to span much of the late 19th and 20th centuries. LIFE-M's methodological innovation is the use of birth certificate data as a basis for historical record linking and machine learning to achieve record linkage on an unprecedented scale.

Once completed LIFE-M will facilitate the study of economic and geographic mobility and family formation and dissolution over the 20th century. It will also enhance our understanding of the long-term impacts of adverse events, public policies, or family background.


National Science Foundation


  • Martha J. Bailey

Project Period

2015-09-15 - 2020-08-31