Historical Event-History Demography
Also known as: Historical hazard analysis, Eurasian Project event-history, Survival analysis of vital events, Micro-level demographic response models
Historical event-history demography applies the statistical machinery of survival and hazard analysis to longitudinal individual-level historical data, modelling the risk that a person experiences a demographic event—death, marriage, migration, or a birth—as it varies with their changing circumstances. Pioneered by the Eurasian Population and Family History Project, whose comparative findings Bengtsson, Campbell and Lee synthesised in Life under Pressure (2004), the approach exploits population registers and reconstituted families that record events with precise dates alongside time-varying covariates such as grain prices, household composition and social standing. Its signature contribution is measuring the short-term demographic response to economic stress: how mortality, fertility and marriage reacted, differentially by class and household position, to harvest failure and price spikes. By moving from aggregate correlations to individual hazards, it reveals who bore the brunt of subsistence crises and how families buffered, or failed to buffer, their most vulnerable members.
Key highlights
- Isolates short-term demographic responses to economic stress at the individual level
- Reveals differential vulnerability by class, age, sex and household position
- Handles censoring, staggered entry and time-varying covariates rigorously
- Moves beyond aggregate correlation to identify mechanisms and who is affected
Intuition
This section is available to Pro members. Upgrade to Pro
How it works
This section is available to Pro members. Upgrade to Pro
When to use it
Use historical event-history demography when you have individual-level longitudinal data—population registers, continuous parish reconstitutions, or genealogies—recording dated events together with covariates that change over time, and when your question concerns the determinants of demographic behaviour rather than mere trends. It excels at measuring short-term responses to economic shocks, testing for differential vulnerability by class, gender, age and household position, and modelling competing risks such as marriage versus migration. It is the appropriate tool when aggregate correlations cannot identify mechanisms or distinguish who is affected. It is unsuitable where data are only aggregate, where event dates are imprecise, or where covariate histories cannot be reconstructed at the individual level.
Strengths & limitations
- Isolates short-term demographic responses to economic stress at the individual level
- Reveals differential vulnerability by class, age, sex and household position
- Handles censoring, staggered entry and time-varying covariates rigorously
- Moves beyond aggregate correlation to identify mechanisms and who is affected
- Demands rich longitudinal micro-data rarely available outside register populations
- Results from exceptional register communities may not generalise
- Imprecise event dating undermines the timing on which hazards depend
- Reconstructing complete time-varying covariate histories is laborious and gap-prone
Common pitfalls
This section is available to Pro members. Upgrade to Pro
Applications
This section is available to Pro members. Upgrade to Pro
Frequently asked
Why use hazard models instead of regression on counts?
Hazard models exploit the exact timing of events and the time individuals spend at risk, properly handling censoring and individuals who enter or leave observation midstream. They allow covariates to change within a person's life, so a specific bad harvest can be linked to risk in that season. Count regressions on aggregates lose this individual timing and cannot identify who responded or through what mechanism.
What did the Eurasian Project change?
It dismantled the stereotype of a Malthusian-checked Europe versus a crisis-prone Asia by showing, with harmonised micro-data and common models, that both regions regulated population through household and social mechanisms, just in different ways. By measuring individual-level responses to economic stress across five societies, it demonstrated that demographic behaviour was actively managed everywhere, reshaping comparative debates about living standards and family systems.
Why enter prices as deviations from trend?
Long-run price levels reflect structural conditions confounded with many other slowly changing factors. Entering prices as short-term deviations from a trend isolates the effect of transient shocks—the bad harvest, the dearth year—on the immediate risk of death, marriage or migration. This makes the coefficient interpretable as the demographic response to crisis rather than to the general standard of living.
Sources
- 1.Bengtsson, T., Campbell, C., & Lee, J. Z. (2004). Life under Pressure: Mortality and Living Standards in Europe and Asia, 1700-1900. MIT Press.ISBN 9780262025515
- 2.Wrigley, E. A., Davies, R. S., Oeppen, J. E., & Schofield, R. S. (1997). English Population History from Family Reconstitution 1580-1837. Cambridge University Press.ISBN 9780521590150
You have read it. What now?
Cite this page
ScholarGate. (2026, June 23). Historical Event-History Demography. ScholarGate. https://scholargate.app/historical-demography/historical-event-history-demography