Event history modeling of world fertility survey data∗

Abstract

Event history analysis seems ideally suited for the analysis of World Fertility Survey, WFS, data, which consists of full birth histories and related information, but it has not been much used for this purpose. This may be because event history analysis has practical drawbacks for WFS data, namely partial dates, computational burden, the need to take account of five clocks at once and the difficulty of interpreting coefficients. We propose a modeling strategy for the event history analysis of WFS data which overcomes these problems, and we apply it to the previously unanalyzed WFS data from Iran. This yields estimates of the time of onset of fertility decline and the extent to which it was due to compositional changes in the population. It also enables us to determine whether it was a period effect, a cohort effect, or both. These results would have been hard to obtain using other approaches. In addition, the usefulness of ACE as an exploratory tool for determining the best coding of independent variables is illustrated.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 32 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.