Age, period, and cohort effects on maternal mortality: A linear logit model

Abstract

Cohort approach is used to disentangle age, period, and cohort effects on maternal mortality in New York State. By comparing various age * period * cohort linear logit models on the logits of maternal mortality rates, we conclude that period and age effects are the dominant influences on maternal mortality, and cohort effect does not contribute as much as we expect after adjustment for age and period. The implications are that, as a set, changes in those temporal variables which cut across cohorts appear to be more important than changes in those variables which distinguish them.