Document Type



The suitability of a class of statistical regression models, hazard models, is examined for use in studying questions arising in hum an biology involving waiting times. A general description of hazard models is given, and the use of hazard models is demonstrated by a study of the effect of prolonged breastfeeding—breastfeeding after the resumption of menses—on the monthly probability of conception. The data used in the study are taken from the Determinants of Natural Fertility Survey, conducted by the International Center for Diarrheal Disease Research, Bangladesh. In the hazard model analysis, we show that, when considered in conjunction with other factors, breastfeeding beyond the resumption of menses has a significant effect on the monthly probability of conception.