Based on parish registers, demographic histories of Crulai (France), Tourouvre-au-Perche (France), and Geneva (Switzerland) established the childhood mortality experienced by complete sibships during periods of at least half a century before the French revolution. These observations may be presented as frequencies in incomplete five-dimensional contingency tables. The five dimensions are: survival (living or dead), completed sibship size, birth order, type of family (according to completeness of information about family), and epoch (period in which the family lived).
This paper reanalyzes these published data, using hierarchical log-linear models to discern which interactions among the five variables can justifiably be inferred from the data. The neonatal and infant mortality rates of firstborn are probably higher than those of later sibs (in Crulai and Tourouvre). But mortality by age 20 (in Geneva) is associated strongly with the epoch, type of family, and family size, and not significantly with birth order. The increase in mortality with completed family size is insufficient to select, in an evolutionary sense, for limited family size.