Comment on “compromised birth outcomes and infant mortality among racial and ethnic groups”

Frisbie, Forbes, and Pullum (1996) show that it is meaningful to account for low birth weight, preterm delivery, and intrauterine growth-retardation when analyzing differences in compromised birth outcomes and infant mortality among racial and ethnic groups. I compare their findings for the 1987 U.S. birth cohort with findings for the 1988 U.S. birth cohort, using linked birth and infant death vital statistics from the National Center for Health Statistics. I focus on their calculation of fetal growth curves, which are highly at odds with the curves commonly used in the obstetric and pediatric literature. I compare birth outcome distributions and infant death probabilities using Frisbie et al. 's method and other standards. I conclude that Frisbie et al. 's method is not suited for the study of intrauterine growth-retardation at the population level because of the major flaws in gestational age measurement that exist in the type of data they use. An appropriate alternative is to apply a standard of normal intrauterine growth derived from antenatal estimation of fetal weight-for-gestational-age to the vital statistics data.     

Mixed contracts for the newsvendor problem with real options and discrete demand

In this paper we consider the newsvendor model with real options under discrete demand. We consider a mixed contract where the retailer can order a combination of q units subject to the conditions in a classical newsvendor contract and Q real options on the same items. We provide a closed form solution to this mixed contract when the demand is discrete and study some of its properties. In particular we demonstrate that a mixed contract may be superior to a real option contract when a manufacturer has a bound on how much variance she is willing to accept.     

On aggregation of strongly dependent time series

We consider cross-sectional aggregation of time series with long-range dependence. This question arises for instance from the statistical analysis of networks where aggregation is defined via routing matrices. Asymptotically, aggregation turns out to increase dependence substantially, transforming a hyperbolic decay of autocorrelations to a slowly varying rate. This effect has direct consequences for statistical inference. For instance, unusually slow rates of convergence for nonparametric trend estimators and nonstandard formulas for optimal bandwidths are obtained. The situation changes, when time-dependent aggregation is applied. Suitably chosen time-dependent aggregation schemes can preserve a hyperbolic rate or even eliminate autocorrelations completely.     

Not your lucky day: romantically and numerically special wedding date divorce risks

Characteristics of couples on or about their wedding day and characteristics of weddings have been shown to predict marital outcomes. Little is known, however, about how the dates of the weddings correlate with marriage durability. Using Dutch marriage and divorce registries from 1999 to 2013, this study compares the durations of marriages that began on unusually popular wedding dates with marriages on ordinary dates. We identify several distinct types of popular dates, including Valentine’s Day and numerically special days (dates with the same or sequential number values, e.g., 9.9.99, 1.2.03), showing that on an adjusted basis, the incidence of weddings on such dates was 137–509% higher than ordinary dates. The hazard odds of divorce for these special-date weddings were 18–36% higher than ordinary-date weddings. Sorting on couples’ observable characteristics accounts for some of the higher divorce risks, but even after controlling for these characteristics, special-date weddings were more vulnerable, with 10–17% higher divorce odds compared to ordinary dates. These relationships are even stronger for couples who have not married before.     

Statistically nonrepresentative stratified sampling: A sampling technique for qualitative studies

Summary When doing quantitative studies, we usually need a statistically representative sample. The same is often not the case with qualitative studies where we need a sample with variations along the independent variables. The technique described here is simple to use and guarantees variations. A statistically representative sample, on the other hand, if small, often gives few variations. Thus, one could say that the technique presented is a kind of statistically nonrepresentative stratified sampling useful in qualitative studies.The author wishes to thank the editors ofQualitiative Sociology for valuable comments and suggestions made on an earlier version of this note.     

Subset selection of superior populations when the number of populations is large

The situation where k populations are partitioned into one inferior group and one superior group is considered. The statistical problem is to select a random size subset of superior populations while trying to avoid including any inferior populations. A selection procedure is assumed to satisfy the condition that the probability of selecting at least one superior population is bounded below by P¹<1. The performance of a procedure is measured by the probability of including an inferior population.The asymptotic performance, as k→∞ of Gupta's traditional maximum type procedure ψ^G is considered in the location-model. For normally distributed populations, ψ^G turns out to be asymptotically optimal, provided the size of the inferior group does not become infinitely larger than the size of the superior group.     

Modern family initiation in sweden: Experience of women born between 1936 and 1960

This report investigates trends in the initial phases of the family-building process for Swedish women in five-year cohorts born between 1936 and 1960, using life-table techniques. Non-marital cohabitation was much more widespread in our pre-World War II cohort than has been realized previously. Among never-married women, first-birth fertility was remarkably stable for those in and those not in a consensual union alike. Strong increases in non-marital fertility have resulted from progressively increasing exposure to the higher fertility of consensual unions instead of to the very low fertility of single women. Cohabitational first-birth fertility is not high compared with marital fertility.     

The impact of education on modern family-union initiation

The impact of education on formation of first unions is analyzed using interview data from a sample of Swedish women born in 1936–1960. A distinction is made between achieved level of education and the effect of being a student. The former appears to have little effect, but students start consensual unions at lower rates than corresponding non-students, and they also marry at much lower rates. Social background has not been important for marriage formation, but it has been for cohabitation, which was pioneered by the working class. There is no evidence that modern cohabitation started as a campus movement.     

The role of voluntary social welfare organisations in Norway: a democratic alternative to a bureaucratic welfare state?

Taking as a point of departure the postulated political-ideological and fiscal ‘crisis of the welfare state’, this article emphasises recent changes in the relationship between the four sectors of welfare providers: the informal sector of the family or community; the for-profit sector — where social goods are offered by profit-seeking institutions; the formalised sector of voluntary organisations; and the public sector of statutory bodies. Discussion is concentrated on the changing relationship between the voluntary and public sectors. Are voluntary organisations able to cope with new and extensive welfare problems within a more decentralised welfare state? Do they express the values, and do they possess the resources that both governmental agencies and the organisations themselves take for granted?