Percentage points of a weighted Kolmogorov-Smirnov statistic

Let F and G be the cumulative distribution functions corresponding to two independent random variables. Define the shift function, Δ(x), by F(x)=G(x+Δ(x)). Doksum and Sievers (1976) compared two confidence bands for Δ(x). The confidence band they found to be best requires the percentage points of a weighted form of the Kolmogorov-Smirnov statistic. The goal in this paper is to supply a table of some of the exact percentage points.     

Comparing two dependent groups via quantiles

This paper considers two general ways dependent groups might be compared based on quantiles. The first compares the quantiles of the marginal distributions. The second focuses on the lower and upper quantiles of the usual difference scores. Methods for comparing quantiles have been derived that typically assume that sampling is from a continuous distribution. There are exceptions, but generally, when sampling from a discrete distribution where tied values are likely, extant methods can perform poorly, even with a large sample size. One reason is that extant methods for estimating the standard error can perform poorly. Another is that quantile estimators based on a single-order statistic, or a weighted average of two-order statistics, are not necessarily asymptotically normal. Our main result is that when using the Harrell–Davis estimator, good control over the Type I error probability can be achieved in simulations via a standard percentile bootstrap method, even when there are tied values, provided the sample sizes are not too small. In addition, the two methods considered here can have substantially higher power than alternative procedures. Using real data, we illustrate how quantile comparisons can be used to gain a deeper understanding of how groups differ.     

Fear of acquaintance versus stranger rape as a "master status": towards refinement of the "shadow of sexual assault"

Using a sample of 1010 women from a southeastern state university, we explore whether associations between fear of sexual assault and other crime-specific fears vary based on presumed victim-offender relationship. More specifically, we assess the extent to which fear of stranger- and acquaintance-perpetrated sexual assaults differ in the extent to which they are correlated with fear of other crime victimizations. Multivariate logistic regression analysis revealed that both fear of stranger-perpetrated sexual assault and fear of acquaintance-perpetrated sexual assault were positively associated with nearly all other crime-specific fears under examination. However, associations were particularly strong between fear of sexual assault by a stranger and fear of other stranger-perpetrated crimes. Findings have significant implications for how academic institutions should comprehensively address direct and indirect negative influences of violence against college women.     

Seeking control in the midst of uncertainty: Women’s experiences of choosing mode of birth after caesarean

Problem

Clinical practice guidelines indicate that over 80% of women with a previous caesarean should be offered a planned vaginal birth after caesarean (VBAC), however only one third of eligible women choose to plan a VBAC. To support informed choices for birth after caesarean, it is necessary to understand the factors that influence women’s decision-making.

Getting Clear About the "Sign Rule"

The question of the "validity" of the "sign-rule" has been a source of continuing disagreement among sociologists. Some of the confusion surrounding this question can be dispelled by focusing on the problem of providing satisfactory interpretations for calculi constructed to represent various commentators' versions of acceptable "sign-rule" arguments. It is shown that the formulae of a calculus constructed to represent standard sign rule arguments must be interpreted in terms of propositions asserting that rankings of objects in virtue of one property are identical to rankings in virtue of another property. A system constructed on the basis of "the assumption of high correlations" is shown to involve distinctions between the logical forms of the premises and the conclusions of key arguments. This sharply limits the deductive power of this system. A third system, constructed on the basis of the "causal modeling" view of the sign rule, is shown to require an interpretation which renders the procedure irrelevant to the construction and testing of general theories.     

Political Mobilization in the Pews: Religious Contacting and Electoral Turnout

Objective . We probe the impact of voter contact by religious groups, in the form of direct attempts to encourage voters to vote in a certain way and the placement of voter guides in churches, on voter turnout among white evangelical Protestants, white mainline Protestants, white Roman Catholics, and black Protestants in 1994, 1996, and 1998. Methods . Using data from the 1994, 1996, and 1998 National Election Studies, we fit a series of logistic regression models of voter turnout that feature, as key predictors, variables indicating whether an individual was contacted by "any groups concerned with moral or religious issues that tried to encourage you to vote in a particular way" and whether "information about candidates, parties or political issues [was] made available in your place of worship before the election." Results . These forms of contact were most commonly experienced by white evangelicals and black Protestants, and in many instances such contacts accomplished their intended purpose. Conclusions . Interest group contacts—at least contacts from the types of groups examined here—have the potential to be no more effective than contacts by political parties, perhaps because their messages can be more narrowly targeted.     

If Momma Ain't Happy: Explaining Declines in Marital Satisfaction Among New Mothers

This study tests competing explanations for the link between the transition to motherhood and declines in wives' marital satisfaction. Using data from the first and second waves of the National Survey of Families and Households (N = 569), we found that new mothers' marital satisfaction declines could be attributed to reductions in wives' quality time spent with their husbands and to increases in perceptions of unfairness in housework. Family role traditionalization in the wake of the birth of a child did not directly explain marital satisfaction declines but was linked to perceptions of marital unfairness. Attendance at religious worship services did not moderate the association between the transition to motherhood and marital satisfaction changes.     

The Effects of Religious Fundamentalism and Religiosity on Preference for Traditional Family Norms*

This study examines the effects of religion on preference for a patriarchal family, one in which the husband makes decisions while the wife is subservient to him. The effects of both religious fundamentalism and personal religiosity are considered using a survey of adults in a Southwestern city. The analysis reveals a strong positive direct effect of adherence to a fundamentalist doctrine on support for the patriarchal family, but no direct effect of personal religiosity. An interaction effect of these two variables, reported in some other studies of the effect of religion on other family issues, is not found. The effect of religious fundamentalism is equal in magnitude to the effect of age, and greater than the effects of education, gender, family income, head of household occupational prestige, subjective class identification, race and rural background. With the exceptions of age and gender, religious fundamentalism serves as a crucial intervening variable in the relationships between these variables and endorsement of patriarchal norms in the husband-wife relationship.