Confidence intervals for secondary parameters following a sequential test

In sequential studies, formal interim analyses are usually restricted to a consideration of a single null hypothesis concerning a single parameter of interest. Valid frequentist methods of hypothesis testing and of point and interval estimation for the primary parameter have already been devised for use at the end of such a study. However, the completed data set may warrant a more detailed analysis, involving the estimation of parameters corresponding to effects that were not used to determine when to stop, and yet correlated with those that were. This paper describes methods for setting confidence intervals for secondary parameters in a way which provides the correct coverage probability in repeated frequentist realizations of the sequential design used. The method assumes that information accumulates on the primary and secondary parameters at proportional rates. This requirement will be valid in many potential applications, but only in limited situations in survival analysis.     

An Investigation of Measures of Modern and Old-Fashioned Sexism

Working from the Principle of Beneficence we make the case that there is a need for adequate measures of sexism in men and women. Swim, Aikin, Hall and Hunter (1995) suggest that modern sexism represents a constellation of beliefs in which individuals: (a) disavow women's present-day discrimination; (b) reject women's demands for political and economic power; and (c) disapprove of policies designed to promote gender equality. To assess this construct, Swim et al. (1995) developed the Modern Sexism Scale (MSS), and to date, few studies have assessed its reliability and factor structure. Using data from 187 Canadian participants, confirmatory factor analysis was used to assess the unidimensionality of the MSS and Swim and associates' (1995) Old-Fashioned Sexism Scale (OFSS). Results do not support Swim et al.'s conceptualization of modern sexism as a unidimensional construct; however, the OFSS fit a unidimensional model. The implications of these findings are discussed.     

Beyond Simple Differences: Moderators of Gender Differences in Heteronormativity

ABSTRACT

Heteronormativity is a culturally embedded system defining acceptable identities and behaviors in romantic relationships. Recent literature has suggested that heteronormativity is strongly associated with political attitudes, personality characteristics such as tolerance of ambiguity, and key demographic variables such as gender and sexual orientation. However, interactions between gender and other factors have not been thoroughly explored as predictors of heteronormative attitude and beliefs. The current study (N = 306) expands the understanding of predictors of heteronormativity, particularly as they interact with gender. In the current study, higher education was associated with lower heteronormativity among women, but not among men, and expressiveness was associated with lower heteronormativity among men, but not among women. Finally, a 3-way interaction showed that the relationship between education and heteronormativity for men (but not women) depended on trait expressiveness. Future studies are recommended, including observation of changes in heteronormativity over time and exploration of mechanisms that reinforce or reduce heteronormativity.     

Direct and indirect effects of unionization on the wage levels of nurses: A case study of New Jersey hospitals

This study examines the determination of wage rates for nurses in hospital employment. Of particular concern is the effect of the recent increase in unionization by nurses on their wages, both directly and indirectly via threats from competing hospitals’ unionization. To improve on earlier work, the data are disaggregated and gathered from only one state to standardize for the legal, licensing, and reimbursement systems. We also look at the difference between highly skilled professional nurses, RN’s, and more general and less professional nurses, LPN’s. The results show that working conditions and competition in the market influence the wage rate as one would expect. The unionization of nurses, however, affects the wage levels differently for the two groups. We would like to thank Professors Robert Higgs and Alan Childs of Lafayette College, Professor David Fairris of Williams College, Professor James C. Luzier of Muhlenberg College, and an anonymous referee for their helpful comments and suggestions.     

Fill-in of missing data in univariate coastal data

An approach to fill-in of missing data where gaps exist within an otherwise continuous record is addressed. Ad hoc methods of past approaches are discussed and limitations noted. An approach for providing an estimate of data filling consistent with data having a correlation structure is presented. The method provided is an extension of parametric modelling along with additional constraints imposed via a linear filter to account for variance preservation. The method is applied and compared to real data in which a portion of the record has been removed to simulate missing data. Results show the method to provide realistic missing data that preserves the correlation structure and variance of the measured data.     

Children of problem gamblers

An anonymous 37-item Health Survey was administered to 844 randomly selected ninth- to twelfth-grade students in four Southern California public high schools. Systematic information was gathered about their general health, quality of life, school and work adjustment, involvement with a range of potentially addictive substances and activities, and indications of psychosocial maladjustment, including difficulties with the law and suicide attempts. A series of self-ratings of students who characterized one or both of their parents as having a compulsive gambling problem (N=52) were contrasted with those of their classmates who reported no gambling problem among their parents (N=792). Findings have been grouped into three major areas: (a) comparative levels and reported effects of involvement with health-threatening behaviors (i.e., smoking, drinking, drug use, overeating, and gambling); (b) comparative incidence of psychosocial risk indicators (i.e., broken home, unhappy childhood and teenage years, legal action pending, overall quality of youth rated as poor); and (c) comparative incidence of dysphoria, school and work problems, and suicide attempts. Across each of these areas children of parents said to gamble excessively were found to be at consistently greater risk than their classmates who did not describe their parents as having a problem with compulsive gambling. These findings strongly suggest that without early and competent intervention, children of parents who gamble excessively: (a) will be seriously disadvantaged when attempting to solve their present adolescent and future adult problems of living; and (b) as a consequence are, themselves, high-risk candidates for developing one or another form of dysfunctional adjustment, including an addictive pattern of behavior.     

Perceived leader integrity: Supporting the construct validity and utility of a multi-dimensional measure in two samples

The empirical study of perceived leader integrity has lagged its intuitively appealing role as a fundamental characteristic of effective leaders. Following theoretical examinations of the definition of integrity and previous work arguing that perceived integrity emerges from judgments of leader consistency and leader morality, we developed a multidimensional measure that includes both perceived morality and consistency items. In a first sample of university students, confirmatory factor analyses and results from regression analyses relating the dimensions to direct measures of leader integrity and trust offer partial support for the utility of including dimensions of moral behavior and consistency (represented by behavioral integrity). Further, we replicated these findings in a second sample of working professionals and found support for our hypotheses showing that dimensions assessing behavioral integrity and moral behavior related to leader effectiveness, job satisfaction, work engagement, and intent to quit as mediated by trust in the leader.     

Sex, Age, and the Implementation of the Motor Voter Act: The 1996 Presidential Election

Objective . Among the existing studies of political participation, few discuss differences between men and women. Of those published, most have focused upon substantive policy preferences, perhaps noting women's newly dominant electoral presence but not probing its characteristics or limits. In this analysis we build on the work of Schlozman, Burns, and Verba (1994) by examining the compound effects of closing dates, state National Voter Registration Act implementation delay, and age upon women and men. Methods . Using the 1996 Current Population Survey Voter Supplement we compare the impact of legal obstacles among different age groups of men and women in the 1996 presidential election. Results . We find that legal restrictions do have a different impact on men and women, especially the youngest and oldest members of the latter group. Conclusions . The most significant implication of our work is that policy efforts aimed at further reducing legal barriers to political participation may facilitate women's growing electoral dominance.