A Convolution Estimator for the Density of Nonlinear Regression Observations

Abstract. The problem of estimating an unknown density function has been widely studied. In this article, we present a convolution estimator for the density of the responses in a nonlinear heterogenous regression model. The rate of convergence for the mean square error of the convolution estimator is of order n ^?1 under certain regularity conditions. This is faster than the rate for the kernel density method. We derive explicit expressions for the asymptotic variance and the bias of the new estimator, and further a data‐driven bandwidth selector is proposed. We conduct simulation experiments to check the finite sample properties, and the convolution estimator performs substantially better than the kernel density estimator for well‐behaved noise densities.     

A critical appraisal of the analysis of variance for two-way classifications

This paper discusses two reasons for invalidity of analysis of variance, namely heterogeneous variance and heterogeneous correlation. Textbook examples of data in two classifications are presented in which these failures of validating assumptions were not recognised and which led to analyses which were seriously in error. Both forms of heterogeneity result in a residual mean square in the usual analysis of variance being made up of heterogeneous components; the difficulty is overcome by partitioning the mean square and using the component appropriate to the hypothesis to be tested and the contrast to be estimated.     

Qualitative archiving: engaging with epistemological misgivings

In this article it is argued that epistemological concerns about the archiving of qualitative data are mis‐directed. Almost all interpretive data makes either an implicit or explicit claim to knowledge in a broader context than the research project on which it is based. The ability to re‐interpret these data in the light of changing broader contexts is entirely consistent with the project of interpretive and constructivist epistemologies which frame reality as socially constructed and contextually contingent. The increasing reflexivity of qualitative research can only assist the future researcher, providing it serves its aims of articulating and deepening the understanding of the original research environment and the motives of researcher and participant. The decision to re‐interpret data should be one based on professional skill rather than epistemological barriers. Qualitative researchers should view the project as one for the long term, rather than as a short‐term threat to the validity of their primary analysis. These arguments are made separately from ongoing debates about the ethical and confidentiality concerns of qualitative archiving.     

Straighten Up and Act Like a Lady: A Qualitative Study of Lesbian Survivors of Intimate Partner Violence

Although scholars have been studying domestic violence for decades now, it is only recently that domestic violence occurring in non-heterosexual relationships has received noteworthy attention. Several researchers have called for further study of lesbian intimate partner violence (IPV) and the experiences of lesbian survivors. This exploratory study was designed to uncover the experiences of lesbian survivors in regards to their background of violence, perception of lesbian community attitudes, and experience with seeking help. Using modified grounded theory, I was able to expose several recurring themes in the data, including the following: history of violence; gendered belief of violence; the reality of lesbian intimate partner violence; help seeking and the silence surrounding lesbian intimate partner violence in the lesbian community; and the roles of homophobia and heterosexism in lesbian intimate partner violence. Survivors repeatedly reported feeling silenced, isolated, and helpless due to the lack of acknowledgment of and support for lesbian survivors of intimate partner violence in their communities. The purpose of this study is to explore the experiences of women who have endured violence at the hands of their same-sex intimate partners.     

A Nordhaus-Gaddum-type result for the induced path number

The induced path number ??(G) of a graph G is defined as the minimum number of subsets into which the vertex set of G can be partitioned so that each subset induces a graph. A Nordhaus-Gaddum-type result is a (tight) lower or upper bound on the sum (or product) of a parameter of a graph and its complement. If G is a subgraph of H, then the graph H?E(G) is the complement of G relative to H. In this paper, we consider Nordhaus-Gaddum-type results for the parameter ?? when the relative complement is taken with respect to the complete bipartite graph K _n,n .     

The Civil War in Song

Human history is often shaped by the outcomes of arguments, not only in the sense of disputes between people or governments, but in the sense of the more rational pursuit of trying to convince others to accept or do certain things by offering reasons that are presented as compelling for so doing. Yet history teachers have done little to help students learn how to identify arguments in this sense, figure out what the arguments being offered are, and evaluate them. This article shows how a generic instructional technique—infusing direct instruction in skillful thinking into content instruction—can be used in the teaching of American history in ways that help students develop and use these thinking skills and that enhance their deep content understanding of the history being taught. The context is a secondary school classroom studying American history.     

Social status, values, and support for reform in education

Using a survey of Ohio and Indiana residents, we analyze the extent to which public support for school vouchers and school finance reform is structured by the same socioeconomic interests and values (equality, humanitarianism, individualism, and limited government) as is public support for contentious welfare policies. Disadvantaged individuals and individuals who live in disadvantaged communities are more likely to support vouchers but social status has a more ambiguous influence on support for finance reform. Values cannot explain the effect of social status on support for these education policies, but they exert independent effects. We speculate that disadvantaged individuals are more likely to see vouchers as in their interests than are advantaged individuals because voucher advocates have allied themselves with social movements and organizations representing clear constituencies (religious conservatives, low-income urban parents). On the other hand, we suggest that finance reform is more of an abstract issue because its advocates have mostly concentrated on intragovernmental litigation, and thus cleavages based on social status tend to be more obscured.     

Stress,Depression and Tiredness among Women: The Social Production and Social Construction of Health*

Cet article traite essentiellement de la production sociale du stress, de la dépression et de la fatigue chez les femmes. Ces problèmes font partie de ceux qui ont été le plus fréquemment évoqués à l'occasion d'une enquête effectuée sur un échantillon aléatoire de 356 femmes canadiennes. Nous avons utilisé les procédures de régression linéaire multiple pour explorer comment ces problèmes de santé sont liés à certains aspects des conditions de vie sociale et matérielle de ces femmes. Certaines de nos conclusions viennent contredire les modéles traditionnels invoqués pour décrire les problemes de santé. En nous appuyant sur les définitions que les femmes ont données, nous croyons avoir décelé un discours sur la santé propre à la classe moyenne. En conclusion, nous soutenons que les études sur la production sociale des maladies devraient aussi explorer la construction sociale des definitions de la santé et de la maladie. This paper focusses on the social production of stress, depression and tiredness among women. These problems were among the most frequently reported by a random sample of 356 Canadian women. The authors use multiple linear regression procedures to explore the links between these health problems and aspects of the social and material conditions of women's lives. Some of the findings contradict the usual patterning of health problems. The authors suggest that by relying on women's own definitions they may have captured a middle-class discourse of health. In conclusion, it is argued that studies of the social production of illness should also explore the ways in which definitions of health and illness are socially constructed.