Properties of design-based functional principal components analysis

This work aims at performing functional principal components analysis (FPCA) with Horvitz–Thompson estimators when the observations are curves collected with survey sampling techniques. One important motivation for this study is that FPCA is a dimension reduction tool which is the first step to develop model-assisted approaches that can take auxiliary information into account. FPCA relies on the estimation of the eigenelements of the covariance operator which can be seen as nonlinear functionals. Adapting to our functional context the linearization technique based on the influence function developed by Deville [1999. Variance estimation for complex statistics and estimators: linearization and residual techniques. Survey Methodology 25, 193–203], we prove that these estimators are asymptotically design unbiased and consistent. Under mild assumptions, asymptotic variances are derived for the FPCA’ estimators and consistent estimators of them are proposed. Our approach is illustrated with a simulation study and we check the good properties of the proposed estimators of the eigenelements as well as their variance estimators obtained with the linearization approach.     

Adolescent Filial Piety as a Moderator between Perceived Maternal Control and Mother–Adolescent Relationship Quality in Hong Kong

This study examined the perceived parental styles of maternal warmth and control, as well as adolescent filial piety, in relation to parent–child relationship quality, in 308 Hong Kong Chinese adolescents. The three mother–child relationship qualities measured were perceived maternal support, conflicts, and relationship depth. Adolescents' attitudes toward filial piety explained unique variance in all three of these parent–child relational qualities, over the constructs of maternal warmth and control. In addition, the interaction of filial piety with maternal control explained unique variance in perceived maternal support and mother–child conflicts, but not relationship depth. Results established the potential unique importance of adolescent filial piety and confirmed our hypothesis that the more adolescents emphasize filial piety, the more parental control exerts a positive effect on mother–child relationship quality in Hong Kong families.     

Measurement for a human science

This paper argues a number of points about measurement in the sociology of mental health: (1) measurement is critical, (2) measures should represent and assess elements of human experience, taking measure of life as people feel it, sense it, and understand it, and (3) social scientists should create a human science, producing information for the people it studies so that they can better understand and control their own lives. We argue that a human science is best achieved with the use of indexes, not diagnoses, to measure mental health. We present a brief history of diagnostic instruments and detail how a diagnosis is made. We show how use of diagnoses to measure mental health discounts much human suffering. They dichotomize the true range of feelings and emotions into crude either/or distinctions that do not reflect the reality of people's lives, and they often exclude suffering such as that due to loss or illness that does not meet medical model preconceptions about mental disorder. Using diagnoses to measure mental health presents a reified image of hidden disease knowable and manageable only by trained professionals--beyond the capacity of the suffering individuals to understand and control.     

Threatened and attempted suicide by partner-violent male respondents petitioned to family violence court

The authors examined threatened and attempted suicide among partner-violent male respondents in a family court domestic violence intervention court based on the reports of 101 women petitioning the court for orders of protection. Suicidal behavior was prevalent; 45.5% of respondents had a history of threatened suicide and 12.9% had a history of suicide attempts. Most recent threats were clustered in the previous 6 months (70.5%) with one-fourth occurring within a week of the petition, potentially indicating a desperate response to a deteriorating relationship. Attempts were not clustered in recent months. Men with a history of threatened or attempted suicide were shown to have been more violent at the index offense and greater domestic violence severity overall, potentially indicating a subsample of more severely partner-violent men also at particularly heightened risk for suicide. The study of suicidal behavior in partner-violent men may inform the prevention of suicide and severe domestic violence.     

The Role of Assertiveness and Decision Making in Early Adolescent Substance Initiation: Mediating Processes

This study examined the mediating processes linking assertiveness and decision making to early adolescent substance initiation, along with the moderating effect of gender on those processes. Models specifying negative expectancies and refusal intentions as mediators of individual rights assertiveness and decision‐making effects on substance initiation were evaluated across 18 months on a nontreatment cohort of young adolescents participating in a prevention trial (average age 12.3 years at baseline; N=357). Results indicated that individual rights assertiveness and decision making had indirect effects on substance initiation through effects on negative outcome expectancies and refusal intentions. Gender differences were found in both the average level and the pattern of relationships among the variables. For girls, refusal intentions were negatively associated with later substance initiation. For boys, early levels of substance initiation were negatively associated with later levels of negative expectancies and refusal intentions. Implications for prevention programming are discussed.     

The 1981 socioeconomic index for occupations in Canada

Nous présentons ici un nouvel index socio-économique des occupations, basé sur le recensement de 1981. Il est généralement admis que l'occupation est le meilleur indicateur de statut socio-économique, mais l'importance accordée au prestige, au revenu et à léducation dans la hiérarchisation des occupations demeure matière à débats. Pour cet index, nous avons décidé d'accorder un poids égal aux niveaux d'éducation et de revenu, en rant que composantes additives du statut socio-économique. Aussi, pour fins de continuité, nous avons calibré l 'index sur la base de l échelle Pineo-Porter de prestige.
This article presents a socioeconomic index for the total Canadian labour force, based on 1981 Census data. It also reviews the problems and criticisms of indexes of this kind, and attempts to specify the meaning of socioeconomic scales and the uses to which they may be legitimately put. The present index is most applicable in situations where access to data is limited to occupational titles and where one desires a unidimensional contextual indicator which locates individuals in the Canadian occupational structure at a given point in time. Sociological analysis of structured inequality, however, may be advanced most effectively if, where feasible, a full range of methodological options is considered, including the assessment of conditions on the level of the individual, the use of other contextual levels such as the workplace, and the investigation of occupation, gender and class as interdependent historical products.