Optimal partitioning for the proportional hazards model

This paper discusses methods for clustering a continuous covariate in a survival analysis model. The advantages of using a categorical covariate defined from discretizing a continuous covariate (via clustering) is (i) enhanced interpretability of the covariate''s impact on survival and (ii) relaxing model assumptions that are usually required for survival models, such as the proportional hazards model. Simulations and an example are provided to illustrate the methods.     

“White Men Are This Nation:” Right‐Wing Militias and the Restoration of Rural American Masculinity*

Abstract The appearance of right‐wing militias was a much‐discussed phenomenon during the past decade. Commentators rightly pointed out their rural origins, their lower‐middle‐class and middle‐class composition, and their ideology rooted in racism, sexism, anti‐Semitism, and homophobia, but few, if any, have commented on the most salient aspect of all: that these are movements of men, who use narratives about masculinity as an analytic prism through which to understand their own situation and to problematize the identities of “others,” and as a rhetorical strategy to recruit and sustain their own membership. In this paper we undertake this analysis, exploring the rural origins of the militia movement, its social composition, ideology, and organization, and its articulation with other white supremacist groups. We argue that their vision of masculinity, particularly a self‐reliant, self‐made masculinity endemic to American history, is the theme unifying both the ideology and the organization of rural militias with the militant right‐wing continuum of which they are only a part.     

STIRring the grid: engaging energy systems design and planning in the context of urban sociotechnical imaginaries

Since the first electrification systems were established in the United States between 1910 and 1930, energy systems governance at the municipal level has included competing visions for how engineering design and energy policy-making should foster particular social outcomes. Using Phoenix as a representative metropolitan area, and the cases of distributed generation and in-home power management devices as examples, this paper explores how the norms and values embedded in energy systems design and planning shape how residents experience change in the energy grid. Through these case studies, the authors argue that such “sociotechnical imaginaries” – collectively formed visions of social life related to science and technology development – are a crucial, yet overlooked, pathway for social science to engage in fostering socially reflexive mechanisms in energy development. To conclude, the authors outline a research program for applying the established methodology of socio-technical integration research (STIR) in order to develop socially reflexive capacities in municipal energy producing, regulating, and planning institutions. Such a program has the ability to produce a deeper intellectual understanding of how energy development occurs, and in doing so generate new pathways for fostering cultural and material changes in the structure of contemporary energy systems.     

Third award: Constructing an experience table to predict the client's continuation in treatment

This study evaluated a community-based treatment program in Sweden for mothers subjected to intimate partner violence. Results based on group means indicated that the mothers showed significantly reduced trauma and psychological symptoms and improved sense of coherence after participating in the program. Surprisingly, no improvement regarding perceived parental locus of control was found. Furthermore, as a complement to group statistics a reliable change index was used, which resulted in more modest results regarding the effectiveness of the treatment.     

Optimal Partitioning for Linear Mixed Effects Models: Applications to Identifying Placebo Responders

A long-standing problem in clinical research is distinguishing drug treated subjects that respond due to specific effects of the drug from those that respond to non-specific (or placebo) effects of the treatment. Linear mixed effect models are commonly used to model longitudinal clinical trial data. In this paper we present a solution to the problem of identifying placebo responders using an optimal partitioning methodology for linear mixed effects models. Since individual outcomes in a longitudinal study correspond to curves, the optimal partitioning methodology produces a set of prototypical outcome profiles. The optimal partitioning methodology can accommodate both continuous and discrete covariates. The proposed partitioning strategy is compared and contrasted with the growth mixture modelling approach. The methodology is applied to a two-phase depression clinical trial where subjects in a first phase were treated openly for 12 weeks with fluoxetine followed by a double blind discontinuation phase where responders to treatment in the first phase were randomized to either stay on fluoxetine or switched to a placebo. The optimal partitioning methodology is applied to the first phase to identify prototypical outcome profiles. Using time to relapse in the second phase of the study, a survival analysis is performed on the partitioned data. The optimal partitioning results identify prototypical profiles that distinguish whether subjects relapse depending on whether or not they stay on the drug or are randomized to a placebo.     

The long-run effect of part-time work

Unlike most of the literature concerning the effects of nonstandard work, we examine the long-term impact of part-time work. Our main focus is on earnings and several important benefits. As might be expected, voluntary part-time work while in school increases earnings of both women and men, whereas involuntary part-time work has no significant impact. Surprisingly, however, voluntary part-time work while not in school has a substantial positive effect for women but is not significant for men. Furthermore, we find that the provision of health insurance, profit-sharing, defined-benefit and defined-contribution plans is primarily determined by factors other than work experience.     

Linear Transformations and the k-Means Clustering Algorithm: Applications to Clustering Curves

Functional data can be clustered by plugging estimated regression coefficients from individual curves into the k-means algorithm. Clustering results can differ depending on how the curves are fit to the data. Estimating curves using different sets of basis functions corresponds to different linear transformations of the data. k-means clustering is not invariant to linear transformations of the data. The optimal linear transformation for clustering will stretch the distribution so that the primary direction of variability aligns with actual differences in the clusters. It is shown that clustering the raw data will often give results similar to clustering regression coefficients obtained using an orthogonal design matrix. Clustering functional data using an L(2) metric on function space can be achieved by clustering a suitable linear transformation of the regression coefficients. An example where depressed individuals are treated with an antidepressant is used for illustration.     

Estimating principal points of univariate distributions

SUMMARY The term 'principal points' originated in a problem of determining 'typical' heads for the design of protection masks, as described by Flury. Two principal points in the mask example correspond to a small and a large size. Principal points are cluster means for theoretical distributions, and sample cluster means from a k -means algorithm are non-parametric estimators of principal points. This paper demonstrates that maximum likelihood estimators and semi-parametric estimators based on symmetry constraints typically perform much better than the k -means estimators. Asymptotic results on the efficiency of these estimators of two principal points for four symmetric univariate distributions are given. Simulation results are provided to examine the performance of the estimators for finite sample sizes. Finally, the different estimators of two principal points are compared using the head dimension data for the design of protection masks.     

Linear Conditional Expectation for Discretized Distributions

Many statistical methods for continuous distributions assume a linear conditional expectation. Components of multivariate distributions are often measured on a discrete ordinal scale based on a discretization of an underlying continuous latent variable. The results in this paper show that common examples of discretized bivariate and trivariate distributions will have a linear conditional expectation. Examples and simulations are provided to illustrate the results.