Dimension-wise sparse low-rank approximation of a matrix with application to variable selection in high-dimensional integrative analyzes of association

Many research proposals involve collecting multiple sources of information from a set of common samples, with the goal of performing an integrative analysis describing the associations between sources. We propose a method that characterizes the dominant modes of co-variation between the variables in two datasets while simultaneously performing variable selection. Our method relies on a sparse, low rank approximation of a matrix containing pairwise measures of association between the two sets of variables. We show that the proposed method shares a close connection with another group of methods for integrative data analysis – sparse canonical correlation analysis (CCA). Under some assumptions, the proposed method and sparse CCA aim to select the same subsets of variables. We show through simulation that the proposed method can achieve better variable selection accuracies than two state-of-the-art sparse CCA algorithms. Empirically, we demonstrate through the analysis of DNA methylation and gene expression data that the proposed method selects variables that have as high or higher canonical correlation than the variables selected by sparse CCA methods, which is a rather surprising finding given that objective function of the proposed method does not actually maximize the canonical correlation.     

Regression models using the LINEX loss to predict lower bounds for the number of points for approximating planar contour shapes

Researchers in statistical shape analysis often analyze outlines of objects. Even though these contours are infinite-dimensional in theory, they must be discretized in practice. When discretizing, it is important to reduce the number of sampling points considerably to reduce computational costs, but to not use too few points so as to result in too much approximation error. Unfortunately, determining the minimum number of points needed to achieve sufficiently approximate the contours is computationally expensive. In this paper, we fit regression models to predict these lower bounds using characteristics of the contours that are computationally cheap as predictor variables. However, least squares regression is inadequate for this task because it treats overestimation and underestimation equally, but underestimation of lower bounds is far more serious. Instead, to fit the models, we use the LINEX loss function, which allows us to penalize underestimation at an exponential rate while penalizing overestimation only linearly. We present a novel approach to select the shape parameter of the loss function and tools for analyzing how well the model fits the data. Through validation methods, we show that the LINEX models work well for reducing the underestimation for the lower bounds.     

Research as a Social Process

The activity of social research has been much discussed in recent years. It is examined here as a social process, with special attention to the participation of different groups of people. Four modes of doing research are identified. The framework accommodates and shows close relationships between established modes of research which generally have been seen to be substantially different. At the same time it includes modes which are more participatory in character and which have important implications for undertaking research, the development of theory, and the functioning of social groups, including society.     

Statutory Child Welfare as a Social Indicator: NSW Trends 1959–1976

A formal analysis of secular trends in statutory child welfare (defined by rates of complaints laid under the Child Welfare Act) showed no changes in overall rates of welfare problems, excepting an increase for boys aged 16–17. There were significant changes in the pattern of problems, and in the pattern of Children's Court dispositions. The trends were used as social indicators of changes in community values and mores, and in welfare practice.     

Conceptual frameworks and the philosophical foundations of general living systems theory

The continued expansion and fragmentation of biological disciplines impede education, communication, and efficient advance of biological research. Reversing these trends may require a unification of theories and concepts from all levels of biological organization. One form of this unification is the statement of generalizations that apply to all living systems. We explore the philosophical foundations of general theories of living systems by analyzing conceptual frameworks as they apply to biology. This analysis examines the relation of empirical observation, theories, and conceptual frameworks within the context of an individual scientist's conceptual continuum. Also presented are a small set of translevel generalizations that articulate our conceptual framework of living systems in terms of organismic system organization, the environmental system-organismic system dyad, system capacity, and system incorporation. A set of procedural rules are stated which suggest minimum criteria for the evaluation of the explanatory adequacy of biological theories. The relation of this work to other similar analyses and syntheses of biological knowledge is discussed.     

Urbanization and Patterns of Juvenile Delinquency in New South Wales

A comparison of urban and rural patterns of juvenile delinquency in N.S.W. showed that, among boys, there were more charges of breaking entering and stealing, assault, robbery, and truancy in the metropolitan area, and more charges of stealing, receiving, malicious damage, offences against good order, and ‘complaints’ (C.W. Act) in country areas. More boys aged 15 to 17 were charged in the metropolitan area and more aged 12 to 14 in country areas. Similar urban-rural differences were found among girls; however, except for truancy and being uncontrollable, they were not significant. Additionally, in rural areas 12-year-old girls were charged more often with criminal offences and selected ‘complaints’.     

Urban Dispersal in Australia

In a recent issue of the Journal, Professor R. E. Lonsdale argued that the relatively successful American experience of decentralization suggests serious difficulties in attempting a comparable programme in Australia. His comparisons, while illuminating many of the problems which must be faced by a realistic regional development policy, are unduly pessimistic in their assessment of the Australian situation. The barriers to urban dispersal in Australia lie less in economic and social conditions than in political attitudes and governmental structures.