BEST SUBSET SELECTION FOR CATEGORICAL DATA

When choosing among models to describe categorical data, the necessity to consider interactions makes selection more difficult. With just four variables, considering all interactions, there are 166 different hierarchical models and many more non-hierarchical models. Two procedures have been developed for categorical data which will produce the "best" subset or subsets of each model size where size refers to the number of effects in the model. Both procedures are patterned after the Leaps and Bounds approach used by Furnival and Wilson for continuous data and do not generally require fitting all models. For hierarchical models, likelihood ratio statistics (G('2)) are computed using iterative proportional fitting and "best" is determined by comparing, among models with the same number of effects, the Pr((chi)(,k)('2) (GREATERTHEQ) G(,ij)('2)) where k is the degrees of freedom for ith model of size j. To fit non-hierarchical as well as hierarchical models, a weighted least squares procedure has been developed.^ The procedures are applied to published occupational data relating to the occurrence of byssinosis. These results are compared to previously published analyses of the same data. Also, the procedures are applied to published data on symptoms in psychiatric patients and again compared to previously published analyses.^ These procedures will make categorical data analysis more accessible to researchers who are not statisticians. The procedures should also encourage more complex exploratory analyses of epidemiologic data and contribute to the development of new hypotheses for study. ^

Interpretation services for immigrants in federally qualified health centers: Barriers, best practices, and suggestions for the future

This paper examines the provision of interpretation services to immigrants with limited English proficiency in Federally Qualified Health Centers, through examination of barriers and best practices. The United States is a nation of immigrants; currently, more than 38 million, or 12.5 percent of the total population, is foreign-born. A substantial portion of this population does not have health insurance or speak English fluently: barriers that reduce the likelihood that they will access traditional health care organizations. This service void is filled by FQHCs, which are non-profit, community-directed providers that remove common barriers to care by serving communities who otherwise confront financial, geographic, language, and cultural barriers. By examining the importance and the implementation of medical interpretation services in FQHCs, suggestions for the future are presented.^

‘The best thing I’ve ever done is ring these people…’: Making a Difference through Family Support

Effective family support strategies offer early intervention and help for families and children at risk of experiencing social exclusion and maltreatment. This paper reports a study which evaluated client outcomes from participation in an Intensive Family Support Service by comparing views of workers and service users on perceived benefits. It profiles the characteristics and circumstances of families recruited to service, services and interventions delivered and the potential of IFSS to lead to safe and positive outcomes for children and families. Findings discussed highlight the individualized and collaborative approach and the high degree of engagement with service users that facilitated gains in the domains of child and family functioning targeted. Implications of the findings for policy and practice in responding to vulnerable families and children are discussed.

Pathway Semantics: An Algebraic Data Driven Algorithm to Generate Hypotheses about Molecular Patterns Underlying Disease Progression

The overarching goal of the Pathway Semantics Algorithm (PSA) is to improve the in silico identification of clinically useful hypotheses about molecular patterns in disease progression. By framing biomedical questions within a variety of matrix representations, PSA has the flexibility to analyze combined quantitative and qualitative data over a wide range of stratifications. The resulting hypothetical answers can then move to in vitro and in vivo verification, research assay optimization, clinical validation, and commercialization. Herein PSA is shown to generate novel hypotheses about the significant biological pathways in two disease domains: shock / trauma and hemophilia A, and validated experimentally in the latter. The PSA matrix algebra approach identified differential molecular patterns in biological networks over time and outcome that would not be easily found through direct assays, literature or database searches. In this dissertation, Chapter 1 provides a broad overview of the background and motivation for the study, followed by Chapter 2 with a literature review of relevant computational methods. Chapters 3 and 4 describe PSA for node and edge analysis respectively, and apply the method to disease progression in shock / trauma. Chapter 5 demonstrates the application of PSA to hemophilia A and the validation with experimental results. The work is summarized in Chapter 6, followed by extensive references and an Appendix with additional material.