Recursive Partitioning in the Health Sciences


Book Description

A demonstration of the recursive partitioning methodology and its effectiveness as a response to the challenge of analysing and interpreting multiple complex pathways to many illnesses, diseases, and ultimately death. For comparison purposes, standard regression methods are presented briefly and then applied in the examples. This book is suitable for three broad groups of readers: biomedical researchers, clinicians, public health practitioners including epidemiologists, health service researchers, and environmental policy advisers; consulting statisticians who can use the recursive partitioning technique as a guide in providing effective and insightful solutions to clients'problems; and statisticians interested in methodological and theoretical issues. The book provides an up-to-date summary of the methodological and theoretical underpinnings of recursive partitioning, as well as a host of unsolved problems the solutions of which would advance the rigorous underpinnings of statistics in general.




Recursive Partitioning and Applications


Book Description

Multiple complex pathways, characterized by interrelated events and c- ditions, represent routes to many illnesses, diseases, and ultimately death. Although there are substantial data and plausibility arguments suppo- ing many conditions as contributory components of pathways to illness and disease end points, we have, historically, lacked an e?ective method- ogy for identifying the structure of the full pathways. Regression methods, with strong linearity assumptions and data-basedconstraints onthe extent and order of interaction terms, have traditionally been the strategies of choice for relating outcomes to potentially complex explanatory pathways. However, nonlinear relationships among candidate explanatory variables are a generic feature that must be dealt with in any characterization of how health outcomes come about. It is noteworthy that similar challenges arise from data analyses in Economics, Finance, Engineering, etc. Thus, the purpose of this book is to demonstrate the e?ectiveness of a relatively recently developed methodology—recursive partitioning—as a response to this challenge. We also compare and contrast what is learned via rec- sive partitioning with results obtained on the same data sets using more traditional methods. This serves to highlight exactly where—and for what kinds of questions—recursive partitioning–based strategies have a decisive advantage over classical regression techniques.







The Oxford Handbook of Integrative Health Science


Book Description

Most health research to date has been pursued within the confines of scientific disciplines that are guided by their own targeted questions and research strategies. Although useful, such inquiries are inherently limited in advancing understanding the interplay of wide-ranging factors that shape human health. The Oxford Handbook of Integrative Health Science embraces an integrative approach that seeks to put together sociodemographic factors (age, gender, race, socioeconomic status) known to contour rates of morbidity and mortality with psychosocial factors (emotion, cognition, personality, well-being, social connections), behavioral factors (health practices) and stress exposures (caregiving responsibilities, divorce, discrimination) also known to influence health. A further overarching theme is to explicate the biological pathways through which these various effects occur. The biopsychosocial leitmotif that inspires this approach demands new kinds of studies wherein wide-ranging assessments across different domains are assembled on large population samples. The MIDUS (Midlife in the U.S.) national longitudinal study exemplifies such an integrative study, and all findings presented in this collection draw on MIDUS. The way the study evolved, via collaboration of scientists working across disciplinary lines, and its enthusiastic reception from the scientific community are all part of the larger story told. Embedded within such tales are important advances in the identification of key protective or vulnerability factors: these pave the way for practice and policy initiatives seeking to improve the nation's health.




Computational Methods in Biomedical Research


Book Description

Continuing advances in biomedical research and statistical methods call for a constant stream of updated, cohesive accounts of new developments so that the methodologies can be properly implemented in the biomedical field. Responding to this need, Computational Methods in Biomedical Research explores important current and emerging computational statistical methods that are used in biomedical research. Written by active researchers in the field, this authoritative collection covers a wide range of topics. It introduces each topic at a basic level, before moving on to more advanced discussions of applications. The book begins with microarray data analysis, machine learning techniques, and mass spectrometry-based protein profiling. It then uses state space models to predict US cancer mortality rates and provides an overview of the application of multistate models in analyzing multiple failure times. The book also describes various Bayesian techniques, the sequential monitoring of randomization tests, mixed-effects models, and the classification rules for repeated measures data. The volume concludes with estimation methods for analyzing longitudinal data. Supplying the knowledge necessary to perform sophisticated statistical analyses, this reference is a must-have for anyone involved in advanced biomedical and pharmaceutical research. It will help in the quest to identify potential new drugs for the treatment of a variety of diseases.




Classification and Regression Trees


Book Description

The methodology used to construct tree structured rules is the focus of this monograph. Unlike many other statistical procedures, which moved from pencil and paper to calculators, this text's use of trees was unthinkable before computers. Both the practical and theoretical sides have been developed in the authors' study of tree methods. Classification and Regression Trees reflects these two sides, covering the use of trees as a data analysis method, and in a more mathematical framework, proving some of their fundamental properties.




Interdisciplinary Research : Case Studies from Health and Social Science


Book Description

Interdisciplinary research now receives a great deal of attention because of the rich, creative contributions it often generates. But a host of factors--institutional, interpersonal and intellectual--also make a daunting challenge of conducting research outside one's usual domain. This newly updated and revised edition of Interdisciplinary Research is a substantive and practical guide to the most effective avenues for collaborative and integrative research in the social, behavioral, and bio-medical sciences. It provides answers to questions such as what is the best way to conduct interdisciplinary research on topics related to human health, behavior, and development? Which are the most successful interdisciplinary research programs in these areas? How do you identify appropriate collaborators? How do you find dedicated funding streams? How do you overcome peer-review and publishing challenges? This is the only book that provides answers directly from researchers who have carried out successful interdisciplinary programs. The editors give a concise of account of the lessons that can be taken from the book, and then present a series of case studies that reveal the most successful interdisciplinary research programs. These programs provide a variety of models of how best to undertake interdisciplinary research. Each of the chapter authors has carried out innovative, collaborative programs, and all give compelling accounts of the benefits of interdisciplinary research and the central strategies required to achieve them.




Expanding the Boundaries of Health and Social Science


Book Description

It is now widely recognized that research on human health requires more than a focus on human biology and disease entities. Lifestyles, attitudes, stress, education, income--all are now understood to contribute to the spread of disease, the effectiveness of curative therapies, and the prevention of illness, as well as to good health and an enhanced sense of well-being. However, despite such developments and the rise of interdisciplinary research, there is still considerable debate about how best to conduct research and shape policies that insightfully integrate concepts and methods drawn from the full range of the health, social, and behavioral sciences. Moreover, scholars and researchers who wish to engage in such interdisciplinary inquiry have no texts that serve as substantive and practical guides to the most effective avenues. This volume fills this unfortunate gap by presenting a series of case studies that provide a variety of illustrative models of how best to undertake interdisciplinary research on health. All the authors have successfully carried out innovative, collaborative research programs; they give compelling accounts of the benefits of interdisciplinary research, and the central strategies required for successfully achieving such benefits. This volume will be an invaluable resource for scholars and scientists, as well as for decision-makers in academic settings, foundations, and government agencies seeking to develop and promote interdisciplinary programs that expand the boundaries of research dedicated to improving human health and well-being.




Encyclopedia of Epidemiology


Book Description

Presents information from the field of epidemiology in a less technical, more accessible format. Covers major topics in epidemiology, from risk ratios to case-control studies to mediating and moderating variables, and more. Relevant topics from related fields such as biostatistics and health economics are also included.




Contemporary Issues in Exploratory Data Mining in the Behavioral Sciences


Book Description

This book reviews the latest techniques in exploratory data mining (EDM) for the analysis of data in the social and behavioral sciences to help researchers assess the predictive value of different combinations of variables in large data sets. Methodological findings and conceptual models that explain reliable EDM techniques for predicting and understanding various risk mechanisms are integrated throughout. Numerous examples illustrate the use of these techniques in practice. Contributors provide insight through hands-on experiences with their own use of EDM techniques in various settings. Readers are also introduced to the most popular EDM software programs. A related website at http://mephisto.unige.ch/pub/edm-book-supplement/offers color versions of the book’s figures, a supplemental paper to chapter 3, and R commands for some chapters. The results of EDM analyses can be perilous – they are often taken as predictions with little regard for cross-validating the results. This carelessness can be catastrophic in terms of money lost or patients misdiagnosed. This book addresses these concerns and advocates for the development of checks and balances for EDM analyses. Both the promises and the perils of EDM are addressed. Editors McArdle and Ritschard taught the "Exploratory Data Mining" Advanced Training Institute of the American Psychological Association (APA). All contributors are top researchers from the US and Europe. Organized into two parts--methodology and applications, the techniques covered include decision, regression, and SEM tree models, growth mixture modeling, and time based categorical sequential analysis. Some of the applications of EDM (and the corresponding data) explored include: selection to college based on risky prior academic profiles the decline of cognitive abilities in older persons global perceptions of stress in adulthood predicting mortality from demographics and cognitive abilities risk factors during pregnancy and the impact on neonatal development Intended as a reference for researchers, methodologists, and advanced students in the social and behavioral sciences including psychology, sociology, business, econometrics, and medicine, interested in learning to apply the latest exploratory data mining techniques. Prerequisites include a basic class in statistics.