Springer Statistics for Health Data Science: An Organic Approach (Springer Texts in Statistics)

Highly interdisciplinary - drawing from statistics, health services, economics, and informatics Goes beyond the formulas, explaining why different methods work, how to choose from among them, and how to avoid misinterpreting results - to create confident users of appropriate analytic methods Addresses topical questions such as data science versus statistics, prediction versus explanation Provides a wide range of analytic and regression-type models specific to research questions about health care use and costs of care In-depth discussion on selection bias in observational data methods for inferring causality Supplementary Material Includes: Code and data for all examples and model analyses, Code for data processing and analysis, Code segments for simulation models