Analysis of observational health care data using SAS [edited by] Douglas E. Faries, Andrew C. Leon, Josep Maria Haro, Robert L. Obenchain.

LOCATED IN THE DESK RESERVE SPECIAL COLLECTIONS CABINET

Includes bibliographical references and index.

Introduction to observational studies -- Propensity score stratification and regression -- Propensity score matching for estimating treatment effects -- Doubly robust estimation of treatment effects -- Propensity scoring with missing values -- Instrumental variable method for addressing selection bias -- Local control approach using JMP -- A two-stage longitudinal propensity adjustment for analysis of observational data -- Analysis of longitudinal observational data using marginal structural models -- Structural nested models -- Regression models on longitudinal propensity scores -- Good research practices for the conduct of observational database studies -- Dose-response safety analyses using large health care databases -- Costs and cost-effectiveness analysis using propensity score bin bootstrapping -- Incremental net benefit -- Cost and cost-effectiveness analysis with censored data -- Addressing measurement and sponsor biases in observational research -- Sample size calculation for observational studies.

Annotation This book guides researchers in performing and presenting high-quality analyses of all kinds of non-randomized studies, including analyses of observational studies, claims database analyses, assessment of registry data, survey data, pharmaco-economic data, and many more applications. The text is sufficiently detailed to provide not only general guidance, but to help the researcher through all of the standard issues that arise in such analyses. Just enough theory is included to allow the reader to understand the pros and cons of alternative approaches and when to use each method. The numerous contributors to this book illustrate, via real-world numerical examples and SAS code, appropriate implementations of alternative methods. The end result is that researchers will learn how to present high-quality and transparent analyses that will lead to fair and objective decisions from observational data.