Analyzing Complex Survey Data

Experience & InterestTeaching and research in public health (Survey design and analysis in mental health and nutrition, demographic analysis of infant mortality and reproductive health, biostatical and epidemiologic analysis of cancer registry data and environmental surveys, statistical methods in epidemiology) Ron Forthofer has a B.S. in mathematics from the University of Dayton, and an M.S. in mathematical statistics and a Ph.D. in biostatistics from the University of North Carolina at Chapel Hill.  He is a retired professor of biostatistics from the University of Texas School of Public Health in Houston.  He also spent time with the National Center for Health Statistics and with Hoechst Pharmaceutical in Germany.  Since Ron retired and moved to Colorado in 1991, he has been an activist for peace and social justice, working on health care, trade issues, international peace, and Social Security.  In his spare time, he ran for Congress in 2000 and for Governor in 2002 for the Green Party.

• Series Editor’s IntroductionAcknowledgments1. Introduction2. Sample Design and Survey DataTypes of SamplingThe Nature of Survey DataA Different View of Survey Data3. Complexity of Analyzing Survey DataAdjusting for Differential Representation: The WeightDeveloping the Weight by PoststratificationAdjusting the Weight in a Follow-Up SurveyAssessing the Loss or Gain in Precision: The Design EffectThe Use of Sample Weights for Survey Data Analysis4. Strategies for Variance EstimationReplicated Sampling: A General ApproachBalanced Repeated ReplicationJackknife Repeated ReplicationThe Bootstrap MethodThe Taylor Series Method (Linearization)5. Preparing for Survey Data AnalysisData Requirements for Survey AnalysisImportance of Preliminary AnalysisChoices of Method for Variance EstimationAvailable Computing ResourcesCreating Replicate WeightsSearching for Appropriate Models for Survey Data Analysis6. Conducting Survey Data AnalysisA Strategy for Conducting Preliminary AnalysisConducting Descriptive AnalysisConducting Linear Regression AnalysisConducting Contingency Table AnalysisConducting Logistic Regression AnalysisOther Logistic Regression ModelsDesign-Based and Model-Based Analyses7. Concluding RemarksNotesReferencesIndexAbout the Authors