Normal view MARC view ISBD view

Innovative Statistical Methods for Public Health Data.

By: Chen, Ding-Geng (Din).
Contributor(s): Wilson, Jeffrey.
Material type: TextTextSeries: eBooks on Demand.ICSA Book Series in Statistics Ser: Publisher: Cham : Springer, 2015Copyright date: ©2015Description: 1 online resource (354 pages).Content type: text Media type: computer Carrier type: online resourceISBN: 9783319185361.Subject(s): Medical laboratoriesGenre/Form: Electronic books.Additional physical formats: Print version:: Innovative Statistical Methods for Public Health DataDDC classification: 362.1015195 LOC classification: QA276-280Online resources: Click here to view this ebook.
Contents:
Intro -- Preface -- Contents -- Contributors -- Part I Modelling Clustered Data -- Methods for Analyzing Secondary Outcomes in Public Health Case-Control Studies -- 1 Introduction -- 2 Data Example: Genetic Association with Smoking Behavior in a Lung Cancer Case-Control Study -- 3 Design-Based Approach to Secondary Outcome Analysis -- 4 Model-Based Approach to Secondary Outcome Analysis -- 5 Data Analysis -- 5.1 Inverse Probability Weights -- 5.2 Propensity Score Matching -- 6 Discussion -- References -- Controlling for Population Density Using Clustering and Data Weighting Techniques When Examining Social Health and Welfare Problems -- 1 Introduction -- 2 Background -- 3 Method -- 4 Results -- 4.1 Bivariate -- 4.1.1 Correlation Table Comparison -- 4.2 Multivariate -- 4.2.1 Path Comparison -- 5 Discussion -- References -- On the Inference of Partially Correlated Data with Applications to Public Health Issues -- 1 Introduction -- 2 Tests for Normal Data -- 2.1 Proposed Weighted Tests by Samawi and Vogel (2014) -- 2.2 New Test Procedure by Samawi and Vogel (2014) -- 2.3 Bootstrap Method to Estimate the p-Value of T0 in Case 2 and 3 -- 2.4 Illustration: A Vaginal Pessary Satisfaction Data (Samawi and Vogel 2014) -- 3 Tests for Binary Data -- 3.1 Test of Homogeneity in a Case-Control Study -- 3.2 Existing Methods for Testing the Above Hypotheses for Partially Matched Data -- 3.3 Proposed Method of Testing the Above Hypothesis for Partially Matched Data (Samawi and Vogel 2011) -- 3.4 Illustration and Final Results and Conclusions -- 3.4.1 Matched-Pairs Data Analysis -- 3.4.2 Unmatched Data Analysis (Excluding Matched-Pair Data) -- 3.4.3 Combined Tests of Matched-Pairs and Unmatched Data -- 4 Nonparametric Test for Partially Correlated Data -- 4.1 Combined Sign Tests for Correlated and Uncorrelated Data: Proposed Methods.
4.1.1 Sign Test for Correlated Data -- 4.1.2 Mann-Whitney Wilcoxon Test for Uncorrelated Data -- 4.1.3 Combined Sign Test with Mann-Whitney Wilcoxon Test -- 4.2 Combined Wilcoxon Signed-Rank Test and Mann-Whitney Wilcoxon Test for Correlated and Uncorrelated Data -- 4.2.1 Wilcoxon Signed-Rank Test for Correlated Data -- 4.2.2 Combined Wilcoxon Rank Test with Mann-Whitney Wilcoxon Test -- 4.3 New Test Procedure -- 4.4 Illustration Using Genetic Data -- Appendix -- References -- Modeling Time-Dependent Covariates in Longitudinal Data Analyses -- 1 Introduction and Motivating Examples -- 2 Classifying Time-Dependent Covariates -- 2.1 Exogeneity -- 2.2 Types of Time-Dependent Covariates -- 3 Subject-Specific Modeling -- 3.1 Conditional Model Decomposition -- 3.2 An Issue with Estimation -- 4 Population-Averaged Modeling -- 4.1 Generalized Estimating Equations -- 4.2 Generalized Method of Moments -- 4.3 GMM with Extended Classification -- 4.4 Minimization For GMM -- 5 Data Example -- 6 Discussion -- 7 Example SAS and R Commands -- 7.1 Random-Intercept Models -- 7.2 Random-Slope Models -- 7.3 Independent GEE -- References -- Solving Probabilistic Discrete Event Systems with Moore -Penrose Generalized Inverse Matrix Method to Extract Longitudinal Characteristics from Cross-Sectional Survey Data -- 1 Background -- 2 A Review of the PDES for Smoking Behavior -- 3 Generalized-Inverse Matrix for PDES -- 4 Demonstration with the MASS Package in R -- 5 Discussion and Conclusions -- Appendix: R Program for Implementation of PDES -- References -- Part II Modelling Incomplete or Missing Data -- On the Effects of Structural Zeros in Regression Models -- 1 Introduction -- 2 Background -- 3 Modeling the Effects of Structural Zeros -- 3.1 Linear and Generalized Linear Models -- 3.2 Zero-Inflated Models -- 4 Simulation Studies -- 4.1 Continuous Response Y.
4.2 Zero-Inflated Poisson Response Y -- 5 A Case Study Example -- 6 Discussion -- References -- Modeling Based on Progressively Type-I Interval Censored Sample -- 1 Introduction -- 2 Data and Likelihood -- 2.1 Likelihood Function -- 2.2 Midpoint Approximation -- 2.3 EM-Algorithm -- 2.4 Moment Method -- 2.5 Method of Probability Plot -- 3 Weibull Distribution Modeling -- 3.1 Maximum Likelihood Estimation -- 3.2 Midpoint Approximation -- 3.3 Method of Moments -- 3.4 Estimation Based on Probability Plot -- 4 Generalized Exponential Distribution Modeling -- 4.1 Maximum Likelihood Estimation -- 4.2 Mid-Point Approximation Method -- 4.3 Method of Moments -- 4.4 Estimation Based on Probability Plot -- 5 Real Data Analysis: Non-Bayesian Approach -- 5.1 The Data -- 5.2 Model Selection -- 5.3 Model Comparison -- 5.4 Model Fitting -- 6 Markov Chain Monte Carlo for Bayesian Estimation -- 6.1 Likelihood Function and Bayes Estimation -- 6.2 A Markov Chain Monte Carlo Process -- 7 Real Data Analysis: Bayesian Approach -- 7.1 The Data -- 7.2 Model Selection -- Appendix -- References -- Techniques for Analyzing Incomplete Data in Public Health Research -- 1 Introduction -- 2 Overview of Missing Data -- 2.1 Pattern of Missingness -- 2.2 Missingness Mechanisms -- 2.2.1 Missing Completely at Random -- 2.2.2 Missing at Random -- 2.2.3 Missing Not at Random -- 2.2.4 Supporting Assumptions of Non-Response -- 3 Missing Data Methods -- 4 Multiple Imputation -- 4.1 Imputation Stage -- 4.1.1 Approaches -- 4.2 Analysis and Combination Stage -- 4.3 Rates of Missing Information -- 5 Example -- 6 Concluding Remarks -- References -- A Continuous Latent Factor Model for Non-ignorable Missing Data -- 1 Introduction -- 2 Models -- 2.1 Review of Continuous Latent Factor Model for Binary Outcomes -- 2.2 Proposed Model -- 3 Maximum Likelihood Estimation -- 3.1 Monte Carlo EM.
3.2 Execution of the E-Step via the Hybrid Algorithm -- 3.3 Maximization Step -- 3.4 Monitor Convergence of MCEM via Bridge Sampling -- 3.5 Standard Error Estimates -- 4 Application: Randomized Study of Dual or Triple Combinations of HIV-1 Reverse Transcriptase Inhibitors -- 4.1 Description of Study -- 4.2 Model Specification -- 4.3 Summary of Analyses Under MAR and MNAR -- 4.4 Distributions on Latent Factor -- 5 Conclusion and Discussion -- References -- Part III Healthcare Research Models -- Health Surveillance -- 1 Introduction -- 2 Background on Industrial Process Monitoring -- 2.1 Monitoring Continuous Outcomes -- 2.2 Monitoring Discrete Outcomes -- 2.3 Control Charts Based on Accumulating Data -- 2.3.1 CUSUM Charts -- 2.3.2 The Exponentially Weighted Moving Average Chart -- 2.4 Multivariate Control Charts -- 3 Health Care Monitoring -- 3.1 Risk-Adjusted Charts -- 3.1.1 Risk-Adjusted p-Charts -- 3.1.2 Risk-Adjusted CUSUM Charts -- 3.1.3 VLAD Charts -- 3.1.4 The Risk-Adjusted EWMA Chart -- 3.1.5 The Risk-Adjusted Sets Method -- 3.2 Other Aspects of Health Care Monitoring -- 4 Disease Surveillance -- 4.1 Modeling Disease Incidence -- 4.2 Detection Methods -- 4.3 Performance Metrics -- 4.3.1 Alternative Metrics -- 4.4 Detecting Seasonal Outbreaks: An Example -- 5 Summary -- 6 Further Reading -- 6.1 Industrial Process Monitoring -- 6.2 Health Care Monitoring -- 6.3 Disease Surveillance -- References -- Standardization and Decomposition Analysis: A Useful Analytical Method for Outcome Difference, Inequality and Disparity Studies -- 1 Introduction -- 2 Method -- 2.1 Algebraic Expression of SDA -- 2.2 Statistical Significance Testing for Component Effect -- 2.3 Computer Program for SDA -- 2.4 Example of Application -- 3 Results -- 4 Discussion -- References -- Cusp Catastrophe Modeling in Medical and Health Research -- 1 Linear and Continuous Paradigm.
2 Nonlinear and Continuous Paradigm -- 3 Nonlinear and Discrete Paradigm -- 4 Quantum Paradigm and Cusp Modeling -- 5 Do Current Research Need More Complex Analytical Paradigm? -- 6 Polynomial Regression Approach -- 6.1 Introduction to the Polynomial Cusp Catastrophe Modeling -- 6.2 Assessment of the Polynomial Cusp Catastrophe Modeling Method -- 6.2.1 Method 1: Significance of the Key Model Coefficients -- 6.2.2 Method 2: Assessment of Alternative Models -- 6.3 Procedure of Modeling Analysis -- 6.4 An Empirical Example -- 6.5 Allocation of Contrail Variables as Asymmetry and Bifurcation -- 7 Likelihood Approach with Stochastic Cusp Catastrophe Model -- 7.1 Introduction to the Likelihood Stochastic Approach -- 7.2 Advantages of the Likelihood Stochastic Cusp Modeling Approach -- 7.2.1 Modeling Cross-Sectional Data -- 7.2.2 Modeling More Than One Observed Variable -- 7.3 The R-Based Cusp Package for Modeling Analysis -- 7.4 Assessment of Data-Model Fit -- 7.5 Steps to Use R-Based Cusp Package -- 7.6 An Empirical Example -- 7.7 Additional Notes -- 7.7.1 Modeling Analysis -- 7.7.2 Results Interpretation -- References -- On Ranked Set Sampling Variation and Its Applications to Public Health Research -- 1 Introduction -- 2 RSS for a Univariate Population -- 2.1 Naive Estimation for the Population Mean -- 2.2 Quantiles and Distribution Function Estimation -- 2.3 Ratio Estimation -- 2.4 Regression Estimation for the Population Mean -- 3 Varied Set Size RSS -- 3.1 Naive Estimator of Population Means Using VSRSS -- 3.2 Ratio Estimation -- 4 Stratified Ranked Set Sample -- 5 Bivariate Population -- 5.1 Ratio Estimators -- 5.2 Regression Estimator Using BVRSS -- References -- Weighted Multiple Testing Correction for Correlated Endpoints in Survival Data -- 1 Introduction -- 2 Weighted Multiple Testing Correction for Correlated Time-to-Event Endpoints.
3 Simulations.
Tags from this library: No tags from this library for this title. Log in to add tags.
Item type Current location Call number URL Status Date due Barcode
Electronic Book UT Tyler Online
Online
QA276-280 (Browse shelf) https://ebookcentral.proquest.com/lib/uttyler/detail.action?docID=4085615 Available EBC4085615

Intro -- Preface -- Contents -- Contributors -- Part I Modelling Clustered Data -- Methods for Analyzing Secondary Outcomes in Public Health Case-Control Studies -- 1 Introduction -- 2 Data Example: Genetic Association with Smoking Behavior in a Lung Cancer Case-Control Study -- 3 Design-Based Approach to Secondary Outcome Analysis -- 4 Model-Based Approach to Secondary Outcome Analysis -- 5 Data Analysis -- 5.1 Inverse Probability Weights -- 5.2 Propensity Score Matching -- 6 Discussion -- References -- Controlling for Population Density Using Clustering and Data Weighting Techniques When Examining Social Health and Welfare Problems -- 1 Introduction -- 2 Background -- 3 Method -- 4 Results -- 4.1 Bivariate -- 4.1.1 Correlation Table Comparison -- 4.2 Multivariate -- 4.2.1 Path Comparison -- 5 Discussion -- References -- On the Inference of Partially Correlated Data with Applications to Public Health Issues -- 1 Introduction -- 2 Tests for Normal Data -- 2.1 Proposed Weighted Tests by Samawi and Vogel (2014) -- 2.2 New Test Procedure by Samawi and Vogel (2014) -- 2.3 Bootstrap Method to Estimate the p-Value of T0 in Case 2 and 3 -- 2.4 Illustration: A Vaginal Pessary Satisfaction Data (Samawi and Vogel 2014) -- 3 Tests for Binary Data -- 3.1 Test of Homogeneity in a Case-Control Study -- 3.2 Existing Methods for Testing the Above Hypotheses for Partially Matched Data -- 3.3 Proposed Method of Testing the Above Hypothesis for Partially Matched Data (Samawi and Vogel 2011) -- 3.4 Illustration and Final Results and Conclusions -- 3.4.1 Matched-Pairs Data Analysis -- 3.4.2 Unmatched Data Analysis (Excluding Matched-Pair Data) -- 3.4.3 Combined Tests of Matched-Pairs and Unmatched Data -- 4 Nonparametric Test for Partially Correlated Data -- 4.1 Combined Sign Tests for Correlated and Uncorrelated Data: Proposed Methods.

4.1.1 Sign Test for Correlated Data -- 4.1.2 Mann-Whitney Wilcoxon Test for Uncorrelated Data -- 4.1.3 Combined Sign Test with Mann-Whitney Wilcoxon Test -- 4.2 Combined Wilcoxon Signed-Rank Test and Mann-Whitney Wilcoxon Test for Correlated and Uncorrelated Data -- 4.2.1 Wilcoxon Signed-Rank Test for Correlated Data -- 4.2.2 Combined Wilcoxon Rank Test with Mann-Whitney Wilcoxon Test -- 4.3 New Test Procedure -- 4.4 Illustration Using Genetic Data -- Appendix -- References -- Modeling Time-Dependent Covariates in Longitudinal Data Analyses -- 1 Introduction and Motivating Examples -- 2 Classifying Time-Dependent Covariates -- 2.1 Exogeneity -- 2.2 Types of Time-Dependent Covariates -- 3 Subject-Specific Modeling -- 3.1 Conditional Model Decomposition -- 3.2 An Issue with Estimation -- 4 Population-Averaged Modeling -- 4.1 Generalized Estimating Equations -- 4.2 Generalized Method of Moments -- 4.3 GMM with Extended Classification -- 4.4 Minimization For GMM -- 5 Data Example -- 6 Discussion -- 7 Example SAS and R Commands -- 7.1 Random-Intercept Models -- 7.2 Random-Slope Models -- 7.3 Independent GEE -- References -- Solving Probabilistic Discrete Event Systems with Moore -Penrose Generalized Inverse Matrix Method to Extract Longitudinal Characteristics from Cross-Sectional Survey Data -- 1 Background -- 2 A Review of the PDES for Smoking Behavior -- 3 Generalized-Inverse Matrix for PDES -- 4 Demonstration with the MASS Package in R -- 5 Discussion and Conclusions -- Appendix: R Program for Implementation of PDES -- References -- Part II Modelling Incomplete or Missing Data -- On the Effects of Structural Zeros in Regression Models -- 1 Introduction -- 2 Background -- 3 Modeling the Effects of Structural Zeros -- 3.1 Linear and Generalized Linear Models -- 3.2 Zero-Inflated Models -- 4 Simulation Studies -- 4.1 Continuous Response Y.

4.2 Zero-Inflated Poisson Response Y -- 5 A Case Study Example -- 6 Discussion -- References -- Modeling Based on Progressively Type-I Interval Censored Sample -- 1 Introduction -- 2 Data and Likelihood -- 2.1 Likelihood Function -- 2.2 Midpoint Approximation -- 2.3 EM-Algorithm -- 2.4 Moment Method -- 2.5 Method of Probability Plot -- 3 Weibull Distribution Modeling -- 3.1 Maximum Likelihood Estimation -- 3.2 Midpoint Approximation -- 3.3 Method of Moments -- 3.4 Estimation Based on Probability Plot -- 4 Generalized Exponential Distribution Modeling -- 4.1 Maximum Likelihood Estimation -- 4.2 Mid-Point Approximation Method -- 4.3 Method of Moments -- 4.4 Estimation Based on Probability Plot -- 5 Real Data Analysis: Non-Bayesian Approach -- 5.1 The Data -- 5.2 Model Selection -- 5.3 Model Comparison -- 5.4 Model Fitting -- 6 Markov Chain Monte Carlo for Bayesian Estimation -- 6.1 Likelihood Function and Bayes Estimation -- 6.2 A Markov Chain Monte Carlo Process -- 7 Real Data Analysis: Bayesian Approach -- 7.1 The Data -- 7.2 Model Selection -- Appendix -- References -- Techniques for Analyzing Incomplete Data in Public Health Research -- 1 Introduction -- 2 Overview of Missing Data -- 2.1 Pattern of Missingness -- 2.2 Missingness Mechanisms -- 2.2.1 Missing Completely at Random -- 2.2.2 Missing at Random -- 2.2.3 Missing Not at Random -- 2.2.4 Supporting Assumptions of Non-Response -- 3 Missing Data Methods -- 4 Multiple Imputation -- 4.1 Imputation Stage -- 4.1.1 Approaches -- 4.2 Analysis and Combination Stage -- 4.3 Rates of Missing Information -- 5 Example -- 6 Concluding Remarks -- References -- A Continuous Latent Factor Model for Non-ignorable Missing Data -- 1 Introduction -- 2 Models -- 2.1 Review of Continuous Latent Factor Model for Binary Outcomes -- 2.2 Proposed Model -- 3 Maximum Likelihood Estimation -- 3.1 Monte Carlo EM.

3.2 Execution of the E-Step via the Hybrid Algorithm -- 3.3 Maximization Step -- 3.4 Monitor Convergence of MCEM via Bridge Sampling -- 3.5 Standard Error Estimates -- 4 Application: Randomized Study of Dual or Triple Combinations of HIV-1 Reverse Transcriptase Inhibitors -- 4.1 Description of Study -- 4.2 Model Specification -- 4.3 Summary of Analyses Under MAR and MNAR -- 4.4 Distributions on Latent Factor -- 5 Conclusion and Discussion -- References -- Part III Healthcare Research Models -- Health Surveillance -- 1 Introduction -- 2 Background on Industrial Process Monitoring -- 2.1 Monitoring Continuous Outcomes -- 2.2 Monitoring Discrete Outcomes -- 2.3 Control Charts Based on Accumulating Data -- 2.3.1 CUSUM Charts -- 2.3.2 The Exponentially Weighted Moving Average Chart -- 2.4 Multivariate Control Charts -- 3 Health Care Monitoring -- 3.1 Risk-Adjusted Charts -- 3.1.1 Risk-Adjusted p-Charts -- 3.1.2 Risk-Adjusted CUSUM Charts -- 3.1.3 VLAD Charts -- 3.1.4 The Risk-Adjusted EWMA Chart -- 3.1.5 The Risk-Adjusted Sets Method -- 3.2 Other Aspects of Health Care Monitoring -- 4 Disease Surveillance -- 4.1 Modeling Disease Incidence -- 4.2 Detection Methods -- 4.3 Performance Metrics -- 4.3.1 Alternative Metrics -- 4.4 Detecting Seasonal Outbreaks: An Example -- 5 Summary -- 6 Further Reading -- 6.1 Industrial Process Monitoring -- 6.2 Health Care Monitoring -- 6.3 Disease Surveillance -- References -- Standardization and Decomposition Analysis: A Useful Analytical Method for Outcome Difference, Inequality and Disparity Studies -- 1 Introduction -- 2 Method -- 2.1 Algebraic Expression of SDA -- 2.2 Statistical Significance Testing for Component Effect -- 2.3 Computer Program for SDA -- 2.4 Example of Application -- 3 Results -- 4 Discussion -- References -- Cusp Catastrophe Modeling in Medical and Health Research -- 1 Linear and Continuous Paradigm.

2 Nonlinear and Continuous Paradigm -- 3 Nonlinear and Discrete Paradigm -- 4 Quantum Paradigm and Cusp Modeling -- 5 Do Current Research Need More Complex Analytical Paradigm? -- 6 Polynomial Regression Approach -- 6.1 Introduction to the Polynomial Cusp Catastrophe Modeling -- 6.2 Assessment of the Polynomial Cusp Catastrophe Modeling Method -- 6.2.1 Method 1: Significance of the Key Model Coefficients -- 6.2.2 Method 2: Assessment of Alternative Models -- 6.3 Procedure of Modeling Analysis -- 6.4 An Empirical Example -- 6.5 Allocation of Contrail Variables as Asymmetry and Bifurcation -- 7 Likelihood Approach with Stochastic Cusp Catastrophe Model -- 7.1 Introduction to the Likelihood Stochastic Approach -- 7.2 Advantages of the Likelihood Stochastic Cusp Modeling Approach -- 7.2.1 Modeling Cross-Sectional Data -- 7.2.2 Modeling More Than One Observed Variable -- 7.3 The R-Based Cusp Package for Modeling Analysis -- 7.4 Assessment of Data-Model Fit -- 7.5 Steps to Use R-Based Cusp Package -- 7.6 An Empirical Example -- 7.7 Additional Notes -- 7.7.1 Modeling Analysis -- 7.7.2 Results Interpretation -- References -- On Ranked Set Sampling Variation and Its Applications to Public Health Research -- 1 Introduction -- 2 RSS for a Univariate Population -- 2.1 Naive Estimation for the Population Mean -- 2.2 Quantiles and Distribution Function Estimation -- 2.3 Ratio Estimation -- 2.4 Regression Estimation for the Population Mean -- 3 Varied Set Size RSS -- 3.1 Naive Estimator of Population Means Using VSRSS -- 3.2 Ratio Estimation -- 4 Stratified Ranked Set Sample -- 5 Bivariate Population -- 5.1 Ratio Estimators -- 5.2 Regression Estimator Using BVRSS -- References -- Weighted Multiple Testing Correction for Correlated Endpoints in Survival Data -- 1 Introduction -- 2 Weighted Multiple Testing Correction for Correlated Time-to-Event Endpoints.

3 Simulations.

Description based on publisher supplied metadata and other sources.

Author notes provided by Syndetics

Ding-Geng (Din) Chen (PhD in Statistics from University of Guelph) is a professor in biostatistics at the University of Rochester. Previously, he was the Karl E. Peace endowed eminent scholar chair in biostatistics from the Jiann-Ping Hsu College of Public Health at the Georgia Southern University. He is also a senior biostatistics consultant for biopharmaceuticals and government agencies with extensive expertise in clinical trials and bioinformatics. He has more than 100-refereed professional publications and co-authored five books in biostatistics. Professor Chen was Section Chair (2011-2014) of Applied Public Health Statistics, American Public Health Association. Professor Jeffrey Wilson was Section Chair (2010-2013) of Applied Public Health Statistics, American Public Health Association. He was also a former Director of Biostatistics Core in the NIH Center Alzheimer. He is also the former Director of the School of Health Management and Policy. He is an Associate Editor for The JMIG and Chair of the Editorial Board of AJPH. His research experience includes grants from the NSF, USDA and NIH. He has published several articles in leading journals in Statistics and Healthcare. He teaches statistics at the graduate level in topics including GLM and GLIMMIX.

There are no comments for this item.

Log in to your account to post a comment.