JAMA guide to statistics and methods

Includes bibliographical references and index.

Interventional Studies -- Trial Strategy and Design -- Enrollment, Allocation of Treatment, and Ethics -- Measurement Outcome and Analysis and Interpretation of Results -- Application of Results -- Observational Studies -- Study Strategy and Design -- Assessment of Risk Factors and Exposures -- Measurement Outcome and Analysis and Interpretation of Results -- Application of Results -- Practical Guide to Data Sets -- INTERVENTIONAL STUDIES: Trial Strategy and Design -- Noninferiority Trials: Is a New Treatment Almost as Effective as Another? -- Use of the Method -- Why Are Noninferiority Trials Conducted? -- What Are the Limitations of Noninferiority Trials? -- Why Was a Noninferiority Trial Conducted in This Case? -- How Should the Results Be Interpreted? -- Caveats to Consider When Looking at a Noninferiority Trial -- Dose-Finding Trials: Optimizing Phase 2 Data in the Drug Development Process -- Use of the Method --

Contents note continued: Why Are Dose-Response Models Used? -- What Are the Limitations of Dose-Response Modeling? -- Why Did the Authors Use Dose-Response Modeling in This Particular Study? -- How Should the Dose-Response Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Results Based on a Dose-Response Model -- Pragmatic Trials: Practical Answers to "Real World" Questions -- Use of the Method -- Why Are Pragmatic Trials Conducted? -- Description of the Method -- What Are the Limitations of Pragmatic Trials? -- Why Was a Pragmatic Trial Conducted in This Case? -- How Should the Results Be Interpreted? -- Cluster Randomized Trials: Evaluating Treatments Applied to Groups -- Use of the Method -- Why Is Cluster Randomization Used? -- What Are Limitations of Cluster Randomization? -- Why Did the Authors Use Cluster Randomization in This Particular Study? -- How Should Cluster Randomization Findings Be Interpreted in This Particular Study? --

Contents note continued: Caveats to Consider When Looking at a Cluster Randomized Trial -- The Stepped-Wedge Clinical Trial: Evaluation by Rolling Deployment -- Use of the Method -- Why Is a Stepped-Wedge Clinical Trial Design Used? -- Description of the Stepped-Wedge Clinical Trial Design -- Limitations of the Stepped-Wedge Design -- How Was the Stepped-Wedge Design Used? -- How Should a Stepped-Wedge Clinical Trial Be Interpreted? -- Sample Size Calculation for a Hypothesis Test -- Use of the Method -- Why Is Power Analysis Used? -- What Are the Limitations of Power Analysis? -- Why Did the Authors Use Power Analysis in This Particular Study? -- How Should This Method's Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Results Based on Power Analysis -- Minimal Clinically Important Difference: Defining What Really Matters to Patients -- Use of the Method -- Why Is the MCID Used? -- What Are the Limitations of MCID Derivation Methods? --

Contents note continued: Why Did the Authors Use MCID in This Particular Study? -- How Should MCID Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Results Based on MClDs -- Enrollment, Allocation of Treatment, and Ethics -- Randomization in Clinical Trials: Permuted Blocks and Stratification -- Explanation of the Concept -- What Are Permuted Blocks and Stratified Randomization? -- Why Are Permuted Blocks and Stratified Randomization Important? -- Limitations of Permuted Block Randomization and Stratified Randomization -- How Were These Approaches to Randomization Used? -- How Does the Approach to Randomization Affect the Trial's Interpretation? -- Equipoise in Research: Integrating Ethics and Science in Human Research -- What Is Equipoise? -- Why Is Equipoise Important? -- What Are the Limitations of Equipoise? -- How Is Equipoise Applied in This Case? -- How Does Equipoise Influence the Interpretation of the Study? --

Contents note continued: Measurement Outcomes and Analysis and Interpretation of Results -- Time-to-Event Analysis -- Use of the Method -- Why Is Time-to-Event Analysis Used? -- What Are the Limitations of the Proportional Hazards Model? -- How Should Time-to-Event Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Results from a Time-to-Event Analysis -- The "Utility" in Composite Outcome Measures: Measuring What Is Important to Patients -- Why Are Composite End Points Used in Clinical Studies? -- Limitations of Composite End Points -- How Were Composite End Points Used in This Study? -- How Does the Use of a Composite End Point Affect the Interpretation of This Study? -- Missing Data: How to Best Account for What Is Not Known -- Use of the Method -- Why Are These Methods Used? -- What Are the Limitations of These Methods? -- Why Did the Authors Use This Method in This Particular Study? --

Contents note continued: How Should This Method's Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at the Results in This Study Based on This Method -- The Intention-to-Treat Principle: How to Assess the True Effect of Choosing a Medical Treatment -- Use of the Method -- Why Is ITT Analysis Used? -- What Are the Limitations of ITT Analysis? -- Why Did the Authors Use ITT Analysis in This Particular Study? -- Caveats to Consider When Looking at Results Based on ITT Analysis -- Analyzing Repeated Measurements Using Mixed Models -- Use of the Method -- Why Are Mixed Models Used for Repeated Measures Data? -- What Are the Limitations of Mixed Models? -- Why Did the Authors Use Mixed Models in This Particular Study? -- Caveats to Consider When Looking at Results From Mixed Models -- Logistic Regression: Relating Patient Characteristics to Outcomes -- Use of the Method -- Why Is Logistic Regression Used? -- Description of the Method --

Contents note continued: What Are the Limitations of Logistic Regression? -- Why Did the Authors Use Logistic Regression in This Study? -- How Should the Results of Logistic Regression -- Be Interpreted in This Particular Study? -- Caveats to Consider When Assessing the Results of a Logistic Regression Analysis -- Logistic Regression Diagnostics: Understanding How Well a Model Predicts Outcomes -- Use of the Method -- Why Are Logistic Regression Model Diagnostic Used? -- Description of the Method -- What Are the Limitations of Logistic Regression Diagnostic? -- Why Did the Authors Use Logistic Regression Diagnostics in -- This Particular Study? -- How Should the Results of Logistic Regression Diagnostics Be Interpreted in This Particular Study? -- Caveats to Consider When Assessing the Results of Logistic Regression Diagnostics -- Number Needed to Treat: Conveying the Likelihood of a Therapeutic Effect -- Explanation of the Concept -- What Is the NNT? --

Contents note continued: Why Is the NNT Important? -- Limitations and Alternatives to the NNT -- How Was the Concept of NNT Applied in This Particular Study? -- How Should the NNT Be Interpreted in the Study by Zhao et al? -- Multiple Comparison Procedures -- Use of the Method -- Why Are Multiple Comparison Procedures Used? -- What Are the Limitations of Multiple Comparison Procedures? -- Why Did the Authors Use Multiple Comparison Procedures in This Particular Study? -- How Should This Method's Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Multiple Comparison Procedures -- To Adjust or Not -- Confirmatory vs Exploratory -- FWER vs FDR -- Definition of Family -- Gatekeeping Strategies for Avoiding False-Positive Results in Clinical Trials With Many Comparisons -- Use of the Method -- Why Is Serial Gatekeeping Used? -- Description of the Method -- What Are the Limitations of Gatekeeping Strategies? --

Contents note continued: How Was Gatekeeping Used in This Case? -- How Should the Results Be Interpreted? -- Multiple Imputation: A Flexible Tool for Handling Missing Data -- Use of the Method -- Why Is Multiple Imputation Used? -- What Are the Limitations of Multiple Imputation? -- Why Did the Authors Use Multiple Imputation in This Particular Study? -- How Should Multiple Imputation Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Results Based on Multiple Imputation -- Interpretation of Clinical Trials That Stopped Early -- Use of the Method -- Why Is Early Stopping Used? -- What Are the Limitations of Early Stopping? -- Why Did the Authors Use Early Stopping in This Study? -- How Should Early Stopping Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at a Trial That Stopped Early -- Bayesian Analysis: Using Prior Information to Interpretthe Results of Clinical Trials -- Prior Information --

Contents note continued: What Is Prior Information? -- Why Is Prior Information Important? -- Limitations of Prior Information -- How Was Prior Information Used? -- How Should the Trial Results Be Interpreted in Light of the Prior Information? -- Application of Results -- Decision Curve Analysis -- Use of the Method -- Why Is DCA Used? -- What Are the Limitations of the DCA Method? -- Why Did the Authors Use DCA in This Particular Study? -- How Should DCA Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Results Based on DCA -- Methods for Evaluating Changes in Health Care Policy---The Difference-in-Differences Approach -- Use of the Method -- Why Was the Difference-in-Differences Method Used? -- What Are the Limitations of the Difference-in-Differences Method? -- Why Did the Authors Use the Difference-in-Differences Method? -- How Should the Findings Be Interpreted? --

Contents note continued: Caveats to Consider When Assessing the Results of a Difference-in-Differences Analysis -- OBSERVATIONAL STUDIES Study Strategy and Design -- Case-Control Studies: Using "Real-world" Evidence to Assess Association -- Explanation of the Method -- What Are Case-Control and Nested Case-Control Studies? -- Why Are Case-Control Studies Used? -- Limitations of Case-Control Studies -- How Was the Method Applied in This Case? -- How Does the Case-Control Design Affect the Interpretation of the Study? -- Meta-analyses Can Be Credible and Useful: A New Standard -- Overview -- The Existing Evidence -- Improvements -- Conclusions -- Mendelian Randomization -- Use of the Method -- Why Is Mendelian Randomization Used? -- What Are the Limitations of Mendelian Randomization? -- How Did the Authors Use Mendelian Randomization? -- Caveats to Consider When Evaluating Mendelian Randomization Studies --

Contents note continued: Using the E-Value to Assess the Potential Effect of Unmeasured Confounding in Observational Studies -- Why ls the E-Value Used? -- What Are the Limitations of the E-Value? -- Why Did the Authors Use the E-Value in This Particular Study? -- How Should the E-Value Findings Be Interpreted in This Particular Study? -- Caveats to Consider When Looking at Results Based on the E-Value -- Assessment of Risk Factors and Exposures -- Confounding by Indication in Clinical Research -- Addressing Confounding in Clinical Research -- Use of Methods to Control Confounding -- What Are the Limitations of Methods to Control for Confounding? -- How Should the Results Be Interpreted? -- Caveats to Consider When Interpreting an Analysis Intended to Adjust for Confounding by Indication -- Mediation Analysis -- Use of the Method -- Why Is Mediation Analysis Used? -- Description of Mediation Analysis -- What Are the Limitations of Mediation Analysis? --

Contents note continued: Why Did the Authors Use Mediation Analysis? -- Caveats to Consider When Assessing the Results of Mediation Analysis -- Measurement Outcome and Analysis and Interpretation of Results -- Odds Ratios---Current Best Practice and Use -- Why Report Odds Ratios From Logistic Regression? -- What Are the Limitations of Odds Ratios? -- How Did the Authors Use Odds Ratios? -- How Should the Findings Be Interpreted? -- What Caveats Should the Reader Consider? -- Marginal Effects---Quantifying the Effect of Changes in Risk Factors in Logistic Regression Models -- Use of Marginal Effects -- Why Are Marginal Effects Used? -- What Are Marginal Effects? -- What Are the Limitations of Marginal Effects? -- How Should the Marginal Effects Be Interpreted in Cummings et al? -- Adjusting for Covariates: A Source of False Findings in Published Research Studies -- Treatment Effects in Multicenter Randomized Clinical Trials --

Contents note continued: Estimating Treatment Effects in Multicenter Clinical Trials -- Why Are Differences Between Centers Considered -- When Estimating Treatment Effects? -- How Are Center Effects Incorporated into Estimates of Treatment Effects? -- Limitations of Estimates of Treatment Effects from Multicenter Clinical Trials -- How Were the Multicenter Data Analyzed in the Study by Dodick et al? -- How Should the Results From This Study Be Interpreted? -- The Propensity Score -- Use of the Method -- Why Were Propensity Methods Used? -- What Are the Limitations of Propensity Score Methods? -- Why Did the Authors Use Propensity Methods? -- How Should the Findings Be Interpreted? -- What Caveats Should the Reader Consider When Assessing the Results of Propensity Analyses? -- Using Free-Response Receiver Operating Characteristic Curves to Assess the Accuracy of Machine Diagnosis of Cancer -- Why Are FROC Curves Used? -- How Are FROC Curves Constructed? --

Contents note continued: What Are the Limitations of FROC Curves? -- How Should the FROC Curves Be Interpreted in This Study? -- Caveats to Consider When Looking at FROC Curves -- Random-Effects Meta-analysis: Summarizing Evidence With Caveats -- Why Is Random-Effects Meta-analysis Used? -- Description of Random-Effects Meta-analysis -- Why Did the Authors Use Random-Effects Meta-analysis? -- What Are Limitations of a Random-Effects Meta-analysis? -- Caveats to Consider When Assessing the Results of a Random-Effects Meta-analysis -- How Should the Results of a Random-Effects Meta-analysis Be Interpreted in This Particular Study? -- Bayesian Hierarchical Models -- Why Is a BHM Used? -- What Are the Limitations of BHMs? -- How Were BHMs Used in This Case? -- How Should BHMs Be Interpreted? -- Application of Results -- Evaluating Discrimination of Risk Prediction Models: The C Statistic -- Use of the Method -- Why Are C Statistics Used? --

Contents note continued: What Are the Limitations of the C Statistic? -- Why Did the Authors Use C Statistics in Their Study? -- How Should the Findings Be Interpreted? -- Caveats to Consider When Using C Statistics to Assess Predictive Model Performance -- Overview of Cost-effectiveness Analysis -- The Use of Cost-effectiveness Analysis -- Description of Cost-effectiveness Analysis -- Limitation in the Use of Cost-effectiveness Analysis -- How Was the Cost-effectiveness Analysis Performed in This Study? -- How Should the Cost-effectiveness Analysis Be Interpreted in This Study? -- Choosing a Time Horizon in Cost and Cost-effectiveness Analyses -- The Use of Time Horizon in a Cost-effectiveness Analysis -- Limitations Regarding Selection of Time Horizons -- How Was Time Horizon Defined and Used in the Study? -- How Does the Time Horizon Selected by Wittenborn et al Affect the Interpretation of the Study? -- On Deep Learning for Medical Image Analysis --

Contents note continued: Opening the Deep Learning Black Box -- What Are the Limitations of Deep Learning Methods? -- PRACTICAL GUIDE TO DATA SETS -- A Checklist to Elevate the Science of Surgical Database Research -- Tips for Analyzing Large Data Sets From the JAMA Surgery Statistical Editors -- Study Population Considerations -- Methodological and Sample Size Considerations -- Data Elements and Presentation -- Analytic and Statistical Considerations -- Conclusions -- Practical Guide to Surgical Data Sets: Healthcare Cost and Utilization Project National Inpatient Sample (NIS) -- Introduction to the Healthcare Cost and Utilization Project -- Strengths of Administrative Data -- Limitations of Administrative Data and the HCUP Databases -- Administrative Data Limitations -- NIS Limitations -- Critical Methodologic Considerations -- Unique Capabilities of HCUP -- Practical Guide to Surgical Data Sets: Surveillance, Epidemiology, and End Results (SEER) Database -- Introduction --

Contents note continued: Data Considerations -- Data Sources -- Time Trend Data -- Cancer Data -- Treatment Data -- Statistical Considerations -- Conclusions -- Practical Guide to Surgical Data Sets: Medicare Claims Data -- Introduction -- Pros and Cons of Medicare Data -- Potential Avenues of Research -- Comparative Effectiveness Research -- Health Policy Evaluation -- Understanding Variation -- Where to Find More Information -- Practical Guide to Surgical Data Sets: Military Health System Tricare Encounter Data -- Introduction -- Use of the Data -- Salient and Unique Features of the Data Set -- How Are Data Compiled? -- What Are Common Outcomes That Can Be Studied? -- What Are the Limitations With This Data Set? -- Statistical Considerations -- Where to Find More Information -- Practical Guide to Surgical Data Sets: Veterans Affairs Surgical Quality Improvement Program (VASQIP) -- Advent of the Veterans Affairs Surgical Quality Improvement Program -- Data Considerations --

Contents note continued: Patients -- Procedure -- Hospital -- Outcomes -- Utility and Unique Features of VASQIP -- Statistical Considerations -- Conclusions -- Practical Guide to Surgical Data Sets: National Surgical Quality Improvement Program (NSQIP) and Pediatric NSQIP -- Introduction -- Data Elements and Considerations -- Access and Logistics -- Variables and Outcomes -- Statistical Methodology -- Limitations -- Conclusions -- Practical Guide to Surgical Data Sets: Metabolic and Bariatric Surgery Accreditation and Quality Program (MBSAQIP) -- Introduction -- Data Considerations for the MBSAQIP Participant Use File -- Deidentification of Patients, Facilities, and Clinicians -- MBSAQIP PUF Content -- Outcomes -- Statistical Considerations -- MBSAQIP PUF Advantages and Limitations -- Conclusions -- Practical Guide to Surgical Data Sets: National Cancer Database (NCDB) -- Introduction -- Data Element Considerations -- Hospital Variables -- Tumor Characteristics --

Contents note continued: Treatment Variables -- Outcomes -- Analytic and Statistical Considerations -- Conclusions -- Practical Guide to Surgical Data Sets: National Trauma Data Bank (NTDB) -- Introduction -- Data Compilation and Structure -- Methods -- Limitations -- Recommended Reading -- Conclusions -- Practical Guide to Surgical Data Sets: Society for Vascular Surgery Vascular Quality Initiative (SVSVQI) -- Features of the Data Set -- Statistical Considerations -- Conclusions -- Practical Guide to Surgical Data Sets: Society of Thoracic Surgeons (STS) National Database -- Introduction -- Data Element Considerations -- Adult Cardiac Surgery Database (ACSD) -- Congenital Heart Surgery Database -- General Thoracic Surgery Database -- Data Source -- Outcomes and Other Key Measures -- Accessing Data -- Statistical Considerations -- Limitations -- Conclusions.

"A new, accessible guide to explanations about statistical analytic approaches and methods used in medical research from the experts at JAMA"--

Also available online.