Chapter
1.1.3 What are Statistics?
1.1.4 Approach to Learning
1.2 Formulating a Research Question
1.2.1 Importance of a Well-Defined Research Question
1.2.2 Development of Research Ideas
1.3 Rates: Incidence and Prevalence
1.3.1 Why Do We Need Rates?
1.3.2 Measures of Disease Frequency
1.3.5 Relationship Between Incidence, Duration, and Prevalence
1.4 Concepts of Prevention
1.4.2 Primary, Secondary, and Tertiary Prevention
1.5 Answers to Self-Assessment Exercises
2 Routine Data Sources and Descriptive Epidemiology
Introduction and Learning Objectives
2.1 Routine Collection of Health Information
2.1.2 Compiling Mortality Statistics: The Example of England and Wales
2.1.4 Suicide Among Young Women
2.1.5 Variations in Deaths of Very Young Children
2.2 Descriptive Epidemiology
2.2.1 What is Descriptive Epidemiology?
2.2.2 International Variations in Rates of Lung Cancer
2.2.3 Illness (Morbidity)
2.2.4 Sources of Information on Morbidity
2.2.5 Notification of Infectious Disease
2.2.6 Illness Seen in General Practice
2.3 Information on the Environment
2.3.1 Air Pollution and Health
2.3.2 Routinely Available Data on Air Pollution
2.4 Displaying, Describing, and Presenting Data
2.4.1 Displaying the Data
2.4.2 Calculating the Frequency Distribution
2.4.3 Describing the Frequency Distribution
2.4.4 The Relative Frequency Distribution
2.4.5 Scatterplots, Linear Relationships and Correlation
2.5 Routinely Available Health Data
2.5.2 Classification of Routine Health Information Sources
2.5.5 Population-Based Health Information
2.5.6 Deprivation Indices
2.5.7 Routine Data Sources for Countries Other Than the UK
2.6 Descriptive Epidemiology in Action
2.6.1 The London Smogs of the 1950s
2.7 Overview of Epidemiological Study Designs
2.8 Answers to Self-Assessment Exercises
Introduction and Learning Objectives
3.1 Health Inequalities in Merseyside
3.1.1 Socio-Economic Conditions and Health
3.1.2 Comparison of Crude Death Rates
3.1.3 Usefulness of a Summary Measure
3.2 Indirect Standardisation: Calculation of the Standardised Mortality Ratio (SMR)
3.2.1 Mortality in Liverpool
3.2.2 Interpretation of the SMR
3.2.3 Dealing With Random Variation: The 95 per cent Confidence Interval
3.2.4 Increasing Precision of the SMR Estimate
3.2.5 Mortality in Sefton
3.2.7 Indirectly Standardised Mortality Rates
3.3 Direct Standardisation
3.3.2 An Example: Changes in Deaths From Stroke Over Time
3.3.3 Using the European Standard Population
3.3.4 Direct or Indirect: Which Method is Best?
3.4 Standardisation for Factors Other Than Age
3.5 Answers to Self-Assessment Exercises
Introduction and Learning Objectives
4.1.1 Defining the Research Question
4.1.2 Political Context of Research
4.2.4 Simple Random Sampling
4.2.5 Stratified Sampling
4.2.6 Cluster Random Sampling
4.2.7 Multistage Random Sampling
4.2.8 Systematic Sampling
4.2.9 Convenience Sampling
4.2.10 Sampling People Who are Difficult to Contact
4.2.12 Sampling in Natsal-3
4.3.1 Why Do We Need a Sampling Frame?
4.4 Sampling Error, Confidence Intervals, and Sample Size
4.4.1 Sampling Distributions and the Standard Error
4.4.3 Key Properties of the Normal Distribution
4.4.4 Confidence Interval (CI) for the Sample Mean
4.4.5 Estimating Sample Size
4.4.6 Sample Size for Estimating a Population Mean
4.4.7 Standard Error and 95 per cent CI for a Population Proportion
4.4.8 Sample Size to Estimate a Population Proportion
4.5.1 Determining the Response Rate
4.5.2 Assessing Whether the Sample is Representative
4.5.3 Maximising the Response Rate
4.6.1 Introduction: The Importance of Good Measurement
4.6.2 Interview or Self-Completed Questionnaire?
4.6.3 Principles of Good Questionnaire Design
4.6.4 Development of a Questionnaire
4.6.5 Checking How Well the Interviews and Questionnaires Have Worked
4.6.6 Assessing Measurement Quality
4.6.7 Overview of Sources of Error
4.7 Data Types and Presentation
4.7.3 Displaying and Summarising the Data
4.8 Answers to Self-Assessment Exercises
Introduction and Learning Objectives
5.1 Why Do a Cohort Study?
5.1.1 Objectives of the Study
5.3.1 Importance of Good Measurement
5.3.2 Identifying and Avoiding Measurement Error
5.3.3 The Measurement of Blood Pressure
5.4.3 Non-Fatal Cases (Morbidity)
5.4.4 Challenges Faced with Follow-Up of a Cohort in a Different Setting
5.4.5 Assessment of Changes During Follow-Up Period
5.5 Basic Presentation and Analysis of Results
5.5.1 Initial Presentation of Findings
5.5.3 Hypothesis Test for Categorical Data: The Chi-Squared Test
5.5.4 Hypothesis Tests for Continuous Data: The z-Test and the t-Test
5.6 How Large Should a Cohort Study Be?
5.6.1 Perils of Inadequate Sample Size
5.6.2 Sample Size for a Cohort Study
5.6.3 Example of Output from Sample Size Calculation
5.7 Assessing Whether an Association is Causal
5.7.1 The Hill Viewpoints
5.7.2 Confounding: What Is It and How Can It Be Addressed?
5.7.3 Does Smoking Cause Heart Disease?
5.7.4 Confounding in the Physical Activity and Cancer Study
5.7.5 Methods for Dealing with Confounding
5.8 Simple Linear Regression
5.8.1 Approaches to Describing Associations
5.8.2 Finding the Best Fit for a Straight Line
5.8.3 Interpreting the Regression Line
5.8.4 Using the Regression Line
5.8.5 Hypothesis Test of the Association Between the Explanatory and Outcome Variables
5.8.6 How Good is the Regression Model?
5.8.7 Interpreting SPSS Output for Simple Linear Regression Analysis
5.8.8 First Table: Variables Entered/Removed
5.9 Introduction to Multiple Linear Regression
5.9.1 Principles of Multiple Regression
5.9.2 Using Multivariable Linear Regression to Study Independent Associations
5.9.3 Investigation of the Effect of Work Stress on Bodyweight
5.9.4 Multiple Regression in the Cancer Study
5.9.5 Overview of Regression Methods for Different Types of Outcome
5.10 Answers to Self-Assessment Exercises
Introduction and Learning Objectives
6.1 Why do a Case–Control Study?
6.1.3 Approach to Analysis
6.1.4 Retrospective Data Collection
6.1.5 Applications of the Case–Control Design
6.2 Key Elements of Study Design
6.2.1 Selecting the Cases
6.2.3 Exposure Assessment
6.2.4 Bias in Exposure Assessment
6.3 Basic Unmatched and Matched Analysis
6.3.1 The Odds Ratio (OR)
6.3.2 Calculation of the OR–Simple Matched Analysis
6.3.3 Hypothesis Tests for Case–Control Studies
6.4 Sample Size for a Case–Control Study
6.4.2 What Information is Required?
6.4.3 An Example of Sample Size Calculation Using OpenEpi
6.5 Confounding and Logistic Regression
6.5.3 Logistic Regression
6.5.4 Example: Multivariable Logistic Regression
6.5.5 Matched Studies – Conditional Logistic Regression
6.5.6 Interpretation of Adjusted Results from the New Zealand Study
6.6 Answers to Self-Assessment Exercises
Introduction and Learning Objectives
Typology of Intervention Study Designs Described in This Chapter
7.1 Why Do an Intervention Study?
7.1.2 Structure of a Randomised, Controlled Intervention Study
7.2 Key Elements of Intervention Study Design
7.2.1 Defining Who Should be Included and Excluded
7.2.2 Intervention and Control
7.2.6 Ethical Issues for Intervention Studies
7.3 The Analysis of Intervention Studies
7.3.1 Review of Variables at Baseline
7.3.3 Compliance with the Treatment Allocation
7.3.4 Analysis by Intention-to-Treat
7.3.5 Analysis per Protocol
7.3.6 What is the Effect of the Intervention?
7.3.7 Drawing Conclusions
7.3.8 Adjustment for Variables Known to Influence the Outcome
7.3.10 The Crossover Trial
7.4 Testing More-Complex Interventions
7.4.2 Randomised Trial of Individuals for a Complex Intervention
7.4.4 Analysis and Interpretation
7.4.5 Departure from the Ideal Blinded RCT Design
7.4.6 The Cluster Randomised Trial
7.4.7 The Community (Cluster) Randomised Trial
7.4.8 Non-Randomised Intervention Designs
7.4.9 The Natural Experiment
7.5 Analysis of Intervention Studies Using a Cluster Design
7.5.1 Why Does the Use of Clusters Make a Difference?
7.5.2 Summarising Clustering Effects: The Intra-Class Correlation Coefficient
7.5.3 Multi-Level Modelling
7.5.4 Analysis of the Cluster RCT of Physical Activity
7.6 How Big Should the Intervention Study Be?
7.6.2 Sample Size for a Trial with Categorical Data Outcomes
7.6.3 One-Sided and Two-Sided Tests
7.6.4 Sample Size for a Trial with Continuous Data Outcomes
7.6.5 Sample Size for an Intervention Study Using Cluster Design
7.6.6 Estimation of Sample Size is not a Precise Science
7.7 Intervention Study Registration, Management, and Reporting
7.7.4 Reporting Standards (CONSORT)
7.8 Answers to Self-Assessment Exercises
8 Life Tables, Survival Analysis, and Cox Regression
Introduction and Learning Objectives
8.1.2 Why Do We Need Survival Analysis?
8.1.4 Kaplan–Meier Survival Curves
8.1.5 Kaplan–Meier Survival Curves
8.1.7 Interpretation of the Kaplan–Meier Survival Curve
8.2.2 The Hazard Function
8.2.3 Assumption of Proportional Hazards
8.2.4 The Cox Regression Model
8.2.5 Checking the Assumption of Proportional Hazards
8.2.6 Interpreting the Cox Regression Model
8.2.8 Application of Cox Regression
8.3.2 Current Life Tables and Life Expectancy at Birth
8.3.3 Life Expectancy at Other Ages
8.3.4 Healthy or Disability-Free Life Expectancy
8.3.5 Abridged Life Tables
8.4 Answers to Self-Assessment Exercises
9 Systematic Reviews and Meta-Analysis
Introduction and Learning Objectives
Increasing Power by Combining Studies
9.1 The Why and How of Systematic Reviews
9.1.1 Why is it Important that Reviews be Systematic?
9.1.2 Method of Systematic Review – Overview and Developing a Protocol
9.1.3 Deciding on the Research Question and Objectives for the Review
9.1.4 Defining Criteria for Inclusion and Exclusion of Studies
9.1.5 Identifying Relevant Studies
9.1.6 Assessment of Methodological Quality
9.1.8 Describing the Results
9.2 The Methodology of Meta-Analysis
9.2.1 Method of Meta-Analysis – Overview
9.2.2 Assessment of Publication Bias – the Funnel Plot
9.2.4 Calculating the Pooled Estimate
9.2.5 Presentation of Results: Forest Plot
9.2.6 Sensitivity Analysis
9.2.7 Statistical Software for the Conduct of Meta-Analysis
9.2.8 Another Example of the Value of Meta-Analysis – Identifying a Dangerous Treatment
9.3 Systematic Reviews and Meta-Analyses of Observational Studies
9.3.2 Why Conduct a Systematic Review of Observational Studies?
9.3.3 Approach to Meta-Analysis of Observational Studies
9.3.4 Method of Systematic Review of Observational Studies
9.3.5 Method of Meta-Analysis of Observational Studies
9.4 Reporting and Publishing Systematic Reviews and Meta-Analyses
9.5 The Cochrane Collaboration
9.5.2 Cochrane Collaboration Logo
9.5.3 Collaborative Review Groups
9.6 Answers to Self-Assessment Exercises
10 Prevention Strategies and Evaluation of Screening
Introduction and Learning Objectives
10.1.1 Relative and Attributable Risk
10.1.3 Attributable Fraction (AF) for a Dichotomous Exposure
10.1.4 Attributable Fraction for Continuous and Multiple Category Exposures
10.1.5 Years of Life Lost (YLL) and Years Lived with Disability (YLD)
10.1.6 Disability-Adjusted Life Years (DALYs)
10.1.7 Burden Attributable to Specific Risk Factors
10.2 Strategies of Prevention
10.2.1 The Distribution of Risk in Populations
10.2.2 High-Risk and Population Approaches to Prevention
10.2.3 Safety and the Population Strategy
10.2.4 The High-Risk and Population Strategies Revisited
10.2.5 Implications of Genomic Research for Disease Prevention
10.3 Evaluation of Screening Programmes
10.3.1 Purpose of Screening
10.3.2 Criteria for Programme Evaluation
10.3.3 Assessing Validity of a Screening Test
10.3.4 Methodological Issues in Studies of Screening Programme Effectiveness
10.3.5 Are the Wilson–Jungner Criteria Relevant Today?
10.4 Cohort and Period Effects
10.4.1 Analysis of Change in Risk Over Time
10.4.2 Example: Suicide Trends in UK Men and Women
10.5 Answers to Self-Assessment Exercises
11 Probability Distributions, Hypothesis Testing, and Bayesian Methods
Introduction and Learning Objectives
11.1 Probability Distributions
11.1.1 Probability – A Brief Review
11.1.2 Introduction to Probability Distributions
11.1.3 Types of Probability Distribution
11.1.4 Probability Distributions: Implications for Statistical Methods
11.2 Data That Do Not Fit a Probability Distribution
11.2.1 Robustness of an Hypothesis Test
11.2.2 Transforming the Data
11.2.3 Principles of Non-Parametric Hypothesis Testing
11.3 Hypothesis Testing: Summary of Common Parametric and Non-Parametric Methods
11.3.2 Review of Hypothesis Tests
11.3.3 Fundamentals of Hypothesis Testing
11.3.4 Summary: Stages of Hypothesis Testing
11.3.5 Comparing Two Independent Groups
11.3.6 Comparing Two Paired (or Matched) Groups
11.3.7 Testing for Association Between Two Groups
11.3.8 Comparing More Than Two Groups
11.3.9 Association Between Categorical Variables
11.4 Choosing an Appropriate Hypothesis Test
11.4.2 Using a Guide Table for Selecting a Hypothesis Test
11.4.3 The Problem of Multiple Significance Testing
11.5.1 Introduction: A Different Approach to Inference
11.5.2 Bayes’ Theorem and Formula
11.5.3 Application and Relevance
11.6 Answers to Self-Assessment Exercises
Quantitative Methods for Health Research
：A Practical Interactive Guide to Epidemiology and Statistics
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
