Quality of Life Outcomes in Clinical Trials and Health-Care Evaluation

Stephen J. Walters – School of Health and Related Research, University of Sheffield. Dr Walters has had experience both in research and teaching, and is currently the Senior Lecturer in Medical Statistics at Sheffield University. He has conducted numerous grant-funded research projects, and has nearly 150 publications to his name. These include 85 articles in a range of refereed journals, 2 co-authored books, and contributed chapters in three other books.

Preface. 1 Introduction.

Summary.

1.1 What is quality of life?

1.2 Terminology.

1.3 History.

1.4 Types of quality of life measures.

1.5 Why measure quality of life?

1.6 Further reading.

2 Measuring quality of life.

Summary.

2.1 Introduction.

2.2 Principles of measurement scales.

2.3 Indicator and causal variables.

2.4 The traditional psychometric model.

2.5 Item response theory.

2.6 Clinimetricscal.

2.7 Measuring quality of life: indicator or causal items.

2.8 Developing and testing questionnaires.

2.9 Further reading.

3 Choosing a quality of life measure for your study.

Summary.

3.1 Introduction.

3.2 How to choose between instruments.

3.3 Appropriateness.

3.4 Acceptability.

3.5 Feasibility.

3.6 Validity.

3.7 Reliability.

3.8 Responsiveness.

3.9 Precision.

3.10 Interpretability.

3.11 Finding quality of life instruments.

4 Design and sample size issues: How many subjects do I need for my study?

Summary.

4.1 Introduction.

4.2 Significance tests, P-values and power.

4.3 Sample sizes for comparison of two independent groups.

4.4 Choice of sample size method with quality of life outcomes.

4.5 Paired data.

4.6 Equivalence/non-inferiority studies.

4.7 Unknown standard deviation and effect size.

4.8 Cluster randomized controlled trials.

4.9 Non-response.

4.10 Unequal groups.

4.11 Multiple outcomes/endpoints.

4.12 Three or more groups.

4.13 What if we are doing a survey, not a clinical trial?.

4.14 Sample sizes for reliability and method comparison studies.

4.15 Post-hoc sample size calculations.

4.16 Conclusion: Usefulness of sample size calculations.

4.17 Further reading.

5 Reliability and method comparison studies for quality of life measurements.

Summary.

5.1 Introduction.

5.2 Intra-class correlation coefficient.

5.3 Agreement between individual items on a quality of life questionnaire.

5.4 Internal consistency and Cronbach's alpha.

5.5 Graphical methods for assessing reliability or agreement between two quality of life measures or assessments.

5.6 Further reading.

5.7 Technical details.

6 Summarizing, tabulating and graphically displaying quality of life outcomes.

Summary.

6.1 Introduction.

6.2 Graphs.

6.3 Describing and summarizing quality of life data.

6.4 Presenting quality of life data and results in tables and graphs.

7 Cross-sectional analysis of quality of life outcomes.

Summary.

7.1 Introduction.

7.2 Hypothesis testing (using P-values).

7.3 Estimation (using confidence intervals).

7.4 Choosing the statistical method.

7.5 Comparison of two independent groups.

7.6 Comparing more than two groups.

7.7 Two groups of paired observations.

7.8 The relationship between two continuous variables.

7.9 Correlation.

7.10 Regression.

7.11 Multiple regression.

7.12 Regression or correlation?.

7.13 Parametric versus non-parametric methods.

7.14 Technical details: Checking the assumptions for a linear regression analysis.

8 Randomized controlled trials.

Summary.

8.1 Introduction.

8.2 Randomized controlled trials.

8.3 Protocols.

8.4 Pragmatic and explanatory trials.

8.5 Intention-to-treat and per-protocol analyses.

8.6 Patient flow diagram.

8.7 Comparison of entry characteristics.

8.8 Incomplete data.

8.9 Main analysis.

8.10 Interpretation of changes/differences in quality of life scores.

8.11 Superiority and equivalence trials.

8.12 Adjusting for other variables.

8.13 Three methods of analysis for pre-test/post-test control group designs.

8.14 Cross-over trials.

8.15 Factorial trials.

8.16 Cluster randomized controlled trials.

8.17 Further reading.

9 Exploring and modelling longitudinal quality of life data.

Summary.

9.1 Introduction.

9.2 Summarizing, tabulating and graphically displaying repeated QoL assessments.

9.3 Time-by-time analysis.

9.4 Response feature analysis – the use of summary measures.

9.5 Modelling of longitudinal data.

9.6 Conclusions.

10 Advanced methods for analysing quality of life outcomes.

Summary.

10.1 Introduction.

10.2 Bootstrap methods.

10.3 Bootstrap methods for confidence interval estimation.

10.4 Ordinal regression.

10.5 Comparing two independent groups: Ordinal quality of life measures (with less than 7 categories).

10.6 Proportional odds or cumulative logit model.

10.7 Continuation ratio model.

10.8 Stereotype logistic model.

10.9 Conclusions and further reading.

11 Economic evaluations.

Summary.

11.1 Introduction.

11.2 Economic evaluations.

11.3 Utilities and QALYs.

11.4 Economic evaluations alongside a controlled trial.

11.5 Cost-effectiveness analysis.

11.6 Cost–effectiveness ratios.

11.7 Cost–utility analysis and cost–utility ratios.

11.8 Incremental cost per QALY.

11.9 The problem of negative (and positive) incremental cost–effectiveness ratios.

11.10 Cost-effectiveness acceptability curves.

11.11 Further reading.

12 Meta-analysis.

Summary.

12.1 Introduction.

12.2 Planning a meta-analysis.

12.3 Statistical methods in meta-analysis.

12.4 Presentation of results.

12.5 Conclusion.

12.6 Further reading.

13 Practical issues.

Summary.

13.1 Missing data.

13.2 Multiplicity, multi-dimensionality and multiple quality of life outcomes.

13.3 Guidelines for reporting quality of life studies.

Solutions to exercises.

Appendix A: Examples of questionnaires.

Appendix B: Statistical tables.

References.

Index.