Atjaunināt sīkdatņu piekrišanu

How to Design, Analyse and Report Cluster Randomised Trials in Medicine and Health Related Research [Hardback]

(Medical Statistics Group, School of Health and Related Research, University of Sheffield, UK), (Medical Statistics Group, School of Health and Related Research, University of Sheffield, UK)
  • Formāts: Hardback, 272 pages, height x width x depth: 252x178x18 mm, weight: 572 g
  • Sērija : Statistics in Practice
  • Izdošanas datums: 16-May-2014
  • Izdevniecība: John Wiley & Sons Inc
  • ISBN-10: 1119992028
  • ISBN-13: 9781119992028
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 89,76 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
  • Bibliotēkām
How to Design, Analyse and Report Cluster Randomised Trials in Medicine and Health Related ResearchPalielināt
  • Formāts: Hardback, 272 pages, height x width x depth: 252x178x18 mm, weight: 572 g
  • Sērija : Statistics in Practice
  • Izdošanas datums: 16-May-2014
  • Izdevniecība: John Wiley & Sons Inc
  • ISBN-10: 1119992028
  • ISBN-13: 9781119992028
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9781119992028.html
Keywords:
"A much-needed guide to the design and analysis of cluster randomized trials, How to Design, Analyse and Report Cluster Randomised Trials in Medicine and Health Related Research delivers practical guidance on the design and analysis of cluster randomisedtrials (cRCTs) in healthcare research. Detailing how to use Stata and SPSS and R for statistical analysis, each analysis technique is carefully explained with mathematics kept to a minimum. Written in a clear, accessible style by experienced statisticians, the text provides a practical approach for applied statisticians and biomedical researchers"--Provided by publisher.

Campbell and Walters present a textbook on cluster randomized trials in medicine and health service research that covers a wide range of trials using real data, and shows how to do all the analyses in two commercial packages--SPSS and Stata--and the free open-source package R. The many exercises with answers are from courses they have taught. For readers who will not design and run cluster trials but will need to interpret them, there are special sections and exercises on reading and interpreting cluster trials. Annotation ©2014 Ringgold, Inc., Portland, OR (protoview.com)

A complete guide to understanding cluster randomised trials

Written by two researchers with extensive experience in the field, this book presents a complete guide to the design, analysis and reporting of cluster randomised trials. It spans a wide range of applications: trials in developing countries, trials in primary care, trials in the health services. A key feature is the use of R code and code from other popular packages to plan and analyse cluster trials, using data from actual trials. The book contains clear technical descriptions of the models used, and considers in detail the ethics involved in such trials and the problems in planning them. For readers and students who do not intend to run a trial but wish to be a critical reader of the literature, there are sections on the CONSORT statement, and exercises in reading published trials.

  • Written in a clear, accessible style
  • Features real examples taken from the authors’ extensive practitioner experience of designing and analysing clinical trials
  • Demonstrates the use of R, Stata and SPSS for statistical analysis
  • Includes computer code so the reader can replicate all the analyses
  • Discusses neglected areas such as ethics and practical issues in running cluster randomised trials

How to Design, Analyse and Report Cluster Randomised Trials in Medicine and Health Related Research provides an excellent reference tool and can be read with profit by statisticians, health services researchers, systematic reviewers and critical readers of cluster randomised trials.

Recenzijas

Overall, the reviewers are enthusiastic about the book. The authors have covered all important areas of cRCTs, using a practical and pragmatic approach to the topic. The code is helpful for the practical implementation of the examples. The material is simple to understand, which will appeal to applied researchers, not only to biostatisticians. As such, we clearly recommend this book to all researchers interested in cRCTs. For biostatisticians involved in cRCTs and investigators of cRCTs, it is a must-have on the bookshelf.  (Biometrical Journal, 1 May 2015)

Preface xiii
Acronyms and abbreviations xv
1 Introduction
1(26)
1.1 Randomised controlled trials
1(2)
1.1.1 A-Allocation at random
1(1)
1.1.2 B-Blindness
2(1)
1.1.3 C-Control
2(1)
1.2 Complex interventions
3(1)
1.3 History of cluster randomised trials
4(1)
1.4 Cohort and field trials
4(1)
1.5 The field/community trial
5(3)
1.5.1 The REACT trial
5(1)
1.5.2 The Informed Choice leaflets trial
6(1)
1.5.3 The Mwanza trial
7(1)
1.5.4 The paramedics practitioner trial
7(1)
1.6 The cohort trial
8(3)
1.6.1 The PoNDER trial
8(1)
1.6.2 The DESMOND trial
9(1)
1.6.3 The Diabetes Care from Diagnosis trial
10(1)
1.6.4 The REPOSE trial
11(1)
1.6.5 Other examples of cohort cluster trials
11(1)
1.7 Field versus cohort designs
11(1)
1.8 Reasons for cluster trials
12(2)
1.9 Between-and within-cluster variation
14(1)
1.10 Random-effects models for continuous outcomes
15(3)
1.10.1 The model
15(1)
1.10.2 The intracluster correlation coefficient
16(1)
1.10.3 Estimating the intracluster correlation (ICC) coefficient
16(1)
1.10.4 Link between the Pearson correlation coefficient and the intraclass correlation coefficient
17(1)
1.11 Random-effects models for binary outcomes
18(2)
1.11.1 The model
18(1)
1.11.2 The ICC for binary data
19(1)
1.11.3 The coefficient of variation
19(1)
1.11.4 Relationship between cvc and ρ for binary data
20(1)
1.12 The design effect
20(1)
1.13 Commonly asked questions
21(1)
1.14 Websources
21(6)
Exercise
22(1)
Appendix 1.A
22(5)
2 Design issues
27(23)
2.1 Introduction
27(1)
2.2 Issues for a simple intervention
28(2)
2.2.1 Phases of a trial
28(1)
2.2.2 `Pragmatic' and `explanatory' trials
29(1)
2.2.3 Intention-to-treat and per-protocol analyses
29(1)
2.2.4 Non-inferiority and equivalence trials
30(1)
2.3 Complex interventions
30(4)
2.3.1 Design of complex interventions
30(2)
2.3.2 Phase I modelling/qualitative designs
32(1)
2.3.3 Pilot or feasibility studies
33(1)
2.3.4 Example of pilot/feasibility studies in cluster trials
33(1)
2.4 Recruitment bias
34(1)
2.5 Matched-pair trials
34(3)
2.5.1 Design of matched-pair studies
34(2)
2.5.2 Limitations of matched-pairs designs
36(1)
2.5.3 Example of matched-pair design: The Family Heart Study
36(1)
2.6 Other types of designs
37(4)
2.6.1 Cluster factorial designs
37(1)
2.6.2 Example cluster factorial trial
38(1)
2.6.3 Cluster crossover trials
38(1)
2.6.4 Example of a cluster crossover trial
39(1)
2.6.5 Stepped wedge
39(1)
2.6.6 Pseudorandomised trials
40(1)
2.7 Other design issues
41(1)
2.8 Strategies for improving precision
41(1)
2.9 Randomisation
42(8)
2.9.1 Reasons for randomisation
42(1)
2.9.2 Simple randomisation
43(1)
2.9.3 Stratified randomisation
43(1)
2.9.4 Restricted randomisation
43(1)
2.9.5 Minimisation
44(1)
Exercise
45(3)
Appendix 2.A
48(2)
3 Sample size: How many subjects/clusters do I need for my cluster randomised controlled trial?
50(33)
3.1 Introduction
51(2)
3.1.1 Justification of the requirement for a sample size
51(1)
3.1.2 Significance tests, P-values and power
51(2)
3.1.3 Sample size and cluster trials
53(1)
3.2 Sample size for continuous data -- comparing two means
53(3)
3.2.1 Basic formulae
53(1)
3.2.2 The design effect (DE) in cluster RCTs
54(1)
3.2.3 Example from general practice
55(1)
3.3 Sample size for binary data -- comparing two proportions
56(3)
3.3.1 Sample size formula
56(1)
3.3.2 Example calculations
57(1)
3.3.3 Example: The Informed Choice leaflets study
58(1)
3.4 Sample size for ordered categorical (ordinal) data
59(3)
3.4.1 Sample size formula
59(1)
3.4.2 Example calculations
60(2)
3.5 Sample size for rates
62(1)
3.5.1 Formulae
62(1)
3.5.2 Example comparing rates
63(1)
3.6 Sample size for survival
63(1)
3.6.1 Formulae
63(1)
3.6.2 Example of sample size for survival
64(1)
3.7 Equivalence/non-inferiority studies
64(2)
3.7.1 Equivalence/non-inferiority versus superiority
64(1)
3.7.2 Continuous data -- comparing the equivalence of two means
65(1)
3.7.3 Example calculations for continuous data
65(1)
3.7.4 Binary data -- comparing the equivalence of two proportions
66(1)
3.8 Unknown standard deviation and effect size
66(1)
3.9 Practical problems
67(1)
3.9.1 Tips on getting the SD
67(1)
3.9.2 Non-response
67(1)
3.9.3 Unequal groups
67(1)
3.10 Number of clusters fixed
68(1)
3.10.1 Number of clusters and number of subjects per cluster
68(1)
3.10.2 Example with number of clusters fixed
69(1)
3.10.3 Increasing the number of clusters or number of patients per cluster?
69(1)
3.11 Values of the ICC
69(1)
3.12 Allowing for imprecision in the ICC
70(1)
3.13 Allowing for varying cluster sizes
70(1)
3.13.1 Formulae
70(1)
3.13.2 Example of effect of variable cluster size
71(1)
3.14 Sample size re-estimation
71(1)
3.14.1 Adjusting for covariates
72(1)
3.15 Matched-pair studies
72(1)
3.15.1 Sample sizes for matched designs
72(1)
3.15.2 Example of a sample size calculation for a matched study
72(1)
3.16 Multiple outcomes/endpoints
73(1)
3.17 Three or more groups
74(1)
3.18 Crossover trials
74(1)
3.18.1 Formulae
75(1)
3.18.2 Example of a sample size formula in a crossover trial
75(1)
3.19 Post hoc sample size calculations
75(1)
3.20 Conclusion: Usefulness of sample size calculations
76(1)
3.21 Commonly asked questions
76(7)
Exercise
77(1)
Appendix 3.A
78(5)
4 Simple analysis of cRCT outcomes using aggregate cluster-level summaries
83(19)
4.1 Introduction
83(1)
4.1.1 Methods of analysing cluster randomised trials
83(1)
4.1.2 Choosing the statistical method
84(1)
4.2 Aggregate cluster-level analysis -- carried out at the cluster level, using aggregate summary data
84(2)
4.3 Statistical methods for continuous outcomes
86(5)
4.3.1 Two independent-samples t-test
86(2)
4.3.2 Example
88(3)
4.4 Mann--Whitney U test
91(3)
4.5 Statistical methods for binary outcomes
94(1)
4.6 Analysis of a matched design
95(3)
4.7 Discussion
98(1)
4.8 Commonly asked question
98(4)
Exercise
99(1)
Appendix 4.A
99(3)
5 Regression methods of analysis for continuous outcomes using individual person-level data
102(24)
5.1 Introduction
102(2)
5.2 Incorrect models
104(1)
5.2.1 The simple (independence) model
104(1)
5.2.2 Fixed effects
104(1)
5.3 Linear regression with robust standard errors
105(3)
5.3.1 Robust standard errors
105(2)
5.3.2 Example of use of robust standard errors
107(1)
5.3.3 Cluster-specific versus population-averaged models
107(1)
5.4 Random-effects general linear models in a cohort study
108(4)
5.4.1 General models
108(1)
5.4.2 Fitting a random-effects model
109(1)
5.4.3 Example of a random-effects model from the PoNDER study
110(1)
5.4.4 Checking the assumptions
110(2)
5.5 Marginal general linear model with coefficients estimated by generalised estimating equations (GEE)
112(2)
5.5.1 Generalised estimating equations
112(1)
5.5.2 Example of a marginal model from the PoNDER study
113(1)
5.6 Summary of methods
114(1)
5.7 Adjusting for individual-level covariates in cohort studies
115(3)
5.8 Adjusting for cluster-level covariates in cohort studies
118(1)
5.9 Models for cross-sectional designs
119(1)
5.10 Discussion of model fitting
120(6)
Exercise
122(1)
Appendix 5.A
123(3)
6 Regression methods of analysis for binary, count and time-to-event outcomes for a cluster randomised controlled trial
126(17)
6.1 Introduction
126(1)
6.2 Difference between a cluster-specific model and a population-averaged or marginal model for binary data
127(2)
6.3 Analysis of binary data using logistic regression
129(1)
6.4 Review of past simulations to determine efficiency of different methods for binary data
130(1)
6.5 Analysis using summary measures
131(1)
6.6 Analysis using logistic regression (ignoring clustering)
132(2)
6.7 Random-effects logistic regression
134(1)
6.8 Marginal models using generalised estimating equations
135(1)
6.9 Analysis of count data
135(2)
6.10 Survival analysis with cluster trials
137(2)
6.11 Missing data
139(1)
6.12 Discussion
139(4)
Exercise
139(1)
Appendix 6.A
140(3)
7 The protocol
143(16)
7.1 Introduction
143(1)
7.2 Abstract
144(3)
7.3 Protocol background
147(1)
7.4 Research objectives
147(1)
7.5 Outcome measures
147(1)
7.6 Design
147(1)
7.7 Intervention details
148(1)
7.8 Eligibility
148(1)
7.9 Randomisation
149(1)
7.10 Assessment and data collection
149(1)
7.11 Statistical considerations
150(3)
7.11.1 Sample size
150(1)
7.11.2 Statistical analysis
151(1)
7.11.3 Interim analyses
152(1)
7.12 Ethics
153(2)
7.12.1 Declaration of Helsinki
153(1)
7.12.2 Informed consent
154(1)
7.13 Organisation
155(1)
7.13.1 The team
155(1)
7.13.2 Trial forms
155(1)
7.13.3 Data management
155(1)
7.13.4 Protocol amendments
156(1)
7.14 Further reading
156(3)
Exercise
156(3)
8 Reporting of cRCTs
159(19)
8.1 Introduction: Extended CONSORT guidelines for reporting and presenting the results from cRCTs
159(1)
8.2 Patient flow diagram
160(1)
8.3 Comparison of entry characteristics
160(7)
8.4 Incomplete data
167(4)
8.5 Reporting the main outcome
171(3)
8.6 Subgroup analysis and analysis of secondary outcomes/endpoints
174(1)
8.7 Estimates of between-cluster variability
175(1)
8.7.1 Example of reporting the ICC: The PoNDER cRCT
175(1)
8.8 Further reading
175(3)
Exercise
176(2)
9 Practical issues
178(17)
9.1 Preventing bias in cluster randomised controlled trials
178(3)
9.1.1 Problems with identifying and recruiting patients to cluster trials
178(1)
9.1.2 Preventing biased recruitment
179(2)
9.2 Developing complex interventions
181(1)
9.3 Choice of method of analysis
182(3)
9.4 Missing data
185(3)
9.5 Example sensitivity analysis: Imputation of missing 6-month EPDS data for at-risk women from the PoNDER cRCT
188(4)
9.6 Multiplicity of outcomes
192(3)
9.6.1 Limiting the number of confirmatory tests
192(1)
9.6.2 Summary measures and statistics
193(1)
9.6.3 Global tests and multiple comparison procedures
193(1)
9.6.4 Which multiple comparison procedure to use?
194(1)
10 Computing software
195(48)
10.1 R
195(4)
10.1.1 History
195(1)
10.1.2 Installing R
196(1)
10.1.3 Simple use of R
197(1)
10.1.4 An example of an R program
198(1)
10.2 Stata (version 12)
199(13)
10.2.1 Introduction to Stata
199(2)
10.2.2 Aggregate cluster-level analysis -- carried out at the cluster level, using aggregate summary data
201(1)
10.2.3 Random-effects models -- continuous outcomes
202(3)
10.2.4 Random-effects models -- binary outcomes
205(1)
10.2.5 Random-effects models -- count outcomes
206(2)
10.2.6 Marginal models -- continuous outcomes
208(1)
10.2.7 Marginal models -- binary outcomes
209(1)
10.2.8 Marginal models -- count outcomes
210(2)
10.3 SPSS (version 19)
212(20)
10.3.1 Introduction to SPSS
212(1)
10.3.2 Comparing cluster means using aggregate cluster-level analysis --carried out at the cluster level, using aggregate summary data
213(2)
10.3.3 Marginal models
215(12)
10.3.4 Random-effects models
227(5)
10.4 Conclusion and further reading
232(11)
References
234(9)
Index 243
MICHAEL J. CAMPBELL and STEPHEN J. WALTERS, Medical Statistics Group, School of Health and Related Research, University of Sheffield, UK