Muutke küpsiste eelistusi

E-raamat: Practical Guide to Cluster Randomised Trials in Health Services Research

(University of London, UK), (Queen Mary, University of London, UK)
  • Formaat: PDF+DRM
  • Sari: Statistics in Practice
  • Ilmumisaeg: 03-Jan-2012
  • Kirjastus: John Wiley & Sons Inc
  • Keel: eng
  • ISBN-13: 9781119966258
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 78,98 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
  • Raamatukogudele
Practical Guide to Cluster Randomised Trials in Health Services ResearchSuurem pilt
  • Formaat: PDF+DRM
  • Sari: Statistics in Practice
  • Ilmumisaeg: 03-Jan-2012
  • Kirjastus: John Wiley & Sons Inc
  • Keel: eng
  • ISBN-13: 9781119966258
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

"There is relatively little literature on cluster randomized trials, with only two previous books on the subject, both now quite old, and neither were focused on the practical aspects of the trials. This book provides that much needed practical guide to the design, execution and analysis of cluster randomized trials in health services research. It also provides an overview of the topic's numerous recent developments since the 2000 publication of the last book in this area.The opening chapter defines and introduces cluster randomized trials, before going on to present an overview of the subject's history and recent developments. The following chapters focus on all the major issues presented in the order in which investigators think about issues when they are designing a trial. The chapters focus on: trial quality, reporting, how to design an intervention, how to ensure the validity of results, how to choose both the design and the analysis of the trial, sample size calculations, choosing an intra-cluster correlation coefficient, the uses of piloting, how to conduct a cost-effectiveness analysis, and how these trials should be synthesized.The book also contains numerous tables, graphs and diagrams and a substantial number of recent trials"--Provided by publisher.

"This book aims to provide that much needed practical guide to the design, execution and analysis of cluster randomized trials in health services research"--Provided by publisher.

Cluster randomisedtrials are trials in which groups (or clusters) of individuals are randomly allocated to different forms of treatment. In health care, these trials often compare different ways of managing a disease or promoting healthy living, in contrast to conventional randomised trials which randomise individuals to different treatments, classically comparing new drugs with a placebo. They are increasingly common in health services research. This book addresses the statistical, practical, and ethical issues arising from allocating groups of individuals, or clusters, to different interventions.

Key features:

  • Guides readers through the stages of conducting a trial, from recruitment to reporting.
  • Presents a wide range of examples with particular emphasis on trials in health services research and primary care, with both principles and techniques explained.
  • Topics are specifically presented in the order in which investigators think about issues when they are designing a trial.
  • Combines information on the latest developments in the field together with a practical guide to the design and implementation of cluster randomised trials.
  • Explains principles and techniques through numerous examples including many from the authors own experience.
  • Includes a wide range of references for those who wish to read further.

This book is intended as a practical guide, written for researchers from the health professions including doctors, psychologists, and allied health professionals, as well as statisticians involved in the design, execution, analysis and reporting of cluster randomised trials. Those with a more general interest will find the plentiful examples illuminating.

Arvustused

There are several unique strengths to this book. In particular the authors are very experienced statisticians having worked for many years in the design and analysis of cluster randomized trials and have written excellent methodological articles many of which are cited in their book.  (Journal of Biopharmaceutical Statistics, 2012)

 

Preface xiii
Notation xv
Table of cases: Trials used as examples in more than one chapter in the book
xviii
1 Introduction
1(21)
1.1 Introduction to randomised trials
2(1)
1.2 Explanatory or pragmatic trials
2(1)
1.3 How does a cluster randomised trial differ from other trials?
3(6)
1.3.1 Recruitment, randomisation and consent
4(3)
1.3.2 Definition of cluster size
7(1)
1.3.3 Analysis and sample size
7(1)
1.3.4 Interventions used in cluster randomised trials
8(1)
1.4 Between-cluster variability
9(1)
1.4.1 Factors that contribute to between-cluster variability
9(1)
1.4.1.1 Geographical reasons
9(1)
1.4.1.2 Individuals choose the cluster to belong to
9(1)
1.4.1.3 Healthcare provided to the cluster
9(1)
1.4.2 Measuring between-cluster variability
9(1)
1.5 Why carry out cluster randomised trials?
10(3)
1.5.1 The intervention necessarily acts at the cluster level
10(1)
1.5.2 Practical and/or ethical difficulties in randomising at individual level
10(1)
1.5.3 Contamination at health professional level
11(1)
1.5.4 Contamination between members of a cluster
12(1)
1.5.5 Cost or administrative convenience
12(1)
1.5.6 Ensuring intervention is fully implemented
12(1)
1.5.7 Access to routine data
13(1)
1.6 Quality of evidence from cluster randomised trials
13(3)
1.6.1 External validity
13(1)
1.6.2 Internal validity
14(1)
1.6.3 Balancing internal validity, external validity and ethical issues
14(2)
1.7 Historical perspectives
16(2)
1.7.1 Early cluster randomised trials
16(1)
1.7.2 Early cluster randomised trials in health up to 2000
16(1)
1.7.3 Recent methodological developments
17(1)
1.7.3.1 Methods of analysis
17(1)
1.7.3.2 Sample size
17(1)
1.7.3.3 Estimating the intra-cluster correlation coefficient
17(1)
1.7.3.4 Reporting guidelines
17(1)
1.7.3.5 Recruitment and consent
18(1)
1.7.3.6 Complex interventions
18(1)
1.7.3.7 Other topics
18(1)
1.8 Summary
18(4)
References
19(3)
2 Recruitment and ethics
22(22)
2.1 Selecting clusters and participants to enhance external validity
22(2)
2.1.1 Clusters
22(1)
2.1.2 Participants
23(1)
2.2 Ethics of cluster randomised trials
24(11)
2.2.1 Components of consent
25(1)
2.2.2 Classification of interventions and implications for individual participant consent
25(1)
2.2.2.1 Individual-cluster interventions
25(2)
2.2.2.2 Professional-cluster interventions
27(1)
2.2.2.3 External-cluster interventions
27(1)
2.2.2.4 Cluster-cluster interventions
28(1)
2.2.2.5 Multifaceted interventions
29(1)
2.2.3 Cluster guardians
30(2)
2.2.4 Timing of cluster consent
32(1)
2.2.5 Fully informed consent for educational and awareness campaigns
33(1)
2.2.6 Protecting the privacy of individuals
33(1)
2.2.7 Duty of care to control participants
34(1)
2.2.8 Summary of consent issues
35(1)
2.3 Selection and recruitment of participants to enhance internal validity
35(6)
2.3.1 Trials which identify and recruit individual participants before randomisation (scenario 1)
36(1)
2.3.2 Trials where individual participants are not recruited (scenario 2)
37(1)
2.3.3 Trials where participants are recruited after randomisation but blind to allocation status (scenario 3)
38(1)
2.3.4 Trials where recruitment is carried out after randomisation and where the recruiter knows the allocation (also scenario 3)
39(1)
2.3.5 Identification and recruitment bias: Summary
40(1)
2.4 Retention of participants in the trial
41(1)
2.5 Summary
41(3)
References
41(3)
3 Designing interventions
44(16)
3.1 Lack of effectiveness of interventions evaluated in cluster randomised trials
45(1)
3.2 What is a complex intervention?
46(4)
3.3 Phases in the development of a complex intervention
50(1)
3.4 Identifying evidence for potential intervention effect (pre-clinical phase)
50(3)
3.5 Understanding more about intervention components (modelling phase)
53(2)
3.6 Developing the optimum intervention and study design (exploratory trial phase)
55(2)
3.7 What is the intervention?
57(1)
3.8 Summary
58(2)
References
58(2)
4 Pilot and feasibility studies
60(14)
4.1 What is a pilot study?
60(3)
4.1.1 Is there a difference between pilot studies and feasibility studies?
61(1)
4.1.2 Internal and external pilot studies
62(1)
4.2 Reasons for conducting pilot and feasibility studies
63(6)
4.2.1 Piloting randomisation and recruitment
63(3)
4.2.2 Piloting the intervention
66(2)
4.2.3 Acquiring information to help with sample size
68(1)
4.2.4 Refining outcome measures
68(1)
4.3 Designing a pilot or feasibility study
69(2)
4.3.1 Size of pilot study
70(1)
4.3.2 Protocols for pilot studies
71(1)
4.4 Reporting and interpreting pilot studies
71(1)
4.5 Summary
72(2)
References
73(1)
5 Design
74(25)
5.1 Parallel designs with only two arms
75(10)
5.1.1 Introduction
75(1)
5.1.2 Completely randomised designs
75(1)
5.1.3 Choosing factors to balance in designs that are not completely randomised
76(2)
5.1.4 Stratified designs
78(1)
5.1.5 Stratified random sampling within clusters
79(1)
5.1.6 Minimisation
79(3)
5.1.7 Other techniques for balancing factors between trial arms
82(1)
5.1.8 Blocking
82(2)
5.1.9 Matched-pair designs
84(1)
5.1.10 Unequal allocation to intervention arms
85(1)
5.2 Cohort versus cross-sectional designs
85(3)
5.3 Parallel designs with more than two arms
88(4)
5.3.1 Introduction
88(1)
5.3.2 Trials with one more arm than there are active interventions
88(1)
5.3.3 Full factorial designs
89(3)
5.3.4 Randomisation at cluster and individual level
92(1)
5.4 Crossover designs
92(3)
5.5 Further design considerations
95(1)
5.5.1 Pseudo cluster randomisation
95(1)
5.5.2 Stepped wedge designs
95(1)
5.5.3 Equivalence and non-inferiority trials
95(1)
5.5.4 Delayed intervention
96(1)
5.6 Summary
96(3)
References
96(3)
6 Analysis
99(38)
6.1 Data collection and management
99(2)
6.2 Analysis - an introduction
101(3)
6.2.1 Comparing analyses that do and do not take account of clustering
102(2)
6.2.2 The intra-cluster correlation coefficient
104(1)
6.3 Analyses for two-arm, completely randomised, stratified or minimised designs
104(20)
6.3.1 Analyses that do not allow the inclusion of covariates
105(2)
6.3.2 Analysis allowing for the inclusion of covariates at the cluster level only
107(2)
6.3.3 Analyses allowing for the inclusion of covariates at individual and cluster level
109(1)
6.3.3.1 Introduction to different models
109(1)
6.3.3.2 Continuous outcomes - population-averaged and cluster-specific models
110(3)
6.3.3.3 Continuous outcomes - generalised estimating equations
113(1)
6.3.3.4 Continuous outcomes - mixed effects models
114(2)
6.3.3.5 Continuous outcomes - other methods of analysis
116(1)
6.3.3.6 Continuous outcomes - comparison of methods
116(1)
6.3.3.7 Binary outcomes - population-averaged and cluster-specific models
117(2)
6.3.3.8 Binary outcomes - generalised estimating equations
119(1)
6.3.3.9 Binary outcomes - mixed effects models
120(2)
6.3.3.10 Binary outcomes - other methods of analysis
122(1)
6.3.3.11 Binary outcomes - comparison of methods
122(1)
6.3.3.12 Count outcomes
122(2)
6.3.3.13 Time-to-event outcomes
124(1)
6.4 Analyses for other designs
124(5)
6.4.1 Matched designs
124(1)
6.4.2 Parallel trials with more than two arms
125(3)
6.4.3 Crossover, stepped wedge and pseudo cluster randomised designs
128(1)
6.5 Intention to treat and missing values
129(2)
6.6 Analysis planning
131(1)
6.7 Summary
132(5)
References
133(4)
7 Sample size calculations
137(35)
7.1 Factors affecting sample size for cluster randomised designs
138(4)
7.1.1 Measuring between-cluster variation in an outcome variable
138(1)
7.1.2 Definition of cluster size
139(1)
7.1.3 Variability in cluster size
140(1)
7.1.4 Clinically important difference
140(1)
7.1.5 Sample size formulae for individually randomised trials
141(1)
7.2 Calculating sample size using the intra-cluster correlation coefficient
142(3)
7.2.1 Increasing the number of clusters to allow for a clustered design
142(1)
7.2.2 Increasing cluster size to allow for a clustered design
143(2)
7.3 Sample size calculations for rates
145(1)
7.4 Restricted number of clusters
146(3)
7.4.1 Administrative reasons
146(1)
7.4.2 Few clusters are available
147(1)
7.4.3 Cost or other practical difficulties of delivering the intervention
147(1)
7.4.4 Minimum number of clusters required
148(1)
7.5 Trials with a small number of clusters
149(1)
7.5.1 Adjustment to sample size calculations when number of clusters is small
149(1)
7.5.2 Balance between the arms in cluster characteristics
149(1)
7.5.3 Loss of intact clusters
150(1)
7.6 Variability in cluster size
150(4)
7.6.1 Using coefficient of variation in cluster size for estimating sample size
151(1)
7.6.2 Estimating coefficient of variation in cluster size
152(1)
7.6.3 Small clusters arising from incident cases
152(2)
7.6.4 Variable cluster size for rates
154(1)
7.7 Comparison of different measures of between-cluster variability
154(6)
7.7.1 Estimating sample size using between-cluster variance
154(2)
7.7.2 Estimating sample size using between-cluster coefficient of variation in outcome
156(1)
7.7.3 Comparison of measures of between-cluster variability for means
156(1)
7.7.4 Comparison of measures of between-cluster variability for proportions
157(3)
7.8 Matched and stratified designs
160(6)
7.8.1 Matched and stratified designs comparing means
161(1)
7.8.2 Matched and stratified designs comparing proportions
161(1)
7.8.3 Matching correlation
162(1)
7.8.4 Strength of relationship between stratification factors and outcomes
163(1)
7.8.5 Cluster size as a stratification factor in primary care
163(2)
7.8.6 Summary of the effect of stratification on power
165(1)
7.9 Sample size for other designs
166(3)
7.9.1 Unequal numbers in each arm
166(1)
7.9.2 Block randomisation
166(1)
7.9.3 Minimisation
166(1)
7.9.4 Cohort versus cross-sectional studies
166(1)
7.9.5 More than two intervention arms
167(1)
7.9.6 Factorial designs
168(1)
7.9.7 Crossover trials
169(1)
7.10 Summary
169(3)
References
169(3)
8 The intra-cluster correlation coefficient
172(24)
8.1 What is the ICC?
173(2)
8.1.1 Proportion of variance interpretation
173(1)
8.1.2 Pair-wise correlation interpretation
174(1)
8.1.3 Relationship between proportion of variance and pair-wise correlation interpretations
174(1)
8.1.4 Kappa interpretation
174(1)
8.1.5 Interpretation in cluster randomised trials
175(1)
8.2 Sources of ICC estimates
175(4)
8.2.1 ICC estimates from trial reports
175(1)
8.2.2 ICC estimates from lists
176(2)
8.2.3 Patterns in ICCs
178(1)
8.3 Choosing the ICC for use in sample size calculations
179(6)
8.3.1 Single ICC estimate from an existing source
180(1)
8.3.2 Single ICC estimate from pilot study
180(2)
8.3.3 Single ICC estimate based on patterns in ICCs
182(1)
8.3.4 Using more than one ICC estimate from existing sources
182(1)
8.3.5 Baseline or interim sample size calculations
183(1)
8.3.6 Comparing different methods
184(1)
8.3.7 Sensitivity analyses
185(1)
8.4 Calculating ICC values
185(7)
8.4.1 Analysis of variance
186(1)
8.4.2 Pearson product-moment correlation coefficient
187(2)
8.4.3 Mixed effects models
189(2)
8.4.4 Generalised estimating equations
191(1)
8.4.5 Negative ICCs
191(1)
8.5 Uncertainty in ICCs
192(1)
8.6 Summary
193(3)
References
193(3)
9 Other topics
Richard Grieve
196(1)
9.1 Systematic reviews
197(10)
9.1.1 Inclusion criteria
197(1)
9.1.2 Quality
198(2)
9.1.3 Heterogeneity
200(3)
9.1.4 Meta-analyses - incorporating cluster randomised trials using the design effect
203(3)
9.1.5 Other methods of incorporating cluster randomised trials in meta-analyses
206(1)
9.1.6 Incorporating stratified and matched trials into a meta-analysis
206(1)
9.1.7 Reporting systematic reviews
207(1)
9.2 Cost effectiveness analyses
207(5)
9.2.1 Cost effectiveness analyses and cluster randomised trials
208(2)
9.2.2 Appropriate methods for cost effectiveness analyses of cluster randomised trials
210(1)
9.2.2.1 Bivariate multilevel models
210(1)
9.2.2.2 Two-stage bootstrap
210(1)
9.2.2.3 Robust variance methods
211(1)
9.2.3 Current state of knowledge and areas for future research
211(1)
9.3 Process evaluation
212(1)
9.4 Monitoring
213(2)
9.5 Summary
215(3)
References
215(3)
10 Trial reporting
218(49)
10.1 Trial quality and reporting quality
218(9)
10.1.1 Checklists for assessing the quality of cluster randomised trials
219(2)
10.1.2 Consort statement for reporting trials
221(6)
10.1.3 Extension to the Consort statement for cluster randomised trials
227(1)
10.1.4 Other extensions to the Consort statement
227(1)
10.2 Steps to improve trial reporting in the early stages of the trial
227(3)
10.2.1 Trial registration
227(3)
10.2.2 Publication of trial protocol
230(1)
10.3 Reporting randomised trials in journal and conference abstracts
230(2)
10.4 Application of Consort statement to cluster randomised trials
232(30)
10.4.1 Item 1a: Information in title
232(2)
10.4.2 Item 2: Background information
234(3)
10.4.3 Item 3: Trial design
237(2)
10.4.4 Item 4: Description of participants
239(1)
10.4.5 Item 5: Description of interventions
239(2)
10.4.6 Item 6: Outcomes
241(2)
10.4.7 Item 7: Sample size and interim analyses
243(1)
10.4.8 Item 8: Generation of random allocation sequence
244(1)
10.4.9 Item 9: Allocation concealment
245(1)
10.4.10 Item 10: Who generated allocation sequence, enrolled participants and assigned participants to their groups
245(2)
10.4.11 Item 11: Blinding
247(1)
10.4.12 Item 12: Statistical methods
248(1)
10.4.13 Item 13: Participant flow
249(3)
10.4.14 Item 14: Recruitment
252(3)
10.4.15 Item 15: Baseline data
255(2)
10.4.16 Item 16: Numbers analysed
257(1)
10.4.17 Item 17: Outcomes and estimation
257(1)
10.4.18 Item 18: Ancillary analyses
258(1)
10.4.19 Item 19: Adverse events
259(1)
10.4.20 Item 20: Limitations
260(1)
10.4.21 Item 21: Generalisability
261(1)
10.4.22 Item 22: Interpretation
261(1)
10.4.23 Other information
262(1)
10.5 Summary
262(5)
References
263(4)
Index 267
Sandra Eldridge Senior Lecturer, Medical Statistics, Queen Mary, University of London, UK Dr Eldridge is well experienced in designing and analyzing high quality cluster randomized trials, having worked on ten such trials since the mid 1990s. An award-winning speaker on randomized trials, Dr Eldridge has given numerous presentations in many settings and conferences over the last seven years.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97811199662582e.html
Märksõnad: