Design and Analysis of Cluster Randomization Trials in Health Research Allan Donner, Ph.D., Professor and Chair Department of Epidemiology & Biostatistics.

Slides:



Advertisements
Similar presentations
COMPUTER INTENSIVE AND RE-RANDOMIZATION TESTS IN CLINICAL TRIALS Thomas Hammerstrom, Ph.D. USFDA, Division of Biometrics The opinions expressed are those.
Advertisements

Randomized Complete Block and Repeated Measures (Each Subject Receives Each Treatment) Designs KNNL – Chapters 21,
ADVANCED STATISTICS FOR MEDICAL STUDIES Mwarumba Mwavita, Ph.D. School of Educational Studies Research Evaluation Measurement and Statistics (REMS) Oklahoma.
Departments of Medicine and Biostatistics
Chance, bias and confounding
ODAC May 3, Subgroup Analyses in Clinical Trials Stephen L George, PhD Department of Biostatistics and Bioinformatics Duke University Medical Center.
Journal Club Alcohol, Other Drugs, and Health: Current Evidence May–June 2013.
EPIDEMIOLOGY AND BIOSTATISTICS DEPT Esimating Population Value with Hypothesis Testing.
Journal Club Alcohol and Health: Current Evidence May–June 2005.
Common Problems in Writing Statistical Plan of Clinical Trial Protocol Liying XU CCTER CUHK.
Clustered or Multilevel Data
Meta-analysis & psychotherapy outcome research
BS704 Class 7 Hypothesis Testing Procedures
Inferences About Process Quality
Today Concepts underlying inferential statistics
Sample Size Determination
Correlation and Regression Analysis
Chapter 14 Inferential Data Analysis
Richard M. Jacobs, OSA, Ph.D.
Sample Size Determination Ziad Taib March 7, 2014.
Chapter 12 Inferential Statistics Gay, Mills, and Airasian
Chapter 8 Experimental Research
Analysis of Variance. ANOVA Probably the most popular analysis in psychology Why? Ease of implementation Allows for analysis of several groups at once.
Psy B07 Chapter 1Slide 1 ANALYSIS OF VARIANCE. Psy B07 Chapter 1Slide 2 t-test refresher  In chapter 7 we talked about analyses that could be conducted.
Chapter 4 Hypothesis Testing, Power, and Control: A Review of the Basics.
Intervention Studies Principles of Epidemiology Lecture 10 Dona Schneider, PhD, MPH, FACE.
Essentials of survival analysis How to practice evidence based oncology European School of Oncology July 2004 Antwerp, Belgium Dr. Iztok Hozo Professor.
Epidemiology The Basics Only… Adapted with permission from a class presentation developed by Dr. Charles Lynch – University of Iowa, Iowa City.
Sampling and Nested Data in Practice- Based Research Stephen Zyzanski, PhD Department of Family Medicine Case Western Reserve University School of Medicine.
Comparing Two Population Means
PROBABILITY (6MTCOAE205) Chapter 6 Estimation. Confidence Intervals Contents of this chapter: Confidence Intervals for the Population Mean, μ when Population.
Evaluating a Research Report
L 1 Chapter 12 Correlational Designs EDUC 640 Dr. William M. Bauer.
Educational Research: Competencies for Analysis and Application, 9 th edition. Gay, Mills, & Airasian © 2009 Pearson Education, Inc. All rights reserved.
Tips for Researchers on Completing the Data Analysis Section of the IRB Application Don Allensworth-Davies, MSc Statistical Manager, Data Coordinating.
HSRP 734: Advanced Statistical Methods June 19, 2008.
Intervention Studies - Cluster (Randomized) Trials Intervention at the cluster level - What are clusters? - Why intervene in clusters (rather than in individuals)?
Data Analysis – Statistical Issues Bernd Genser, PhD Instituto de Saúde Coletiva, Universidade Federal da Bahia, Salvador
By: Amani Albraikan.  Pearson r  Spearman rho  Linearity  Range restrictions  Outliers  Beware of spurious correlations….take care in interpretation.
Adaptive randomization
Statistics for clinicians Biostatistics course by Kevin E. Kip, Ph.D., FAHA Professor and Executive Director, Research Center University of South Florida,
EXPERIMENTAL EPIDEMIOLOGY
Application of Class Discovery and Class Prediction Methods to Microarray Data Kellie J. Archer, Ph.D. Assistant Professor Department of Biostatistics.
Data Analysis in Practice- Based Research Stephen Zyzanski, PhD Department of Family Medicine Case Western Reserve University School of Medicine October.
N318b Winter 2002 Nursing Statistics Specific statistical tests Chi-square (  2 ) Lecture 7.
Stats 845 Applied Statistics. This Course will cover: 1.Regression –Non Linear Regression –Multiple Regression 2.Analysis of Variance and Experimental.
DTC Quantitative Methods Bivariate Analysis: t-tests and Analysis of Variance (ANOVA) Thursday 14 th February 2013.
Sample Size Determination
Sampling and Nested Data in Practice-Based Research Stephen Zyzanski, PhD Department of Family Medicine Case Western Reserve University School of Medicine.
1 Lecture 11: Cluster randomized and community trials Clusters, groups, communities Why allocate clusters vs individuals? Randomized vs nonrandomized designs.
Design of Clinical Research Studies ASAP Session by: Robert McCarter, ScD Dir. Biostatistics and Informatics, CNMC
The Mixed Effects Model - Introduction In many situations, one of the factors of interest will have its levels chosen because they are of specific interest.
CASE CONTROL STUDY. Learning Objectives Identify the principles of case control design State the advantages and limitations of case control study Calculate.
Types of Studies. Aim of epidemiological studies To determine distribution of disease To examine determinants of a disease To judge whether a given exposure.
Learning Objectives After this section, you should be able to: The Practice of Statistics, 5 th Edition1 DESCRIBE the shape, center, and spread of the.
HYPOTHESIS TESTING FOR DIFFERENCES BETWEEN MEANS AND BETWEEN PROPORTIONS.
Approaches to quantitative data analysis Lara Traeger, PhD Methods in Supportive Oncology Research.
Educational Research Inferential Statistics Chapter th Chapter 12- 8th Gay and Airasian.
1 Study Design Imre Janszky Faculty of Medicine, ISM NTNU.
Uses of Diagnostic Tests Screen (mammography for breast cancer) Diagnose (electrocardiogram for acute myocardial infarction) Grade (stage of cancer) Monitor.
STA248 week 121 Bootstrap Test for Pairs of Means of a Non-Normal Population – small samples Suppose X 1, …, X n are iid from some distribution independent.
Chapter 11 Experimental Designs PowerPoint presentation developed by: Sarah E. Bledsoe & E. Roberto Orellana.
Methods of Presenting and Interpreting Information Class 9.
Demonstration of different analytic methods to account for clustering in an observational study of emergency department use in primary care Michelle Howard,
Sample Size Determination
How many study subjects are required ? (Estimation of Sample size) By Dr.Shaik Shaffi Ahamed Associate Professor Dept. of Family & Community Medicine.
Biostatistics Case Studies 2016
S1316 analysis details Garnet Anderson Katie Arnold
Common Problems in Writing Statistical Plan of Clinical Trial Protocol
Evidence Based Practice
Presentation transcript:

Design and Analysis of Cluster Randomization Trials in Health Research Allan Donner, Ph.D., Professor and Chair Department of Epidemiology & Biostatistics The University of Western Ontario, London, Ontario, Canada Neil Klar, Ph.D., Senior Biostatistician Division of Preventive Oncology Cancer Care Ontario, Toronto, Ontario, Canada

Dr. Allan Donner

Dr. Neil Klar

Learning Objectives To distinguish experimental trials based on the unit of randomization (e.g. individual, family, community). To appreciate the consequences of cluster randomization on sample size estimation and data analysis. To identify key features of a cluster randomization trial which need to be included in reports.

What Are Cluster Randomization Trials? Cluster randomization trials are experiments in which clusters of individuals rather than independent individuals are randomly allocated to intervention groups.

Example 1: Study Purpose: To evaluate the effectiveness of Vitamin A supplements on childhood mortality. 450 villages in Indonesia were randomly assigned to either participate in a Vitamin A supplementation scheme, or serve as a control. One year mortality rates were compared in the two groups. Sommer et al. (Lancet, 1986)

Example 2: Study Purpose: To promote smoking cessation using community resources. 11 paired communities were selected and one member of each pair was randomly assigned to the intervention group. 5-year smoking cessation rates were compared in the two groups. Communities were matched on demographic characteristics (e.g. size, population density) and geographical proximity. COMMIT Research Group (Am J Public Health, 1995)

Example 3: Study Purpose: To evaluate the effectiveness of treated nasal tissues versus standard tissues. 90 families were selected and randomized to one of the two intervention groups separately in each of three family size strata (2, 3, or 4 members per family). 24-week incidence of respiratory illness were compared in the two groups. Farr et al. (Am. J. Epid., 1988)

Reasons for Adopting Cluster Randomization Administrative convenience To obtain cooperation of investigators Ethical considerations To enhance subject compliance To avoid treatment group contamination Intervention is naturally applied at the cluster level

Unit of Randomization vs. Unit of Analysis A key property of cluster randomization trials is that inferences are frequently intended to apply at the individual level while randomization is at the cluster or group level. Thus the unit of randomization may be different from the unit of analysis. In this case, the lack of independence among individuals in the same cluster, i.e. between- cluster variation, creates special methologic challenges in both design and analysis.

Implications of Between-Cluster Variation Presence of between-cluster variation implies: (i) Reduction in effective sample size. Extent depends on degree of within-cluster correlation and on average cluster size. (ii) Standard approaches for sample size estimation and statistical analysis do not apply. Application of standard sample size approaches leads to an underpowered study. Application of standard statistical methods generally tends to bias p-values downwards, i.e. could lead to spurious statistical significance.

Possible Reasons for Between- Cluster Variation 1. Subjects frequently select the clusters to which they belong e.g., Patient characteristics could be related to age or sex differences among physicians 2. Important covariates at the cluster level affect all individuals within the cluster in the same manner e.g. Differences in temperature between nurseries may be related to infection rates 3. Individuals within clusters frequently interact and, as a result, may respond similarly e.g. Education strategies or therapies provided in a group setting 4. Tendency of infectious diseases to spread more rapidly within than among families or communities.

Quantifying the Effect of Clustering Consider a trial in which k clusters of size m are randomly assigned to each of an experimental and control group. Also assume the response variable Y is normally distributed with common variance  2 Aim is to test H 0 :  1 =  2. Then appropriate estimates of  1 and  2 are given by Y 1, Y 2, the usual sample means. Also: V(Y i ) = (  2 /km) [1 + (m - 1)  ], i =1,2 where  is the coefficient of intracluster correlation. Then IF = 1 + (m- 1)  is the “variance inflation factor” or “design effect” associated with cluster randomization.

Variance Component Interpretation of  The overall response variance  2 may be expressed as the sum of two components, i.e.,  2 =  2 A +  2 W, where  2 A = between-cluster component of variance  2 W = within-cluster component of variance then  =  2 A / (  2 A +  2 W )

Sample Size Requirements for Completely Randomized Designs Comparison of Means: Suppose k clusters of size m are to be assigned to each of two intervention groups. Then the number of subjects required per intervention group to test H 0 :  1 =  2 is given by n = {(Z  /2 + Z  ) 2 (2  2 ) [1 + (m – 1)  ]} / (  1 -  2 ) 2 where  2 =  2 A +  2 W Equivalently, the number of required clusters is given by k = n/m.

Example Hsieh (1988) reported on the results of a pilot study for a planned 5-year trial examining cardiovascular risk factors, obtaining cholesterol levels from 754 individuals in 4 worksites. Estimated variance components were S 2 W = 2209, S 2 A = 93.  value of  assessed as  = 93 / ( ) = 0.04 Assuming = 70 subjects/worksite, IF = 1 + (70 - 1) 0.04 = 3.76

 To obtain 80% power at  =.05 (2 sided) for detecting a mean difference of 20 mg/dl between intervention groups, the number of required worksites per group is given by k ={( ) 2 2(2302) (3.76)} / 70 (20) 2 = 4.8  5 To adjust for the use of normal distribution critical values, and possible loss of follow-up, might enroll 7 clusters per group.

Impact on Power of Increasing the Number of Clusters vs. Increasing Cluster Size: Let d = mean difference between intervention groups then, Var (d) = (2  2 / km) [ 1 + ( m – 1)  ] As the number of clusters k  , Var(d)  0 but, as the cluster size size m  , Var (d)  (2  2  ) / k = 2  2 A /k Trial randomizing between 30 and 50 individuals will tend to have almost the same statistical power as trials randomizing the same number of much larger units. But clusters of larger size are often recruited for very practical reasons (to reduce contamination, to avoid logistic or ethical problems, etc.).

Factors Influencing Loss of Precision 1.Interventions often applied on a group basis with little or no attention given to individual study participants. 2.Some studies permit the immigration of new subjects after baseline. 3.Entire clusters, rather than just individuals, may be lost to follow-up. 4.Over-optimistic expectations regarding effect size.

Strategies for Improving Precision in Cluster Randomization Trials 1. Establish cluster-level eligibility criteria so as to reduce between-cluster variability e.g., geographical restrictions. 2.Consider increasing the number of clusters randomized, even if only in the control group. 3.Consider matching or stratifying in the design by baseline variable having prognostic importance. 4.Obtain baseline measurements on other potentially important prognostic variables. 5.Take repeated assessments over time from the same clusters or from different clusters of subjects. 6.Develop a detailed protocol for ensuring compliance and minimizing loss to follow-up.

The Importance of Cluster Level Replication Some investigators have designed community intervention trials in which exactly one cluster has been assigned to each intervention group. Such trials invariably result in interpretational difficulties caused by the total confounding of two sources of variation: –the variation in response due to the effect of intervention, and –the natural variation that exists between the two communities (clusters) even in the absence of an intervention effect. Analysis is only possible under the untenable assumption that there is no clustering of individuals responses within communities. More attention to the effects of clustering when determining sample size might help to eliminate designs which lack replication.

Analysis of Binary Outcomes Objective: To assess the effects of interventions on individuals when clusters are the sampling unit. Statistical Issue: Responses on individuals within the same cluster tend to be positively correlated, violating the assumption of independence required for the application of standard statistical methods.

Example: Data obtained from a study evaluating the effect of school-based interventions in reducing adolescent tobacco use. 12 school units were randomly assigned to each of four conditions, including three intervention conditions and a control condition (existing curriculum). We compare here the effect of the SFG (Smoke Free Generation) intervention to the existing curriculum (EC) with respect to reducing the proportion of children who report using smokeless tobacco after four years of follow-up.

Data Overall rates of tobacco use Control: 91/1479 =.062 Experimental:58/1341 =.043

Procedures Reviewed 1. Standard chi-squared test 2. Two sample t-test on school-specific event rates 3. Direct adjustment of standard chi- square test 4. Generalized estimating equations approach

Hypothesis to be tested:

Two-sample T-test Comparing Average Values of the Event Rates Pooled variance = ( ) / 2= t 22 = ( ) / .00095(1/12 + 1/12) = 1.66 (p =.11)

Adjusted Chi-square Test An adjustment which depends on computing clustering correction factors for each group, is given by: C 1 = {  m 1j [1 + (m 1j - 1)  ]}/  m 1j, C 2 = {  m 2j [1 + (m 2j - 1)  ]}/  m 2j, where m 1j, m 2j are the cluster sizes within groups 1 and 2, respectively, and  is an estimate of within-cluster correlation.

For Data in the Example:  =.011, C 1 = 2.599,C 2 = Then the adjusted one degree of freedom chi-square statistic is given by:  2 A = {M 1 (P 1 – P) 2 / [C 1 P (1 – P)]} + {M 2 (P 2 - P) 2 / [C 2 P (1 - P)]} = {1479 ( ) 2 / [2.599 (.053) ( )]} + {1341 ( ) 2 / [2.536 (.053) ( )]} = 1.83 (p =.18) Comments: 1. Reduces to standard Pearson chi-square test when  = 0 2. Imposes no distributional assumptions on the responses within a cluster. 3. Assumes the C i, i = 1,2 are not significantly different, i.e. estimate the same population design effect.

Generalized Estimating Equations Approach The generalized estimating equations (GEE) approach, developed by Liang and Zeger (1986), can be used to construct an extension of standard logistic regression which adjusts for the effect of clustering, and does not require parametric assumptions. Consider the logistic-regression model given by log [P / (1 - P)] =  0 +  1  where  = 1 if experimental and  = 0 if control The odds ratio for the effect of intervention is given by exp (  1 )

Result: The resulting robust one degree of freedom chi-square statistic, constructed using a working exchangeable correlation matrix is given by X 2 LZ = 2.62 (  = 0.11). Comments: 1) The GEE extensions of logistic regression were fit using the statistical package SAS. These procedures are also available in several other statistical packages (e.g., STATA, SUDAAN). 2) Robust statistical inference are valid so long as there are large numbers of clusters even if the working correlation is not correctly specified. 3) Can be extended to model dependence on individual level covariates.

Summary of Results

Reporting Cluster Randomization Trials: Reporting of study design: Justify the use of cluster randomization. Provide a clear definition of the unit of randomization. Explain how the chosen sample size or statistical power calculations accounts for between-cluster variation.

Reporting of study results: Provide the number of clusters randomized, the average cluster size and the number of subjects selected for study from each cluster. Provide the values of the intracluster correlation coefficient as calculated for the primary outcome variables. Explain how the reported statistical analyses account for between-cluster variations.

References & Links References: 1. Donner A, Klar N. Design and Analysis of Cluster Randomization Trials in Health Research. Arnold, London Statistics notes: Sample size in cluster randomisation Sally M Kerry and J Martin Bland BMJ 1998; 316: 549.

3. Cluster randomised trials: time for improvement Marion K Campbell and Jeremy M Grimshaw BMJ 1998; 317: Ethical issues in the design and conduct of cluster randomised controlled trials Sarah J L Edwards, David A Braunholtz, Richard J Lilford, and Andrew J Stevens BMJ 1999; 318:

Links: The last three articles are available at Arnold Publishers