Developments in cluster randomized trials and <i>Statistics in Medicine</i>

Campbell, Mike; Donner, Allan; Klar, Neil

doi:10.1002/sim.2731

Cited by 232 publications

(198 citation statements)

References 79 publications

Supporting

Mentioning

196

Contrasting

Unclassified

Order By: Relevance

“…We conducted a single-blind, stratified, cluster RCT 8,9 at 4 medical schools to compare 2 interventions with no intervention. Before the study began, randomization was performed by using a random-number generator, and then study arm assignment for each block was disseminated to sites.…”

Section: Methodsmentioning

confidence: 99%

Feedback on Oral Presentations During Pediatric Clerkships: A Randomized Controlled Trial

et al. 2014

View full text Add to dashboard Cite

WHAT'S KNOWN ON THIS SUBJECT: Delivering competent oral case presentations is an important clinical communication skill, yet effective means of improving trainees' presentations have not been identified. WHAT THIS STUDY ADDS:Oral presentation feedback sessions facilitated by faculty by using an 18-item competency-based evaluation form early in pediatric clerkships improved medical students' subsequent oral presentations. Medical schools should consider implementing this evidence-supported practice. abstract OBJECTIVE: To measure the effects of participating in structured oral presentation evaluation sessions early in pediatric clerkships on students' subsequent presentations. METHODS:We conducted a single-blind, 3-arm, cluster randomized controlled trial during pediatric clerkships at Boston University School of Medicine, University of Maryland School of Medicine, Oregon Health & Science University, and Case Western Reserve University School of Medicine. Blocks of students at each school were randomly assigned to experience either (1) no formal presentation feedback (control) or a small-group presentation feedback session early in pediatric clerkships in which students gave live presentations and received feedback from faculty who rated their presentations by using a (2) single-item (simple) or (3) 18-item (detailed) evaluation form. At the clerkship end, overall quality of subjects' presentations was rated by faculty blinded to randomization status, and subjects reported whether their presentations had improved. Analyses included multivariable linear and logistic regressions clustered on clerkship block that controlled for medical school. RESULTS:A total of 476 participants were evenly divided into the 3 arms, which had similar characteristics. Compared with controls, presentation quality was significantly associated with participating in detailed (coefficient: 0.38; 95% confidence interval [CI]: 0.07-0.69) but not simple (coefficient: 0.16; 95% CI: 20.12-0.43) feedback sessions. Similarly, student self-report of presentation improvement was significantly associated with participating in detailed (odds ratio: 2.16; 95% CI: 1.11-4.18] but not simple (odds ratio: 1.89; 95% CI: 0.91-3.93) feedback sessions.CONCLUSIONS: Small-group presentation feedback sessions led by faculty using a detailed evaluation form resulted in clerkship students delivering oral presentations of higher quality compared with controls. Pediatrics 2014;134:965-971 AUTHORS:

show abstract

Section: Methodsmentioning

confidence: 99%

Feedback on Oral Presentations During Pediatric Clerkships: A Randomized Controlled Trial

et al. 2014

View full text Add to dashboard Cite

show abstract

“…This procedure measures the cumulative effect of the treatment and has the maximum number of participants. To adjust for a potential clustering effect we used robust generalised estimating equations 41 with exchangeable correlation structure. For binary outcomes we used a logit link with a binomial distribution for the outcome, and for continuous outcomes we used an identity link with a normal distribution.…”

Section: Discussionmentioning

confidence: 99%

Effectiveness of the diabetes education and self management for ongoing and newly diagnosed (DESMOND) programme for people with newly diagnosed type 2 diabetes: cluster randomised controlled trial

2008

BMJ

View full text Add to dashboard Cite

Objective To evaluate the effectiveness of a structured group education programme on biomedical, psychosocial, and lifestyle measures in people with newly diagnosed type 2 diabetes. Design Multicentre cluster randomised controlled trial in primary care with randomisation at practice level. Setting 207 general practices in 13 primary care sites in the United Kingdom. Participants 824 adults (55% men, mean age 59.5 years). Intervention A structured group education programme for six hours delivered in the community by two trained healthcare professional educators compared with usual care. Main outcome measures Haemoglobin A 1c levels, blood pressure, weight, blood lipid levels, smoking status, physical activity, quality of life, beliefs about illness, depression, and emotional impact of diabetes at baseline and up to 12 months. Main results Haemoglobin A 1c levels at 12 months had decreased by 1.49% in the intervention group compared with 1.21% in the control group. After adjusting for baseline and cluster, the difference was not significant: 0.05% (95% confidence interval −0.10% to 0.20%). The intervention group showed a greater weight loss: −2.98 kg (95% confidence interval −3.54 to −2.41) compared with 1.86 kg (−2.44 to −1.28), P=0.027 at 12 months. The odds of not smoking were 3.56 (95% confidence interval 1.11 to 11.45), P=0.033 higher in the intervention group at 12 months. The intervention group showed significantly greater changes in illness belief scores (P=0.001); directions of change were positive indicating greater understanding of diabetes. The intervention group had a lower depression score at 12 months: mean difference was −0.50 (95% confidence interval −0.96 to −0.04); P=0.032. A positive association was found between change in perceived personal responsibility and weight loss at 12 months (β=0.12; P=0.008). Conclusion A structured group education programme for patients with newly diagnosed type 2 diabetes resulted in greater improvements in weight loss and smoking cessation and positive improvements in beliefs about illness but no difference in haemoglobin A 1c levels up to 12 months after diagnosis. Trial registration Current Controlled Trials ISRCTN17844016.

show abstract

“…When the number of observations differs from cluster to cluster, a t test in which the cluster means are weighted for cluster size is recommended (see, e.g., Campbell, Donner, & Klar, 2007). 4 This analysis is easy to compute and report, and it perfectly accounts for violations of the independence assumption: The Type-I error rate is at its nominal level (i.e., 5%).…”

Section: (Weighted) T Tests On Cluster Meansmentioning

confidence: 99%

Analyzing randomized controlled interventions: Three notes for applied linguists

Vanhove

2015

SSLLT

View full text Add to dashboard Cite

I discuss three common practices that obfuscate or invalidate the statistical analysis of randomized controlled interventions in applied linguistics. These are (a) checking whether randomization produced groups that are balanced on a number of possibly relevant covariates, (b) using repeated measures ANOVA to analyze pretest-posttest designs, and (c) using traditional significance tests to analyze interventions in which whole groups were assigned to the conditions (cluster randomization). The first practice is labeled superfluous, and taking full advantage of important covariates regardless of balance is recommended. The second is needlessly complicated, and analysis of covariance is recommended as a more powerful alternative. The third produces dramatic inferential errors, which are largely, though not entirely, avoided when mixed-effects modeling is used. This discussion is geared towards applied linguists who need to design, analyze, or assess intervention studies or other randomized controlled trials. Statistical formalism is kept to a minimum throughout.

show abstract

Developments in cluster randomized trials and Statistics in Medicine

Cited by 232 publications

References 79 publications

Feedback on Oral Presentations During Pediatric Clerkships: A Randomized Controlled Trial

Feedback on Oral Presentations During Pediatric Clerkships: A Randomized Controlled Trial

Effectiveness of the diabetes education and self management for ongoing and newly diagnosed (DESMOND) programme for people with newly diagnosed type 2 diabetes: cluster randomised controlled trial

Analyzing randomized controlled interventions: Three notes for applied linguists

Contact Info

Product

Resources

About