Sample size calculation in hierarchical 2×2 factorial trials with unequal cluster sizes

ObjectivesTo investigate the extent to which cluster sizes vary in stepped-wedge cluster randomised trials (SW-CRT) and whether any variability is accounted for during the sample size calculation and analysis of these trials.SettingAny, not limited to healthcare settings.ParticipantsAny taking part in an SW-CRT published up to March 2016.Primary and secondary outcome measuresThe primary outcome is the variability in cluster sizes, measured by the coefficient of variation (CV) in cluster size. Secondary outcomes include the difference between the cluster sizes assumed during the sample size calculation and those observed during the trial, any reported variability in cluster sizes and whether the methods of sample size calculation and methods of analysis accounted for any variability in cluster sizes.ResultsOf the 101 included SW-CRTs, 48% mentioned that the included clusters were known to vary in size, yet only 13% of these accounted for this during the calculation of the sample size. However, 69% of the trials did use a method of analysis appropriate for when clusters vary in size. Full trial reports were available for 53 trials. The CV was calculated for 23 of these: the median CV was 0.41 (IQR: 0.22–0.52). Actual cluster sizes could be compared with those assumed during the sample size calculation for 14 (26%) of the trial reports; the cluster sizes were between 29% and 480% of that which had been assumed.ConclusionsCluster sizes often vary in SW-CRTs. Reporting of SW-CRTs also remains suboptimal. The effect of unequal cluster sizes on the statistical power of SW-CRTs needs further exploration and methods appropriate to studies with unequal cluster sizes need to be employed.

Download Full-text

Simulation-Based Sample-Size Calculation for Designing New Clinical Trials and Diagnostic Test Accuracy Studies to Update an Existing Meta-Analysis

The Stata Journal Promoting communications on statistics and Stata ◽

10.1177/1536867x1301300302 ◽

2013 ◽

Vol 13 (3) ◽

pp. 451-473 ◽

Cited By ~ 6

Author(s):

Michael J. Crowther ◽

Sally R. Hinchliffe ◽

Alison Donald ◽

Alex J. Sutton

Keyword(s):

Clinical Trials ◽

Sample Size ◽

Diagnostic Test ◽

Meta Analysis ◽

Sample Size Calculation ◽

Diagnostic Test Accuracy ◽

Test Accuracy ◽

Simulation Based

Download Full-text

The most frequently asked question to a statistician: The sample size

Multiple Sclerosis Journal ◽

10.1177/1352458517695471 ◽

2017 ◽

Vol 23 (5) ◽

pp. 644-646 ◽

Cited By ~ 2

Author(s):

Maria Pia Sormani

Keyword(s):

Clinical Study ◽

Sample Size ◽

Study Design ◽

Treatment Effect ◽

Sample Size Calculation ◽

Ethical Implications ◽

Number Of Patients ◽

Reducing Costs ◽

Correct Size

The calculation of the sample size needed for a clinical study is the challenge most frequently put to statisticians, and it is one of the most relevant issues in the study design. The correct size of the study sample optimizes the number of patients needed to get the result, that is, to detect the minimum treatment effect that is clinically relevant. Minimizing the sample size of a study has the advantage of reducing costs, enhancing feasibility, and also has ethical implications. In this brief report, I will explore the main concepts on which the sample size calculation is based.

Download Full-text

Sample size calculation for clinical trials in which entry criteria and outcomes are counts of events

Statistics in Medicine ◽

10.1002/sim.4780130806 ◽

1994 ◽

Vol 13 (8) ◽

pp. 859-870 ◽

Cited By ~ 18

Author(s):

Robert P. McMahon ◽

Michael Proschan ◽

Nancy L. Geller ◽

Peter H. Stone ◽

George Sopko

Keyword(s):

Clinical Trials ◽

Sample Size ◽

Sample Size Calculation

Download Full-text

Regression dilution bias: Tools for correction methods and sample size calculation

Upsala Journal of Medical Sciences ◽

10.3109/03009734.2012.668143 ◽

2012 ◽

Vol 117 (3) ◽

pp. 279-283 ◽

Cited By ~ 15

Author(s):

Lars Berglund

Keyword(s):

Sample Size ◽

Sample Size Calculation

Download Full-text

Prevalence of Ectopic Eruption, Impaction, Retention and Agenesis of the Permanent Second Molar

The Angle Orthodontist ◽

10.2319/072506-306.1 ◽

2007 ◽

Vol 77 (5) ◽

pp. 773-778 ◽

Cited By ~ 43

Author(s):

Lars Bondemark ◽

Jola Tsiopa

Keyword(s):

Early Diagnosis ◽

Sample Size ◽

Sample Size Calculation ◽

Optimal Time ◽

Second Molar ◽

Ectopic Eruption ◽

Delayed Eruption ◽

Dental Records ◽

The Times ◽

The City

Abstract Objective: To elucidate the prevalence of ectopic eruption, impaction, and primary and secondary retention as well as agenesis of the permanent second molar (M2) among adolescents. Materials and Methods: After a sample size calculation, dental records, including radiographs, of 1543 patients (722 girls and 821 boys), from three clinics in the city of Malmoe, Sweden, were retrospectively analyzed. Series of annual records and radiographs were examined for all patients from 10 to 16 years of age and were carried out during 2004–2006. The prevalence of ectopic eruption, impaction, and primary and secondary retention as well as agenesis of M2s was registered in a standardized manner and according to preset definitions. In addition, the times of emergence of the M2s were recorded. Results: The prevalence of ectopic eruption of M2 was 1.5%, the prevalence of primary retention was 0.6%, and the prevalence of impaction was 0.2%. This means that the overall prevalence of eruption disturbances was 2.3%. In addition, the prevalence of agenesis was 0.8%. The prevalence of ectopic eruption was significantly higher in the mandible. Those patients with eruption disturbances and agenesis of M2 showed significantly delayed eruption of their other M2s compared to the individuals without any eruption disturbances. Conclusions: The prevalence of eruption disturbances was higher than reported earlier, and, even if the disturbances do not occur frequently, it is important to develop an early diagnosis in order to start the treatment at the optimal time.

Download Full-text