Brennan C Kahan1, Michael O Harhay2. 1. Pragmatic Clinical Trials Unit, Centre for Primary Care and Public Health, Queen Mary University of London, 58 Turner Street, London E1 2AB, UK. Electronic address: b.kahan@qmul.ac.uk. 2. Division of Epidemiology, Department of Biostatistics and Epidemiology, Perelman School of Medicine, University of Pennsylvania, 708 Blockley Hall, 423 Guardian Drive, Philadelphia, PA 19146, USA.
Abstract
OBJECTIVES: Adjustment for center in multicenter trials is recommended when there are between-center differences or when randomization has been stratified by center. However, common methods of analysis (such as fixed-effects, Mantel-Haenszel, or stratified Cox models) often require a large number of patients or events per center to perform well. STUDY DESIGN AND SETTING: We reviewed 206 multicenter randomized trials published in four general medical journals to assess the average number of patients and events per center and determine whether appropriate methods of analysis were used in trials with few patients or events per center. RESULTS: The median number of events per center/treatment arm combination for trials using a binary or survival outcome was 3 (interquartile range, 1-10). Sixteen percent of trials had less than 1 event per center/treatment combination, 50% fewer than 3, and 63% fewer than 5. Of the trials which adjusted for center using a method of analysis which requires a large number of events per center, 6% had less than 1 event per center-treatment combination, 25% fewer than 3, and 50% fewer than 5. Methods of analysis that allow for few events per center, such as random-effects models or generalized estimating equations (GEEs), were rarely used. CONCLUSION: Many multicenter trials contain few events per center. Adjustment for center using random-effects models or GEE with model-based (non-robust) standard errors may be beneficial in these scenarios.
OBJECTIVES: Adjustment for center in multicenter trials is recommended when there are between-center differences or when randomization has been stratified by center. However, common methods of analysis (such as fixed-effects, Mantel-Haenszel, or stratified Cox models) often require a large number of patients or events per center to perform well. STUDY DESIGN AND SETTING: We reviewed 206 multicenter randomized trials published in four general medical journals to assess the average number of patients and events per center and determine whether appropriate methods of analysis were used in trials with few patients or events per center. RESULTS: The median number of events per center/treatment arm combination for trials using a binary or survival outcome was 3 (interquartile range, 1-10). Sixteen percent of trials had less than 1 event per center/treatment combination, 50% fewer than 3, and 63% fewer than 5. Of the trials which adjusted for center using a method of analysis which requires a large number of events per center, 6% had less than 1 event per center-treatment combination, 25% fewer than 3, and 50% fewer than 5. Methods of analysis that allow for few events per center, such as random-effects models or generalized estimating equations (GEEs), were rarely used. CONCLUSION: Many multicenter trials contain few events per center. Adjustment for center using random-effects models or GEE with model-based (non-robust) standard errors may be beneficial in these scenarios.
Authors: Rong Chu; Lehana Thabane; Jinhui Ma; Anne Holbrook; Eleanor Pullenayegum; Philip James Devereaux Journal: BMC Med Res Methodol Date: 2011-02-21 Impact factor: 4.615
Authors: Pascal Probst; Fabian Schuh; Colette Dörr-Harim; Anja Sander; Thomas Bruckner; Christina Klose; Inga Rossion; Felix Nickel; Beat Peter Müller-Stich; Arianeb Mehrabi; Thilo Hackert; Markus W Büchler; Markus K Diener Journal: BMJ Open Date: 2021-02-22 Impact factor: 2.692
Authors: Yaseen Arabi; Fahad Al-Hameed; Karen E A Burns; Sangeeta Mehta; Sami Alsolamy; Mohammed Almaani; Yasser Mandourah; Ghaleb A Almekhlafi; Ali Al Bshabshe; Simon Finfer; Mohammed Alshahrani; Imran Khalid; Yatin Mehta; Atul Gaur; Hassan Hawa; Hergen Buscher; Zia Arshad; Hani Lababidi; Abdulsalam Al Aithan; Jesna Jose; Sheryl Ann I Abdukahil; Lara Y Afesh; Maamoun Dbsawy; Abdulaziz Al-Dawood Journal: Trials Date: 2018-03-15 Impact factor: 2.279
Authors: Christian Ovesen; Janus Christian Jakobsen; Christian Gluud; Thorsten Steiner; Zhe Law; Katie Flaherty; Rob A Dineen; Philip M Bath; Nikola Sprigg; Hanne Christensen Journal: BMC Res Notes Date: 2018-06-13