George F Borm1, Jaap Fransen, Wim A J G Lemmens. 1. Department of Epidemiology and Biostatistics, Radboud University Nijmegen Medical Centre, Geert Grooteplein 21, PO Box 9101, NL-6500 HB Nijmegen, The Netherlands. G.Borm@epid.umcn.nl
Abstract
OBJECTIVE: Randomized clinical trials that compare two treatments on a continuous outcome can be analyzed using analysis of covariance (ANCOVA) or a t-test approach. We present a method for the sample size calculation when ANCOVA is used. STUDY DESIGN AND SETTING: We derived an approximate sample size formula. Simulations were used to verify the accuracy of the formula and to improve the approximation for small trials. The sample size calculations are illustrated in a clinical trial in rheumatoid arthritis. RESULTS: If the correlation between the outcome measured at baseline and at follow-up is rho, ANCOVA comparing groups of (1-rho(2))n subjects has the same power as t-test comparing groups of n subjects. When on the same data, ANCOVA is used instead of t-test, the precision of the treatment estimate is increased, and the length of the confidence interval is reduced by a factor 1-rho(2). CONCLUSION: ANCOVA may considerably reduce the number of patients required for a trial.
OBJECTIVE: Randomized clinical trials that compare two treatments on a continuous outcome can be analyzed using analysis of covariance (ANCOVA) or a t-test approach. We present a method for the sample size calculation when ANCOVA is used. STUDY DESIGN AND SETTING: We derived an approximate sample size formula. Simulations were used to verify the accuracy of the formula and to improve the approximation for small trials. The sample size calculations are illustrated in a clinical trial in rheumatoid arthritis. RESULTS: If the correlation between the outcome measured at baseline and at follow-up is rho, ANCOVA comparing groups of (1-rho(2))n subjects has the same power as t-test comparing groups of n subjects. When on the same data, ANCOVA is used instead of t-test, the precision of the treatment estimate is increased, and the length of the confidence interval is reduced by a factor 1-rho(2). CONCLUSION: ANCOVA may considerably reduce the number of patients required for a trial.
Authors: Christopher J Hernandez; Daniel S Ramsey; Stephanie J Dux; Eileen H Chu; Clare M Rimnac Journal: Clin Orthop Relat Res Date: 2012-09 Impact factor: 4.176
Authors: Corrine I Voils; Cynthia J Coffman; Janet M Grubber; David Edelman; Azita Sadeghpour; Matthew L Maciejewski; Jamiyla Bolton; Alex Cho; Geoffrey S Ginsburg; William S Yancy Journal: J Gen Intern Med Date: 2015-04-16 Impact factor: 5.128
Authors: Michael Schwenk; Marwan Sabbagh; Ivy Lin; Pharah Morgan; Gurtej S Grewal; Jane Mohler; David W Coon; Bijan Najafi Journal: J Rehabil Res Dev Date: 2016
Authors: Cristina C Hendrix; Donald E Bailey; Karen E Steinhauser; Maren K Olsen; Karen M Stechuchak; Sarah G Lowman; Abby J Schwartz; Richard F Riedel; Francis J Keefe; Laura S Porter; James A Tulsky Journal: Support Care Cancer Date: 2015-06-12 Impact factor: 3.603
Authors: Brodie M Sakakibara; William C Miller; Melanie Souza; Viara Nikolova; Krista L Best Journal: Arch Phys Med Rehabil Date: 2013-02-04 Impact factor: 3.966
Authors: Thomas J Hoogeboom; Mirelle J P M Stukstette; Rob A de Bie; Jessica Cornelissen; Alfons A den Broeder; Cornelia H M van den Ende Journal: BMC Musculoskelet Disord Date: 2010-07-01 Impact factor: 2.362