Carlos G Grijalva1,2, Christianne L Roumie2,3, Harvey J Murff2,3, Adriana M Hung2,3, Cole Beck4, Xulei Liu2,4, Marie R Griffin1,2,3, Robert A Greevy2,4. 1. Department of Health Policy, Vanderbilt University, Nashville, TN, 37232 USA. 2. VA Tennessee Valley Geriatric Research Education Clinical Center (GRECC), Nashville, TN, 37212 USA. 3. Department of Medicine, Vanderbilt University, Nashville, TN, 37232 USA. 4. Department of Biostatistics, Vanderbilt University, Nashville, TN, 37203 USA.
Abstract
AIM: Evaluate performance of analytical strategies commonly used to adjust for baseline differences in continuous outcome variables for comparative effectiveness studies. PATIENTS & METHODS: Data simulations resembling a comparison of HbA1c values after initiation of antidiabetic treatments adjusting for baseline HbA1c. We evaluated change scores, analyses of covariance including linear, nonlinear with/without robust variance estimations, before and after optimal matching. We also evaluated the impact of measurement error. RESULTS: With increasing HbA1c baseline differences between groups, bias in effect estimates and suboptimal CI coverage probabilities increased in all approaches. These issues were further compounded by measurement error. Matching on baseline HbA1c, substantially mitigated these issues. CONCLUSION: In comparative studies with continuous outcomes, matching on baseline values of the outcome variable improves analytical performance.
AIM: Evaluate performance of analytical strategies commonly used to adjust for baseline differences in continuous outcome variables for comparative effectiveness studies. PATIENTS & METHODS: Data simulations resembling a comparison of HbA1c values after initiation of antidiabetic treatments adjusting for baseline HbA1c. We evaluated change scores, analyses of covariance including linear, nonlinear with/without robust variance estimations, before and after optimal matching. We also evaluated the impact of measurement error. RESULTS: With increasing HbA1c baseline differences between groups, bias in effect estimates and suboptimal CI coverage probabilities increased in all approaches. These issues were further compounded by measurement error. Matching on baseline HbA1c, substantially mitigated these issues. CONCLUSION: In comparative studies with continuous outcomes, matching on baseline values of the outcome variable improves analytical performance.
Authors: Earle W Holmes; Cağatay Erşahin; Geri J Augustine; Gerald A Charnogursky; Margie Gryzbac; Joanne V Murrell; Kathleen M McKenna; Fadi Nabhan; Stephen E Kahn Journal: Am J Clin Pathol Date: 2008-04 Impact factor: 2.493
Authors: Maureen A Smith; Mary S Vaughan-Sarrazin; Menggang Yu; Xinyi Wang; Peter A Nordby; Christine Vogeli; Jonathan Jaffery; Joshua P Metlay Journal: J Am Med Inform Assoc Date: 2019-11-01 Impact factor: 4.497
Authors: David Guy; Rachel Glicksman; Roger Buckley; Patrick Cheung; Hans Chung; Stanley Flax; David Hajek; Andrew Loblaw; Gerard Morton; Jeffery Noakes; Les Spevack; Joseph L K Chin; George Rodrigues Journal: Can Urol Assoc J Date: 2022-04 Impact factor: 2.052