|
|
|
| Selection and adjustment of potential confounders based on changes of effect size using EmpowerStats |
| SHI Hongying1, CHEN Changzhong2, MAO Guangyun1, HUANG Chenping1, YANG Xinjun1. |
1.Department of Preventive Medicine, School of Public Health, Wenzhou Medical University, Wenzhou, 325035; 2.Dana Farber Cancer Institute, Medical College of Harvard University, Massachusetts, 02115
|
|
| Cite this article: |
|
SHI Hongying,CHEN Changzhong,MAO Guangyun, et al. Selection and adjustment of potential confounders based on changes of effect size using EmpowerStats[J]. JOURNAL OF WEZHOU MEDICAL UNIVERSITY, 2017, 47(5): 361-365.
|
|
|
Abstract Objective: To introduce a new method for selecting and adjusting confounding factors. Methods: The disadvantage of traditional method for selecting confounders including methods based on P value or stepwise regression was analyzed was analyzed, and a new method based on the change of effect size was proposed to select the potential confounders which need to be controlled. And the study also demonstrated the application of EmpowerStats software using the new method. Results: EmpowerStats statistical software could automatically choose right regression methods and select the appropriate confounding factors based on the change of effect size conveniently. Conclusion: Selecting confounding factors based on the change of effect size is a better choice, and can give a more accurate independent effect, and has been widely used and accepted worldwide.
|
|
Received: 15 December 2016
|
| |
|
|
|
[1] KROUSEL-WOOD M A, CHAMBERS R B, MUNTNER P. Clinicians’ guide to statistics for medical practice and research: Part II[J]. Ochsner J, 2007, 7(1): 3-7.
[2] GROENWOLD R H, HOES A W, HAK E. Confounding in publications of observational intervention studies[J]. Eur J Epidemiol, 2007, 22 (7): 413-415.
[3] LEE P H. Is a cutoff of 10% appropriate for the change-inestimate criterion of confounder identification?[J]. J Epidemiol, 2014, 24(2): 161-167.
[4] KERNAN W N, VISCOLI C M, BRASS L M, et al. Phenylpropanolamine and the risk of hemorrhagic stroke[J]. N Engl J Med, 2000, 343(25): 1826-1832.
[5] BAGLIETTO L, ENGLISH D R, GERTIG D M, et al. Does dietary folate intake modify effect of alcohol consumption on breast cancer risk? Prospective cohort study[J]. BMJ, 2005, 331(7520): 807-810.
[6] LIU T, DAVID S P, TYNDALE R F, et al. Associations of CYP2A6 genotype with smoking behaviors in southern China[J]. Addiction, 2011, 106(5): 985-994.
[7] KROUSEL-WOOD M A, CHAMBERS R B, MUNTNER P. Clinicians’ guide to statistics for medical practice and research: part I[J]. Ochsner J, 2006, 6(2): 68-83.
[8] 赵晓蒙, 李炳海, 王素珍, 等. 经倾向指数匹配后的gp方案与np方案治疗非小细胞肺癌的疗效评价[J]. 中国卫生统计, 2014, 31(1): 34-36.
[9] 王永吉, 蔡宏伟, 夏结来, 等. 倾向指数第一讲倾向指数的基本概念和研究步骤[J]. 中华流行病学杂志, 2010, 31(3): 347-348.
[10] 王永吉, 蔡宏伟, 夏结来, 等. 倾向指数第二讲倾向指数常用研究方法[J]. 中华流行病学杂志, 2010, 31(5): 584-585.
[11] ELLIS A R, DUSETZINA S B, HANSEN R A, et al. Confounding control in a nonexperimental study of STAR*D data: logistic regression balanced covariates better than boosted CART[J]. Ann Epidemiol, 2013, 23(4): 204-209.
[12] STUKEL T A, FISHER E S, WENNBERG D E, et al. Analysis of observational studies in the presence of treatment selection bias: effects of invasive cardiac management on AMI survival using propensity score and instrumental variable methods[J]. JAMA, 2007, 297(3): 278-285.
[13] VOLPP K G, TROXEL A B, PAULY M V, et al. A randomized, controlled trial of financial incentives for smoking cessation[J]. N Engl J Med, 2009, 360(7): 699-709.
[14] LEE C C, LEE M T, CHEN Y S, et al. Risk of aortic dissection and aortic aneurysm in patients taking oral fluoroquinolone[J]. JAMA Intern Med, 2015, 175(11): 1839-1847.
|
|
|
|
