| 聂志强,欧艳秋,庄建,曲艳吉,麦劲壮,陈寄梅,刘小清.实现logistic与Cox回归相乘相加交互作用的临床实践宏程序[J].中华流行病学杂志,2016,37(5):737-740 |
| 实现logistic与Cox回归相乘相加交互作用的临床实践宏程序 |
| Application of SAS macro to evaluated multiplicative and additive interaction in logistic and Cox regression in clinical practices |
| 收稿日期:2015-10-09 出版日期:2016-05-13 |
| DOI：10.3760/cma.j.issn.0254-6450.2016.05.031 |
| 中文关键词: logistic回归 Cox比例风险模型 交互作用 |
| 英文关键词: Logistic regression Cox proportional hazard model Interactions |
| 基金项目:国家自然科学基金(U1401255);国家"十二五"科技支撑计划(2011BAI11B22,2012BAI04B05);广东省科技计划项目(2012B032000014,2011B031900002,2013B030400001);广东省国际合作项目(2014A050503048);广东省医学科研基金(C2012012) |
|
| 摘要点击次数: 10206 |
| 全文下载次数: 4418 |
| 中文摘要: |
| 病例对照研究常采用条件或非条件logistic分析,生存资料分析常采用Cox比例模型,但多数文献仅纳入主效应模型,然而广义线性模型不同于一般线性模型,其交互作用分为相乘交互与相加交互作用,前者只有统计学意义而后者更符合生物学意义。笔者以SAS 9.4软件编写宏,在计算logistic与Cox相乘交互项同时计算交互对比度、归因比、交互作用指数指标及利用Wald、Delta、PL(profile likelihood) 3种方法的可信区间评价相加交互作用,便于临床流行病学与遗传学大数据分析相乘相加交互作用时参考。 |
| 英文摘要: |
| Conditional logistic regression analysis and unconditional logistic regression analysis are commonly used in case control study, but Cox proportional hazard model is often used in survival data analysis. Most literature only refer to main effect model, however, generalized linear model differs from general linear model, and the interaction was composed of multiplicative interaction and additive interaction. The former is only statistical significant, but the latter has biological significance. In this paper, macros was written by using SAS 9.4 and the contrast ratio, attributable proportion due to interaction and synergy index were calculated while calculating the items of logistic and Cox regression interactions, and the confidence intervals of Wald, delta and profile likelihood were used to evaluate additive interaction for the reference in big data analysis in clinical epidemiology and in analysis of genetic multiplicative and additive interactions. |
|
查看全文
Html全文
查看/发表评论 下载PDF阅读器 |
|
| 关闭 |
|
|
|
