| 实现logistic与Cox回归相乘相加交互作用的临床实践宏程序 |
| |
| 引用本文： | 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. |
| |
| 作者姓名： | 聂志强 欧艳秋 庄建 曲艳吉 麦劲壮 陈寄梅 刘小清 |
| |
| 作者单位： | 510080 广州, 广东省心血管病研究所 广东省华南结构性心脏病重点实验室 广东省人民医院 广东省医学科学院流行病学研究室;510080 广州, 广东省心血管病研究所 广东省华南结构性心脏病重点实验室 广东省人民医院 广东省医学科学院流行病学研究室;510080 广州, 广东省心血管病研究所 广东省华南结构性心脏病重点实验室 广东省人民医院心脏外科;510080 广州, 广东省心血管病研究所 广东省华南结构性心脏病重点实验室 广东省人民医院 广东省医学科学院流行病学研究室;510080 广州, 广东省心血管病研究所 广东省华南结构性心脏病重点实验室 广东省人民医院 广东省医学科学院流行病学研究室;510080 广州, 广东省心血管病研究所 广东省华南结构性心脏病重点实验室 广东省人民医院心脏外科;510080 广州, 广东省心血管病研究所 广东省华南结构性心脏病重点实验室 广东省人民医院 广东省医学科学院流行病学研究室 |
| |
| 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： | 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。
|
| 关 键 词： | logistic回归 Cox比例风险模型 交互作用 |
| 收稿时间： | 2015/10/9 0:00:00 |
Application of SAS macro to evaluated multiplicative and additive interaction in logistic and Cox regression in clinical practices |
| |
| Nie Zhiqiang,Ou Yanqiu,Zhuang Jian,Qu Yanji,Mai Jinzhuang,Chen Jimei and Liu Xiaoqing.Application of SAS macro to evaluated multiplicative and additive interaction in logistic and Cox regression in clinical practices[J].Chinese Journal of Epidemiology,2016,37(5):737-740. |
| |
| Authors: | Nie Zhiqiang Ou Yanqiu Zhuang Jian Qu Yanji Mai Jinzhuang Chen Jimei and Liu Xiaoqing |
| |
| Institution: | Department of Cardiac Surgery, South China Key Laboratory of Structural Heart Disease, Guangdong Cardiovascular Disease Institute, Division of Epidemiology, Guangdong People''s Hospital, Guangdong Academic of Medical Science, Guangzhou 510080, China;Department of Cardiac Surgery, South China Key Laboratory of Structural Heart Disease, Guangdong Cardiovascular Disease Institute, Division of Epidemiology, Guangdong People''s Hospital, Guangdong Academic of Medical Science, Guangzhou 510080, China;Department of Pediatric Cardiology, Guangdong People''s Hospital, Guangdong Academic of Medical Science, Guangzhou 510080, China;Department of Cardiac Surgery, South China Key Laboratory of Structural Heart Disease, Guangdong Cardiovascular Disease Institute, Division of Epidemiology, Guangdong People''s Hospital, Guangdong Academic of Medical Science, Guangzhou 510080, China;Department of Cardiac Surgery, South China Key Laboratory of Structural Heart Disease, Guangdong Cardiovascular Disease Institute, Division of Epidemiology, Guangdong People''s Hospital, Guangdong Academic of Medical Science, Guangzhou 510080, China;Department of Pediatric Cardiology, Guangdong People''s Hospital, Guangdong Academic of Medical Science, Guangzhou 510080, China;Department of Cardiac Surgery, South China Key Laboratory of Structural Heart Disease, Guangdong Cardiovascular Disease Institute, Division of Epidemiology, Guangdong People''s Hospital, Guangdong Academic of Medical Science, Guangzhou 510080, China |
| |
| Abstract: | 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. |
| |
| Keywords: | Logistic regression Cox proportional hazard model Interactions |
|
| 点击此处可从《中华流行病学杂志》浏览原始摘要信息 |
| 点击此处可从《中华流行病学杂志》下载免费的PDF全文 |
|
