文章摘要
杨美霞,周艺彪,姜庆五.测量误差变量与准确测量变量混合对研究真实性的影响[J].中华流行病学杂志,2007,28(8):810-813
测量误差变量与准确测量变量混合对研究真实性的影响
The impact of incorrectly-measured variables when mixed with precisely measured variables on the study of validity in epidemiological research
收稿日期:2006-06-30  出版日期:2014-09-12
DOI:
中文关键词: 测量误差变量;准确测量变量;测量误差;偏倚
英文关键词: Mismeasured variable;Precisely measured variable;Measurement error;Bias
基金项目:国家自然科学基金资助项目(30590374)
作者单位
杨美霞 上海市徐汇区疾病预防控制中心, 上海 200031 
周艺彪 复旦大学公共卫生学院流行病学教研室 
姜庆五 复旦大学公共卫生学院流行病学教研室 
摘要点击次数: 727
全文下载次数: 538
中文摘要:
      目的 探讨测量误差变量与准确测量变量混合情况下测量误差对联系效应估计的影响.方法 利用测量误差大小、准确测量变量与测量误差变量之间的相关性、准确测量变量的个数和联系效应之间的函数,采用R软件做图来讨论分析测量误差对研究真实性的影响.结果 当连续变量Y和Z能准确测量,连续变量X不能准确测量时,无差异性测量误差使所估计的联系效应值总低于实际值,并随X与Z的相关程度的增加,测量误差所致的偏倚会进一步地恶化.在一个错分二分类变量X和一个准确测量连续变量Z混合的情况下,测量误差所致的偏倚不仅跟暴露测量的灵敏度和特异度有关,而且跟X与Z的相关系数以及X的暴露比例有关,并且随着相关系数的增加,AF值逐渐减少.在ρ=0.5时,AF值为1.419,变量X对应变量Y的联系效应估计值大于实际值,但当ρ增至0.9时,AF值为0.474,其联系效应估计值低于实际值,改变了错分偏倚的方向.结论 在准确测量变量和测量误差变量混杂的研究中,用线性回归模型来分析估计多个自变量与应变量之间的联系时,对测量误差所致偏倚的识别、控制和评估是十分必要的,对结果的解释要谨慎.
英文摘要:
      Objective To explore the impact of measurement error on the associated effects under the incorrectly-measured variables when mixed with precisely measured variables.Methods Based on the functions of measurement error,correlation of incorrectly-measured predictors and precisely measured explanatory variables,number of precisely measured explanatory variablea and associated effect,the‘R Project for Statistical Computing’method is used to analyze the impact of measurement on the validity of a study.Results Under the scenario that the continuous response Y and the continuous explanatory Z are precisely measured but the continuous predictor X is incorrectly-measured,when focusing on inference about the effect of X on Y,the non-differential measurement error always makes the value of estimated effect less than the actual value,and the attenuation effect of measurement error more closely worsens the correlation of X and Z.Under a misclassification dichotomous predictor X with an additional precisely measured explanatory variable Z and focusing on inference about the effect of X on Y,the misclassification bias is not only related to the sensitivity and specificity of exposure measurement,but also to the correlation between X and Z and exposure proportion of X.The attenuation factor(AF)decreases gradually with the increasing correlation between X and Z.For instance,in theρ=0.5 scenario,AF is 1.419,and the estimated effect of dichotomous predictor X on continuous response Y is more than the actual effect.When it increases to 0.9,AF is 0.474,the estimated effect becomes less than the true effect.Conclusion In the studies of the impact of measurement error in linear regression with additional precisely measured explanatory variables,the impact of measurement error on the associated effect is relatively complex, suggesting that it is necessary to control and to assess the measurement error bias in order to correctly interpret the results of a study.
查看全文   Html全文     查看/发表评论  下载PDF阅读器
关闭