摘要
选择性偏倚是医学实践中客观存在的,文中从特定因素远期效应考虑,将其分为消除型选择性偏倚与非消除型选择性偏倚。从盐亭县资料提示,非消除型选择性偏倚可分为平行型、递增型和递减型。对非消除型选择性偏倚评诂必须有适宜的观察时间。对资料可根据配对或成组设计进行分析,亦可作相关分析或趋势检验。做结论时,必须有充分观察时期。
Selection bias,which was sepatated into elimination and nonelimination pattern according to forward effect of specially designated factor,are objective existence in medical practice.According to forward effectiveness of a specific factor,and results to analysis data of vasectomized and nonvasecmized men for Yanting County,the nonelimination pattern was separated into three pattern:paralled pattern,progressive extension pattern and progressive decrease pattern.A observation period must be suitable for evaluation on selection bias of nonelimination pattern.A statistical methods for this indicatrix are selected according to paried sign or others.When observing period is full,the conclusion of this data can be obtained,but it is the best that situation would be observed in different area,and synthetic analysis would be executed for this data.
出处
《现代预防医学》
CAS
1998年第1期15-18,共4页
Modern Preventive Medicine
基金
四川省计划生育委员会资助
关键词
偏倚
选择性偏倚
非消除型
评估
Bias Selection bias Selection of nonelimination pattern