摘要
目前统计结果倾向于使用假设检验P值 ,但P值存在一定的局限性。本文总结了三种资料类型效应量的可信区间计算方法及精度的影响因素。统计的结果应同时报告P值与可信区间 ,并为循证医学提供有效证据。
It has a trend at present to overemphasize on hypothesis testing and the use of P values,but P values have some limitations in presentation of study results.Three formulas for calculating confidence intervals for different data types and factors related with precision of CI were summarized in this paper.The right way of presentation of study results should include both P values and confidence intervals,and it will help to provide valid evidences for EBM.
出处
《华西医学》
CAS
2000年第4期402-403,共2页
West China Medical Journal
