GRADE建议通过检查95%可信区间（CI）为决定不精确性的最佳方法。在指南实际运用中，如果CI的上、下限值代表了真实效应，而临床实际情况与之不符时，必须降低证据质量级别（即对效应估计值的把握度）。除外当效应值很大且可信区间提示效应稳健，而总样本量不大且事件数很少的情况，其他应考虑因不精确性而降低证据质量级别。作此决定时，可计算有足够检验效能的单个试验所需的病例数（定义为“最优信息样本量”，即optimal information size，OIS）。对连续型变量，我们建议用类似方法，首先考虑可信区间上、下限值，再计算OIS。系统评价（SR）所需方法略有不同。如果95%CI不包括相对危险度（RR）为1，且总事件发生数或病例数超过OIS标准，则精确性良好。如果95%CI包括了明显获益或危害（我们建议以RR值lt;0.75或gt;1.25作粗标准），即使达到OIS要求，因不精确性而降低证据质量级别较恰当。
Some statistical measures in evidence-based medicine, such as RRR, ARR and NNTwere introduced.
In this paper, we introduce meaning and purpose of confidence interval (CI) in evidence-based medicine, For example, RRR ,ARR ,NNT. It s referance for user and doer of EBM in China.
To show that a new drug is better than, as good as, or no worse than that of a known effective drug. Theoretically, it is necessary to confirm the efficacy of a treatment, but the current practice of clinical trial suggests that there exists many problems in its confirmation including the objectives of clinical investigation vary based on the fact that more and more clinical trials use active controls. Applied statistical methods have to adapt to these changes. In this paper, we illustrated some statistical issues of confirming efficacy in clinical trials, including its conditions, the determination of clinical margin, the forms of the null and alternative hypothesis and confidence intervals, the choice of endpoints and some miscellaneous considerations. We bly suggests that it is necessary to make biostatisticians and clinical trialists understand the importance of using the right statistical methods when investigating clinical trials. We also think these methods introduced in the paper may provide some help in trial design and evaluation.
Etiological and prognostic studies always directly reported effect size with its 95% confidence interval, hence, data transformation was needed when performing meta-analysis based on these studies. Using the data of risk ratio, hazard ratio, odds ratio and 95% confidence interval as an example, this paper introduces the process of using RevMan 5.3 software to convert data and perform meta-analysis.
Most statistical data in observational studies is expressed as the effect value and its 95% confidence interval (95% CI), which do not correspond to the data format used for traditional meta-analyses, so special data conversion is to be needed when Review Manager software is applied to do a meta-analysis for this type of data, which will make the operation complicated and cumbersome. In addition, Stata software is such a powerful statistical software that can be used directly to conduct a meta-analysis with the effect value and its 95% CI. Therefore, it is an indispensable statistical tool for meta-analysis in observational studies. And this study will give a brief introduction how to use Stata software to conduct a meta-analysis with effect value and its 95% CI based on the published meta-analysis data.