Meta分析中关于总体效应量的区间估计

The estimation of interval for overall mean effect in Meta-analysis

在随机效应的Meta分析中,通过修正t-分布法中相应统计量分布的不精确性,得到更高精度的总体效应量的置信区间.与D-L法相比,改进的t-分布法得出的置信区间的覆盖率和精度均有所提高;与t-分布法相比,改进的t-分布法覆盖率相当,但精度有所提高.所以本文提出的方法是基于t-分布法的一种简便和有效的方法.

In the random effect of Meta-analysis, by means of improving the distributed inaccuracy of the corresponding statistics in the t-distribution approach to get a more accurate confidence interval for the overall mean effect. Compared with the D-L approach, coverage probability and accuracy of the confidence interval calculated by the improved t-distribution approach are both increased compared with the t-distribution approach, this new method has an approximated coverage probability but improved accuracy. So the method proposed in this paper is based on the t-distribution approach, and itts simple and effective.