Meta分析中基于Q统计量服从卡方分布线性变换的异质性方差区间估计  

Interval Estimation for the Amount of Heterogeneity in Meta-Analysis Based on Q-Statistic Following Linear Transformation of Chi-Square Distribution

作　　者：刘金涛[1] 秦超英[1] 党红[1] 

机构地区：[1]西北工业大学理学院应用数学系,西安710072

出　　处：《中国循证医学杂志》2012年第11期1404-1406,共3页Chinese Journal of Evidence-based Medicine

摘　　要：目的探讨Meta分析中异质性方差的区间估计。方法在异质性方差区间估计BT法的基础上,采用了卡方分布的线性变换近似Q统计量的分布,提高了Q统计量的分布精度,由此获得Meta分析中异质性方差的区间估计。结果在实例计算中,原方法 Q1分布下异质性方差的可信度为95%的可信区间为(0.07,2.20),改进后方法 Q2分布下异质性方差的可信度为95%的可信区间为(0.00,1.41),缩短了可信区间的宽度。结论 Q统计量分布精度的提高能有效提高异质性方差区间估计的可信度,而且文内提出的方法还可以提高异质性方差区间估计的精度。Objective To investigate confidence interval estimation for the amount of heterogeneity in meta- analysis. Methods On the basis of BT＇s method, the approximate Q-statistic distribution following linear transformation of Chi-square was applied to improve the accuracy of Q-statistic distribution, and to obtain the confidence interval for the amount of heterogeneity in meta-analysis. Results In case, the Q1 distribution obtained 95%CI 0.07 to 2.20, while the Q2 distribution obtained 95%CI 0.00 to 1.41; The proposed method Q2 narrowed down the range of confidence interval. Conclusion On account of improving the accuracy of Q-statistic distribution, the proposed method effectively strength- ens the coverage probabilities of the confidence interval for the amount of heterogeneity. And the proposed method can also improve the precision of the confidence interval estimation for the amount of heterogeneity.

关 键 词：META分析 异质性 Q统计量 区间估计 

分 类 号：R195[医药卫生—卫生统计学]