整合分析中两种假设模型的介绍及实例分析

Comparison of two hypotheses models in meta-analysis and its sample using

整合分析(meta-analysis)是对同一主题下多个独立实验结果进行综合的统计学方法,被认为是到目前为止最好的数量综合方法。在进行整合分析时,首选应提出统计假设,根据假设的不同可将整合分析分为固定效应模型(fixedeffect model)和随机效应模型(random effect model),前者假定有相似的多个研究在同一分组里有一个共同的真实效应值,由于取样误差,导致在实际效应值的测定中各研究间存在差别;在后者中,假定各研究间有随机变量,因此,不共享一个真实效应值。介绍了两种假设模型下整合分析的计算方法,并进行了实例分析。

Meta-analysis is a statistical method to summary independent studies under the same subject. Hypothesis is the dependence of analysis. There are two hypothesis models: fixed effect size model and random effect size model. In fixed-model, it is assumed that there is a real effect size in all studies, and it is sampling error that leads to the difference among studies. In random-model, it is assumed that there is a random variable in all studies, which and sampling error are sources of the difference among studies. These tow models were introduced and real sample analysis was done.