Multivariate Behav Res. 1994 Jul 1;29(3):237-62. doi: 10.1207/s15327906mbr2903_3.
The source of an event related brain potential (ERP) is estimated from multivariate measurements of this ERP on the head under several mathematical and physical constraints on the parameters of the source model. We will discuss statistical aspects of standard methods to estimate these parameters and their confidence intervals. In addition new principled tests of the goodness of fit as well as of differences between estimated sources are proposed and compared with customary approaches in psychophysiology. Several factors which influence the statistical analysis, in particular the number of measurement leads, will be discussed.
在头部的事件相关脑电位 (ERP) 的多元测量的情况下,根据源模型参数的几个数学和物理约束,估计源的 ERP。我们将讨论标准方法来估计这些参数及其置信区间的统计方面。此外,还提出了新的拟合优度的原则性检验,以及估计源之间的差异,与心理生理学中的惯用方法进行比较。讨论了影响统计分析的几个因素,特别是测量导联的数量。