ensemble average

Based on examples, introduces significance of difference test method between sample average and ensemble average in cases of totality submission normal distribution ( variance known of unknown big, small sample) or totality non-normal distribution in education experiment;

结合实例，介绍了教育实验中总体服从正态分布（方差已知或未知，大、小样本）或总体非正态几种情形下样本平均数与总体平均数间差异显著性的检验方法；

Using microscopic sdIBM-2 formalism and procedure of canonical ensemble average, finite-temperature specific heat of nuclei is calculated. The existence of peaks in the specific heat shows the occurrence of phase transition of thermal excitation mode.

应用微观sdIBM-2形式体系、正则系综平均法和鞍点近似，能计算出核在有限温度下的比热，比热峰的存在表明核发生了热激发相变。

The gradient estimation in the proposed algorithm is improved by using the weighted time average instead of the instantaneous value to approximate the ensemble average.

在本文中，所提算法的梯度估计用加权时间平均值来代替瞬时值去近似总体均值。这样能较好地消除误差通道辨识环节和主动控制环节之间的相互影响，从而提高系统的总体性能。