PsychStatsWiki

本页面只读。您可以查看源文件，但不能更改它。如果您觉得这是系统错误，请联系管理员。

====方差的分解====


**1.方差的可分解性：**
  * 指总的离差平方和可以分解为几个不同来源的平方和。


**2.总方差的组成：**
  * 组间平方和（分子）：处理间方差
  * 组内平方和（分母）：不是由于处理引起的方差
  * {{:组内的分解.png?300 |}}
  * 
  * 可简化为：
  * {{:组内的分解_简_.png?150 |}}
  * 
  * 公式的理解：总平方和=组内平方和+组间平方和

====Decomposition of variance====

**1.Decomposability of variance:**
  *The total sum of squares of deviations can be decomposed into the sum of squares by different sources.

**2.Composition of total variance:**
  *Inter group sum of squares (numerator): variance between treatments.
  *Within group sum of squares (denominator): variance not caused by processing.
  * {{:组内的分解.png?300 |}}
  * 
  * Which can be simplified as
  * {{:组内的分解_简_.png?150 |}}
  * 
  * Understanding of the formula: The total sum of squares = The sum of squares within groups + The sum of squares between groups