6.4 Variance of a Discrete Random Variable

离散随机变量的方差

6.4.1 核心概念总结 / Core Concepts Summary

方差的定义:

方差 \(\operatorname{Var}(X)\) 定义为随机变量 \(X\) 与其期望值 \(\mathrm{E}(X)\) 的平均平方偏差:

\[\operatorname{Var}(X) = \mathrm{E}[(X - \mathrm{E}(X))^2]\]

方差的另一种等价计算公式为:

\[\operatorname{Var}(X) = \mathrm{E}(X^2) - [\mathrm{E}(X)]^2\]

方差的基本性质:

Basic Properties of Variance:

  1. 非负性:对于任何随机变量,方差总是非负的。Non-negativity: For any random variable, variance is always non-negative.
  2. 零方差:当且仅当随机变量为常数时,方差为零。Zero variance: Variance is zero if and only if the random variable is constant.
  3. 散布程度:方差越大,随机变量的分布越分散。Degree of dispersion: The larger the variance, the more dispersed the distribution of the random variable.
  4. 单位相关:方差的单位是随机变量单位的平方。Unit dependence: The unit of variance is the square of the unit of the random variable.

6.4.2 计算方法总结 / Calculation Methods Summary

方差的两种计算方法:

Two Methods for Calculating Variance:

  1. 定义法:使用公式 \(\operatorname{Var}(X) = \sum (x - \mu)^2 P(X = x)\),其中 \(\mu = \mathrm{E}(X)\)。Definition method: Use the formula \(\operatorname{Var}(X) = \sum (x - \mu)^2 P(X = x)\), where \(\mu = \mathrm{E}(X)\).
  2. 简便法:使用公式 \(\operatorname{Var}(X) = \mathrm{E}(X^2) - [\mathrm{E}(X)]^2\)。Convenient method: Use the formula \(\operatorname{Var}(X) = \mathrm{E}(X^2) - [\mathrm{E}(X)]^2\).

骰子方差计算示例 / Dice Variance Calculation Example:

对于公平六面骰子,两种方法都得到相同结果 \(\frac{35}{12}\)。

\[\mathrm{E}(X^2) = \frac{1}{6}(1 + 4 + 9 + 16 + 25 + 36) = \frac{91}{6}\]

\[\operatorname{Var}(X) = \frac{91}{6} - \left(\frac{7}{2}\right)^2 = \frac{91}{6} - \frac{49}{4} = \frac{35}{12}\]

6.4.3 与其他统计量的关系 / Relationship with Other Statistics

标准差 / Standard Deviation:

标准差是方差的平方根:

\[\sigma = \sqrt{\operatorname{Var}(X)}\]

标准差与随机变量具有相同的单位,便于解释。

The standard deviation is the square root of the variance and has the same unit as the random variable, making it easier to interpret.

与期望值的关系 / Relationship with Expected Value:

方差可以表示为二阶原点矩与一阶原点矩平方的差值。

Variance can be expressed as the difference between the second-order origin moment and the square of the first-order origin moment.

重要区别 / Important Distinction:

期望值 \(\mathrm{E}(X)\) 表示随机变量的中心位置,方差 \(\operatorname{Var}(X)\) 表示随机变量围绕中心位置的散布程度。

The expected value \(\mathrm{E}(X)\) represents the central location of the random variable, while the variance \(\operatorname{Var}(X)\) represents the degree of dispersion around the central location.

6.4.4 应用要点总结 / Application Key Points

计算技巧 / Calculation Tips:

  • 优先使用简便计算公式 \(\operatorname{Var}(X) = \mathrm{E}(X^2) - [\mathrm{E}(X)]^2\)。
    Use the convenient formula \(\operatorname{Var}(X) = \mathrm{E}(X^2) - [\mathrm{E}(X)]^2\) first.
  • 对于对称分布,方差的计算可能更简单。
    For symmetric distributions, variance calculation may be simpler.
  • 注意单位换算,方差的单位是原变量单位的平方。
    Pay attention to unit conversion; variance has units that are the square of the original variable's units.
  • 标准差通常比方差更容易解释和比较。
    Standard deviation is usually easier to interpret and compare than variance.

常见错误提醒 / Common Mistakes Reminder:

  • 不要混淆方差和标准差的概念和计算。
    Do not confuse the concepts and calculations of variance and standard deviation.
  • 计算 \(\mathrm{E}(X^2)\) 时要小心,不要忘记平方。
    When calculating \(\mathrm{E}(X^2)\), be careful not to forget the squaring.
  • 方差总是非负的,如果计算结果为负则表明计算错误。
    Variance is always non-negative; if the calculation result is negative, it indicates a calculation error.

6.4.5 思维导图总结 / Mind Map Summary

离散随机变量方差知识体系:

核心概念 计算方法 性质特点 应用领域
• 方差定义
• 平均平方偏差
• 散布程度度量
• 定义公式
• 简便公式
• 二阶矩方法
• 逐步计算
• 非负性
• 零方差条件
• 单位相关性
• 与期望值关系
• 风险评估
• 质量控制
• 实验设计
• 统计推断