📚 The Distribution of Sums and Averages of Samples | 样本总和与样本均值的分布
In statistical inference, we often draw random samples from a population to estimate unknown parameters. Two fundamental statistics are the sample sum and the sample mean. Because samples vary, these statistics are random variables with their own probability distributions, known as sampling distributions. Understanding the expected value, variance, and shape of these distributions—particularly through the Central Limit Theorem—is essential for constructing confidence intervals and conducting hypothesis tests in IB Mathematics.
在统计推断中，我们经常从总体中抽取随机样本以估计未知参数。样本总和与样本均值是两个基本统计量。由于样本会变化，这些统计量本身就是具有概率分布的随机变量，即抽样分布。理解这些分布的期望值、方差和形态（尤其是通过中心极限定理）对于在IB数学中构建置信区间和进行假设检验至关重要。
1. Sample Statistics as Random Variables | 样本统计量作为随机变量
When we take a random sample of size n from a population, each observation Xi is a random variable. The sample mean X̄ = (X1 + X2 + ... + Xn)/n and the sample sum T = X1 + X2 + ... + Xn are functions of these random variables. Therefore, X̄ and T are also random variables, each with its own distribution called a sampling distribution. The properties of these distributions depend on the population distribution, the sample size, and the sampling method.
当我们从总体中抽取容量为 n 的随机样本时，每个观测值 Xi 都是一个随机变量。样本均值 X̄ = (X1 + X2 + ... + Xn)/n 和样本总和 T = X1 + X2 + ... + Xn 都是这些随机变量的函数。因此，X̄ 和 T 也是随机变量，各自具有抽样分布。这些分布的性质取决于总体分布、样本容量以及抽样方法。
2. Expected Value of the Sample Mean | 样本均值的期望
If we draw a random sample from a population with mean μ, the expected value of the sample mean X̄ is equal to the population mean. This property holds regardless of the population distribution or the sample size, provided the sample is unbiased.
如果我们从均值为 μ 的总体中抽取随机样本，那么样本均值 X̄ 的期望值等于总体均值。无论总体分布或样本容量如何，只要样本是无偏的，这一性质都成立。
E(X̄) = μ
This result tells us that the sample mean is an unbiased estimator of μ. Over many repeated samples, the average of the sample means will centre exactly on the true population mean.
这个结果表明样本均值是 μ 的无偏估计量。在多次重复抽样中，样本均值的平均值将正好集中在真实总体均值周围。
3. Expected Value of the Sample Sum | 样本总和的期望
The sample sum T is simply n times the sample mean. Using the linearity of expectation, we can derive its expected value directly.
样本总和 T 就是样本均值的 n 倍。利用期望的线性性质，可以直接推出它的期望值。
E(T) = E(nX̄) = nE(X̄) = nμ
Thus, if the population mean is μ, the expected total of n independent observations is nμ. If we know the expected value per trial, scaling up to a sum is straightforward.
因此，若总体均值为 μ，n 个独立观测值的期望总和就是 nμ。如果已知单次试验的期望值，按比例推算总和便很简单。
4. Variance of the Sample Mean | 样本均值的方差
When sampling is independent and either the population is infinite or the sample is drawn with replacement, the variance of the sample mean is the population variance divided by the sample size. This shows that larger samples yield more precise estimates.
当抽样是独立的，且总体无限或有放回地抽取样本时，样本均值的方差等于总体方差除以样本容量。这表明样本越大，估计越精确。
Var(X̄) = σ² / n
The standard deviation of the sample mean, σ/√n, is called the standard error of the mean. It shrinks as n grows, reflecting the increased stability of X̄.
样本均值的标准差 σ/√n 称为均值的标准误差。它随着 n 的增加而缩小，反映 X̄ 稳定性的提高。
5. Variance of the Sample Sum | 样本总和的方差
The sample sum T is the sum of n independent identically distributed random variables. Its variance is therefore n times the individual variance, provided the observations are independent.
样本总和 T 是 n 个独立同分布随机变量之和。因此，若各观测值独立，其方差就是单个方差的 n 倍。
Var(T) = nσ²
While the mean becomes less variable as n increases, the sum becomes more variable. The standard deviation of the sum is √(n)σ. This is important when we need to make probability statements about totals rather than averages.
随着 n 增加，均值变异度减小，而总和的变异度却增大。总和的标准差为 √(n)σ。当我们需要对总量而非均值作概率陈述时，这非常重要。
6. Distribution of the Sample Mean from a Normal Population | 正态总体下样本均值的分布
If the population itself is normally distributed, the sample mean has an exact normal distribution for any sample size n. This is a consequence of the reproductive property of the normal distribution: linear combinations of independent normal variables remain normal.
若总体本身服从正态分布，那么对于任意样本容量 n，样本均值都恰好服从正态分布。这是正态分布可加性的结果：独立正态变量的线性组合仍为正态。
If X ~ N(μ, σ²), then X̄ ~ N(μ, σ²/n)
Similarly, the sample sum T from a normal population follows a normal distribution: T ~ N(nμ, nσ²). This exact result allows us to compute probabilities for X̄ and T using z‑scores when σ is known, without needing a large sample.
类似地，来自正态总体的样本总和 T 也服从正态分布：T ~ N(nμ, nσ²)。这一精确结果允许我们在已知 σ 时，通过 z 分数计算 X̄ 和 T 的概率，且不需要大样本。
7. The Central Limit Theorem | 中心极限定理
The Central Limit Theorem (CLT) is one of the most powerful tools in statistics. It states that for independent and identically distributed random variables with finite mean μ and variance σ², the sampling distribution of the sample mean approaches a normal distribution as the sample size increases, regardless of the shape of the population distribution.
中心极限定理（CLT）是统计学中最强大的工具之一。它指出，对于具有有限均值 μ 和方差 σ² 的独立同分布随机变量，当样本容量增大时，样本均值的抽样分布趋近于正态分布，无论总体分布形状如何。
X̄ ≈ N(μ, σ²/n) for large n (usually n ≥ 30)
This means we can use normal probability calculations for sample means even when the population is skewed or discrete, as long as the sample size is sufficiently large. The CLT is the foundation of many inference procedures.
这意味着，即便总体是偏态的或离散的，只要样本容量足够大，我们仍然可以对样本均值使用正态概率计算。中心极限定理是众多推断方法的基础。
8. Distribution of the Sample Sum via CLT | 通过中心极限定理看样本总和的分布
Because T = nX&# ality control, inventory management, and other applications where total quantities matter.
由于 T = nX̄，中心极限定理同样意味着当 n 较大时，样本总和也近似服从正态分布。总和的近似分布常用于质量控制、库存管理以及其他关注总量的应用场景。
T ≈ N(nμ, nσ²) for large n (n ≥ 30 typically)
When applying the normal approximation to sums, the same sample size guidelines apply. The approximation improves as n gets larger. Note that if the population is normal, both the mean and sum are exactly normal for any n.
在对总和应用正态近似时，遵循同样的样本容量准则。n 越大，近似效果越好。需要注意的是，如果总体本身是正态的，那么无论 n 多大，均值和总和都精确服从正态分布。
9. Conditions for Normal Approximation | 正态近似的条件
To safely use the normal distribution for X̄ or T, we must check a few conditions: (1) The data must come from a random sample or a randomized experiment. (2) Observations must be independent. In practice, independence is reasonable if the sample size is less than 10% of the population when sampling without replacement. (3) The sample size must be large enough; the rule of thumb n ≥ 30 works for most distributions, but strongly skewed populations may require larger n.
要安全地对 X̄ 或 T 使用正态分布，我们必须检查几个条件：(1) 数据须来自随机样本或随机化实验。(2) 观测值必须独立。实际中，若为无放回抽样，当样本容量小于总体的 10% 时可认为独立。(3) 样本容量必须足够大；经验法则 n ≥ 30 适用于大多数分布，但高度偏态的总体可能需要更大的 n。
Additionally, if the population standard deviation σ is unknown (the usual case), we substitute the sample standard deviation s and use the t‑distribution for means; however
Published by TutorHao | IB Mathematics Revision Series | aleveler.com
更多咨询请联系16621398022（同微信）
或截图后用「扫一扫 → 相册」选择本图