📚 Further Statistics FS Module Ultimate Revision Pack | 进阶统计 FS 模块终极备考资料包
Welcome to your comprehensive revision pack for the Further Statistics (FS) module in A-Level Further Mathematics. This guide consolidates key concepts, essential formulas, common pitfalls, and exam strategies to help you master the FS syllabus. Whether you’re tackling FS1 or FS2, this resource will support your independent study and last-minute revision.
欢迎使用进阶数学中进阶统计（FS）模块的综合备考资料。本指南汇集核心概念、必背公式、常见误区与应试策略，助你全面掌握 FS 考纲。无论你正在学习 FS1 还是 FS2，这份资料都能为你的自主复习与考前冲刺提供有力支持。
1. Discrete Random Variables & Expectation Algebra | 离散随机变量与期望代数
Discrete random variables (DRVs) form the foundation of Further Statistics. You must be able to construct a probability distribution table and compute expected value E(X) and variance Var(X) efficiently. Core identities are shown below.
离散随机变量是进阶统计的基础。你必须熟练掌握构建概率分布表并高效计算期望 E(X) 与方差 Var(X)。核心恒等式如下。
E(X) = Σ x·P(X=x) Var(X) = E(X²) − [E(X)]²
Expectation algebra simplifies linear combinations: for constants a and b, E(aX + b) = aE(X) + b and Var(aX + b) = a²Var(X). For independent variables X and Y, E(X±Y)=E(X)±E(Y) and Var(X±Y)=Var(X)+Var(Y). These rules underpin many FS problems.
期望代数可简化线性组合：对于常数 a 与 b，有 E(aX + b) = aE(X) + b，Var(aX + b) = a²Var(X)。对于独立变量 X 与 Y，E(X±Y)=E(X)±E(Y) 且 Var(X±Y)=Var(X)+Var(Y)。这些法则贯穿 FS 诸多题型。
Always check whether variables are independent before combining variances. Common mistake: adding variances for dependent data.
在合并方差前务必检查变量是否独立。常见错误：对非独立数据直接相加方差。
2. Poisson Distribution & Approximations | 泊松分布及其近似
The Poisson distribution models the number of events occurring in a fixed interval of time or space, assuming events happen independently at a constant average rate λ. The probability function is:
泊松分布用于描述固定时间或空间区间内随机事件发生的次数，假设事件独立且平均发生率 λ 恒定。其概率函数为：
X ~ Po(λ): P(X=x) = e⁻λ λˣ / x! for x = 0,1,2,…
Mean and variance both equal λ. The Poisson distribution is often used to approximate a binomial B(n, p) when n is large and p is small, with λ = np (commonly np < 10).
均值与方差都等于 λ。泊松分布常用于近似二项分布 B(n, p)，当 n 很大而 p 很小，取 λ = np（通常 np < 10）。
If X~Po(λ₁) and Y~Po(λ₂) are independent, then X + Y ~ Po(λ₁ + λ₂). This additive property is very useful in combining independent Poisson processes.
若 X~Po(λ₁) 与 Y~Po(λ₂) 独立，则 X+Y ~ Po(λ₁+λ₂)。这个可加性在合并独立泊松过程时非常有用。
3. Geometric & Negative Binomial Distributions | 几何分布与负二项分布
The geometric distribution Geom(p) models the number of trials until the first success, assuming independent trials with constant success probability p.
几何分布 Geom(p) 模拟直到第一次成功所需的试验次数，假设每次试验独立且成功概率 p 恒定。
P(X=x) = (1−p)ˣ⁻¹ p, x = 1,2,3,…
E(X) = 1/p, Var(X) = (1−p)/p². The geometric distribution is memoryless.
E(X)=1/p，Var(X)=(1−p)/p²。几何分布具有无记忆性。
The negative binomial NB(r, p) counts the trials needed to achieve the r-th success. It generalises the geometric distribution (r=1).
负二项分布 NB(r, p) 计算实现第 r 次成功所需的试验次数，它是几何分布的推广（r=1）。
P(X=x) = C(x−1, r−1)·p^r·(1−p)^(x−r), x = r, r+1,…
E(X)=r/p, Var(X)=r(1−p)/p². Be careful with the definition of X: some specifications start counting failures, but the ‘trials until r successes’ version is standard in most FS modules.
E(X)=r/p，Var(X)=r(1−p)/p²。注意 X 的定义：部分考纲计失败次数，但 ‘直至 r 次成功所需的试验次数’ 为多数 FS 模块的标准定义。
4. Hypothesis Testing for Discrete Distributions | 离散分布的假设检验
Hypothesis tests for binomial, Poisson and geometric distributions follow the same structure: state null H₀ and alternative H₁, choose significance level α, find the critical region or calculate the p‑value.
针对二项、泊松和几何分布的假设检验遵循相同结构：陈述零假设 H₀ 与备择假设 H₁，选取显著性水平 α，找出临界区域或计算 p 值。
Because the test statistic is discrete, the actual significance level is often slightly below α. You must compute probabilities such as P(X ≥ c | H₀) or P(X ≤ c | H₀) accurately.
由于检验统计量是离散的，实际显著性水平常略低于 α。你必须准确计算概率，如 P(X ≥ c | H₀) 或 P(X ≤ c | H₀)。
For a one‑tailed test, compare the test statistic with the critical value; for a two‑tailed test, split α/2 on each tail. Always write a conclusion in context: ‘Reject H₀, there is sufficient evidence…’ or ‘Do not reject H₀…’.
对于单尾检验，将检验统计量与临界值比较；双尾检验则在两侧各取 α/2。结论务必结合情境表述：’拒绝 H₀，有充分证据…’ 或 ‘不拒绝 H₀…’。
Common mistake: misidentifying the direction of the test. Read the problem carefully to decide whether it is lower‑tail, upper‑tail, or two‑tailed.
常见错误：误判检验方向。仔细读题，区分下尾、上尾或双尾检验。
5. Chi-Squared Tests (Goodness of Fit & Association) | 卡方检验（拟合优度与独立性）
Chi‑squared tests assess whether observed frequencies differ significantly from expected frequencies. The test statistic is:
卡方检验用于评估观察频数与期望频数之间是否存在显著差异。检验统计量为：
χ² = Σ (O − E)² / E
For goodness of fit, degrees of freedom ν = number of categories − 1 − number of estimated parameters. For a contingency table (test of association), ν = (rows − 1)(columns − 1).
拟合优度检验中，自由度 ν = 类别数 − 1 − 估计参数的个数。对于列联表（独立性检验），ν = (行数−1)(列数−1)。
Key assumption: all expected frequencies should be at least 5. If necessary, combine adjacent categories to meet this condition.
关键假设：所有期望频数至少为 5。如不满足，需合并相邻类别。
Compare the calculated χ² with the critical value from tables. If χ² > critical value, reject H₀ (at the given significance level). A significant result indicates the model does not fit or variables are associated.
将计算得到的 χ² 与查表临界值比较。若 χ² > 临界值，拒绝 H₀（在给定显著性水平下）。显著结果说明模型拟合不佳或变量间存在关联。
6. Continuous Random Variables & PDF/CDF | 连续随机变量与概率密度函数/累积分布函数
A continuous random variable X is described by its probability density function f(x), which satisfies f(x) ≥ 0 and ∫ f(x) dx = 1 over the sample space. The cumulative distribution function is F(x)=P(X ≤ x)=∫₋∞ˣ f(t) dt.
连续随机变量 X 由概率密度函数 f(x) 描述，满足 f(x) ≥ 0 且在整个样本空间上积分 ∫ f(x) dx = 1。累积分布函数为 F(x)=P(X ≤ x)=∫₋∞ˣ f(t) dt。
Probabilities are computed as P(a < X < b) = ∫ₐᵇ f(x) dx = F(b) − F(a). The median m satisfies F(m)=0.5; the mode maximises f(x).
概率计算：P(a < X < b) = ∫ₐᵇ f(x) dx = F(b) − F(a)。中位数 m 满足 F(m)=0.5；众数使 f(x) 最大。
Expected value: E(X) = ∫ x f(x) dx; E(g(X)) = ∫ g(x) f(x) dx. Variance is Var(X) = E(X²) − [E(X)]².
期望值：E(X) = ∫ x f(x) dx；E(g(X)) = ∫ g(x) f(x) dx。方差为 Var(X) = E(X²) − [E(X)]²。
When the PDF is piecewise, integrate over appropriate intervals. A common error is forgetting to normalise the function or misidentifying the domain.
当 PDF 为分段函数时，应在相应区间上积分。常见错误包括忘记归一化或误判定义域。
7. Combinations of Random Variables | 随机变量的组合
For any random variables X, Y and constants a, b: E(aX ± bY) = aE(X) ± bE(Y). If X and Y are independent, Var(aX ± bY) = a²Var(X) + b²Var(Y). Note the variance of a difference also adds the variances.
对于任意随机变量 X, Y 及常数 a, b：E(aX ± bY) = aE(X) ± bE(Y)。若 X 与 Y 独立，则 Var(aX ± bY) = a²Var(X) + b²Var(Y)。注意差值的方差同样为方差之和。
Sum of independent normal variables: if X~N(μ₁,σ₁²) and Y~N(μ₂,σ₂²) are independent, then X+Y ~ N(μ₁+μ₂, σ₁²+σ₂²) and X−Y ~ N(μ₁−μ₂, σ₁²+σ₂²).
独立正态变量之和：若 X~N(μ₁,σ₁²) 与 Y~N(μ₂,σ₂²) 独立，则 X+Y ~ N(μ₁+μ₂, σ₁²+σ₂²) 且 X−Y ~ N(μ₁−μ₂, σ₁²+σ₂²)。
For a random sample of size n, the sample mean X̄ has E(X̄)=μ and Var(X̄)=σ²/n. If the population is normal, X̄ is exactly normal; otherwise, the Central Limit Theorem ensures approximate normality for large n.
对于容量为 n 的随机样本，样本均值 X̄ 满足 E(X̄)=μ, Var(X̄)=σ²/n。若总体为正态，X̄ 亦为正态；否则由中心极限定理保证当 n 较大时近似正态。
8. Estimation & Confidence Intervals | 估计与置信区间
A point estimator θ̂ is unbiased if E(θ̂) = θ. The sample mean is an unbiased estimator of the population mean μ; the sample variance s² = Σ(x−x̄)²/(n−1) is unbiased for σ².
点估计量 θ̂ 若无偏，则满足 E(θ̂) = θ。样本均值是总体均值 μ 的无偏估计量；样本方差 s² = Σ(x−x̄)²/(n−1) 是 σ² 的无偏估计。
A 95% confidence interval for the mean μ (variance known) is:
方差已知时，均值 μ 的 95% 置信区间为：
x̄ ± z₀.₀₂₅ · σ/√n
where z₀.₀₂₅ = 1.96. If σ is unknown but n is large, replace σ with the sample standard deviation s. For small samples from a normal population with unknown variance, use the t‑distribution.
其中 z₀.₀₂₅ = 1.96。若 σ 未知但 n 较大，可用样本标准差 s 替代 σ。对于正态总体方差未知的小样本，应使用 t 分布。
Confidence intervals for a proportion p are constructed similarly: p̂ ± z · √[p̂(1−p̂)/n], provided n is large enough.
比例 p 的置信区间类似构建：p̂ ± z · √[p̂(1−p̂)/n]，前提是 n 足够大。
9. Probability Generating Functions (PGFs) | 概率生成函数
For a non‑negative integer valued discrete random variable X, the probability generating function is Gₓ(t) = E(t^X) = Σ tˣ P(X=x). PGFs uniquely define the distribution.
对于非负整数值离散随机变量 X，其概率生成函数定义为 Gₓ(t) = E(t^X) = Σ tˣ P(X=x)。PGF 可唯一确定分布。
Key properties: Gₓ(1) = 1; E(X) = G’ₓ(1); Var(X) = G”ₓ(1) + G’ₓ(1) − [G’ₓ(1)]².
关键性质：Gₓ(1)=1；E(X)=G’ₓ(1)；Var(X)=G”ₓ(1)+G’ₓ(1)−[G’ₓ(1)]²。
Standard PGFs:
标准 PGF：
- Poisson(λ): G(t) = e^(λ
Published by TutorHao | 进阶数学 Revision Series | aleveler.com
更多咨询请联系16621398022（同微信）
屏轩国际教育cambridge primary/secondary checkpoint, cat4, ukiset,ukcat,igcse,alevel,PAT,STEP,MAT, ibdp,ap,ssat,sat,sat2课程辅导，国外大学本科硕士研究生博士课程论文辅导