📚 A-Level Maths Example Responses: MA04 Unit S2 | A-Level 数学示例精讲：MA04 单元 S2 知识点
This article provides a detailed revision guide for A-Level Mathematics Unit S2 (often part of the Statistics 2 module), covering key topics such as the binomial distribution, Poisson distribution, continuous random variables, normal approximations, hypothesis testing, and confidence intervals. Each section includes worked example responses that illustrate the step‑by‑step reasoning required to achieve full marks in the examination. The bilingual format is designed to reinforce understanding in both English and Chinese, ensuring that learners can articulate mathematical arguments clearly.
本文为 A-Level 数学 S2 单元（通常属于统计学第二部分）提供详尽的知识点精讲，涵盖二项分布、泊松分布、连续随机变量、正态近似、假设检验以及置信区间等核心内容。每个小节均配有示例讲解，展示考试中获得满分所需的逐步推理过程。中英双语的设计旨在帮助学习者透彻理解概念，并能清晰表达数学论证。
1. Binomial Distribution Essentials | 二项分布要点
A binomial distribution is used when there are a fixed number of independent trials, each with exactly two possible outcomes (success/failure), and the probability of success remains constant. If a random variable X follows a binomial distribution, we write X ~ B(n, p), where n is the number of trials and p is the probability of success. The probability mass function is given by P(X = r) = (nCr) × pʳ × (1 − p)ⁿ⁻ʳ. You must be able to calculate probabilities both from the formula and using statistical tables.
当进行固定次数的独立试验，每次试验只有两种可能结果（成功/失败），且成功概率保持不变时，应使用二项分布。若随机变量 X 服从二项分布，记作 X ~ B(n, p)，其中 n 是试验次数，p 是成功概率。概率质量函数为 P(X = r) = (nCr) × pʳ × (1 − p)ⁿ⁻ʳ。学生必须既能使用公式计算概率，又能查阅统计表。
Example response: A fair die is rolled 10 times. Find the probability that exactly three rolls show a ‘6’. Let X ~ B(10, 1/6). Then P(X = 3) = 10C3 × (1/6)³ × (5/6)⁷. Using a calculator, 10C3 = 120, so P(X = 3) = 120 × (1/6)³ × (5/6)⁷ ≈ 0.155. The working must clearly state the distribution and the formula used.
示例讲解： 一枚均匀的骰子投掷 10 次，求恰好出现 3 次“6”的概率。设 X ~ B(10, 1/6)，则 P(X = 3) = 10C3 × (1/6)³ × (5/6)⁷。使用计算器得到 10C3 = 120，因此 P(X = 3) = 120 × (1/6)³ × (5/6)⁷ ≈ 0.155。解题过程必须明确写出分布以及所使用的公式。
2. Poisson Distribution & Its Conditions | 泊松分布及其使用条件
A Poisson distribution models the number of events occurring in a fixed interval of time or space, provided events happen independently and at a constant average rate. If X ~ Po(λ), where λ is the mean (and also the variance), then P(X = r) = (e⁻λ × λʳ) / r!. The Poisson distribution is particularly useful for rare events or when n is large and p is small in a binomial setting (as an approximation). Always verify that events occur singly and randomly.
泊松分布用于模拟在固定时间或空间间隔内发生的事件次数，条件是事件独立发生且具有恒定的平均速率。若 X ~ Po(λ)，其中 λ 是均值（同时也是方差），则 P(X = r) = (e⁻λ × λʳ) / r!。泊松分布特别适用于稀有事件，或在二项分布中当 n 很大而 p 很小时作为近似。使用前务必验证事件是否独立且随机发生。
Example response: A call centre receives an average of 4 calls per minute. Find the probability of receiving exactly 2 calls in a given minute. Let X ~ Po(4). P(X = 2) = e⁻⁴ × 4² / 2! = (0.0183) × 16 / 2 ≈ 0.1465. State that calls occur independently and at a constant average rate to justify the model.
示例讲解： 一个呼叫中心平均每分钟接到 4 个电话。求在某一分钟内恰好接到 2 个电话的概率。设 X ~ Po(4)，P(X = 2) = e⁻⁴ × 4² / 2! = (0.0183) × 16 / 2 ≈ 0.1465。需要说明电话独立到达且平均速率恒定，以证明模型的正确性。
3. Using Binomial and Poisson Tables | 使用二项与泊松分布表
In the examination, you will be expected to read cumulative probabilities directly from the provided statistical tables. For a binomial distribution, the tables typically give P(X ≤ r) for various n, p. You must then manipulate these to find P(X ≥ r) = 1 − P(X ≤ r − 1) or P(X = r) = P(X ≤ r) − P(X ≤ r − 1). For a Poisson distribution, tables give P(X ≤ r) for selected λ values. Always state which table value you are using and show the subtraction step clearly.
在考试中，你需要能够直接从提供的统计表中读取累积概率。对于二项分布，表格通常给出不同 n 和 p 下的 P(X ≤ r)。然后你需要进行变换来求得 P(X ≥ r) = 1 − P(X ≤ r − 1) 或 P(X = r) = P(X ≤ r) − P(X ≤ r − 1)。对于泊松分布，表格给出所选 λ 值下的 P(X ≤ r)。务必要说明使用了哪个表格值，并清晰展示减法步骤。
Example response: Using tables for X ~ B(20, 0.4), find P(X ≥ 8). Tables give cumulative probabilities. P(X ≥ 8) = 1 − P(X ≤ 7). Look up P(X ≤ 7) = 0.4159 (from table). Hence P(X ≥ 8) = 1 − 0.4159 = 0.5841. Never subtract from 1 without referencing the cumulative probability obtained from the table.
示例讲解： 对于 X ~ B(20, 0.4)，使用表格求 P(X ≥ 8)。表格给出累积概率，P(X ≥ 8) = 1 − P(X ≤ 7)。查表得 P(X ≤ 7) = 0.4159，因此 P(X ≥ 8) = 1 − 0.4159 = 0.5841。一定要先写出查得的累积概率，再用 1 减去，不能遗漏步骤。
4. Normal Approximations to Binomial | 二项分布的正态近似
When n is large and p is not too close to 0 or 1, a binomial distribution can be approximated by a normal distribution with mean μ = np and variance σ² = np(1 − p). A continuity correction must be applied because a discrete distribution is being approximated by a continuous one. For example, to approximate P(X = a), use P(a − 0.5 < X < a + 0.5) under the normal curve. Examiners look specifically for the continuity correction statement and the standardisation to Z‑scores.
当 n 很大且 p 不太接近 0 或 1 时，二项分布可以用均值为 μ = np、方差为 σ² = np(1 − p) 的正态分布来近似。因为是用连续分布近似离散分布，必须进行连续性校正。例如，要近似 P(X = a)，应使用正态曲线下 P(a − 0.5 < X < a + 0.5)。阅卷人会特别关注连续性校正的说明以及标准化为 Z 值的步骤。
X ~ B(n, p) ≈ N(np, np(1 − p))
Example response: Approximate P(X ≤ 55) for X ~ B(100, 0.6). Mean = 60, variance = 24. With continuity correction, P(X ≤ 55) ≈ P(Y < 55.5), where Y ~ N(60, 24). Standardise: Z = (55.5 − 60)/√24 ≈ −0.919. Then look up Φ(−0.92) ≈ 0.1788 from normal tables. Conclude: P(X ≤ 55) ≈ 0.179.
示例讲解： 对于 X ~ B(100, 0.6)，近似计算 P(X ≤ 55)。均值为 60，方差为 24。进行连续性校正，P(X ≤ 55) ≈ P(Y < 55.5)，其中 Y ~ N(60, 24)。标准化：Z = (55.5 − 60)/√24 ≈ −0.919。查正态分布表得 Φ(−0.92) ≈ 0.1788。结论：P(X ≤ 55) ≈ 0.179。
5. Poisson Approximation to Binomial | 二项分布的泊松近似
When n is large and p is very small (typically n > 50 and np < 5), the binomial distribution can be approximated by a Poisson distribution with λ = np. This approximation simplifies calculations significantly. The quality of the approximation depends on both n and p; remember to state the condition np < 5 clearly before using it. The approximation works because the binomial tends to the Poisson when n → ∞ and np remains fixed.
当 n 很大且 p 非常小（通常 n > 50 且 np < 5）时，二项分布可用泊松分布近似，其中 λ = np。这种近似极大简化了计算。近似的质量取决于 n 和 p；使用前务必明确说明 np < 5 的条件。该近似之所以成立，是因为当 n → ∞ 且 np 保持不变时，二项分布趋向于泊松分布。
Example response: A factory produces electronic chips with a 0.2% defect rate. 2000 chips are tested. Find the probability of finding at most 2 defectives. Let X ~ B(2000, 0.002). Since np = 4 < 5, approximate X ~ Po(4). P(X ≤ 2) = P(X = 0) + P(X = 1) + P(X = 2) = e⁻⁴ × (1 + 4 + 8) = e⁻⁴ × 13 ≈ 0.0183 × 13 = 0.2379. Always verify np < 5 before applying the approximation.
示例讲解： 一家工厂生产电子芯片，次品率为 0.2%。测试 2000 个芯片，求发现至多 2 个次品的概率。设 X ~ B(2000, 0.002)。由于 np = 4 < 5，近似为 X ~ Po(4)。P(X ≤ 2) = P(X = 0) + P(X = 1) + P(X = 2) = e⁻⁴ × (1 + 4 + 8) = e⁻⁴ × 13 ≈ 0.0183 × 13 = 0.2379。使用近似前务必确认 np < 5。
6. Continuous Random Variables & PDFs | 连续随机变量与概率密度函数
A continuous random variable is described by a probability density function (pdf), f(x), which satisfies f(x) ≥ 0 for all x and the total area under the curve equals 1. Probabilities are found by integration: P(a < X < b) = ∫ₐᵇ f(x) dx. Do not confuse the pdf with the cumulative distribution function (cdf), F(x) = P(X ≤ x) = ∫ from −∞ to x f(t) dt. The median m is found by solving F(m) = 0.5.
连续随机变量通过概率密度函数 f(x) 来描述，该函数满足 f(x) ≥ 0 且曲线下总面积为 1。概率通过积分求得：P(a < X < b) = ∫ₐᵇ f(x) dx。不要将概率密度函数与累积分布函数 F(x) = P(X ≤ x) = ∫ 从 −∞ 到 x f(t) dt 混淆。中位数 m 通过求解 F(m) = 0.5 得到。
P(a < X < b) = ∫ₐᵇ f(x) dx and ∫∞ f(x) dx = 1
Example response: A random variable X has pdf f(x) = k(3 − x) for 0 ≤ x ≤ 3, and 0 otherwise. Find k and P(X > 1). First, ∫₀³ k(3 − x) dx = 1 ⇒ k[3x − x²/2]₀³ = k(9 − 4.5) = 4.5k = 1, so k = 2/9. Then P(X > 1) = ∫₁³ (2/9)(3 − x) dx = (2/9)[3x − x²/2]₁³ = (2/9)(4.5 − 2.5) = 4/9.
示例讲解： 已知随机变量 X 的概率密度函数为 f(x) = k(3 − x)，0 ≤ x ≤ 3，其他区域为 0。求 k 和 P(X > 1)。首先，∫₀³ k(3 − x) dx = 1 ⇒ k[3x − x²/2]₀³ = k(9 − 4.5) = 4.5k = 1，所以 k = 2/9。然后 P(X > 1) = ∫₁³ (2/9)(3 − x) dx = (2/9)[3x − x²/2]₁³ = (2/9)(4.5 − 2.5) = 4/9。
7. Hypothesis Testing: Key Concepts | 假设检验：核心概念
A hypothesis test is a formal procedure to assess whether sample data provide sufficient evidence against a null hypothesis H₀. In S2, tests are often one‑tailed or two‑tailed, with a fixed significance level α (commonly 5%). The critical region is the set of values for which H₀ is rejected. You must define the test statistic, state its distribution under H₀, find critical values from tables, and compare the observed test statistic to the critical region. Never accept H₀; only ‘do not reject’.
假设检验是一种正式程序，用于评估样本数据是否提供了足够的证据反对零假设 H₀。在 S2 中，检验通常是单尾或双尾的，并设定固定的显著性水平 α（通常为 5%）。拒绝域是导致拒绝 H₀ 的一组值。你必须定义检验统计量，说明其在 H₀ 下的分布，从表格中查找临界值，并将观测到的检验统计量与拒绝域进行比较。永远不能说“接受 H₀”，只能说“不拒绝 H₀”。
Example response: Test whether a coin is biased towards heads using 20 tosses that gave 15 heads. H₀: p = 0.5, H₁: p > 0.5 (one‑tailed). Test statistic X = number of heads ~ B(20, 0.5) under H₀. Using 5% significance, find c such that P(X ≥ c) ≤ 0.05. From tables, P(X ≥ 15) = 0.0207, P(X ≥ 14) = 0.0577, so critical region is X ≥ 15. Observed 15 lies in critical region → reject H₀. Evidence suggests bias towards heads.
示例讲解： 检验一枚硬币是否偏向正面，投掷 20 次得到 15 次正面。H₀: p = 0.5, H₁: p > 0.5（单尾）。检验统计量 X = 正面次数，在 H₀ 下 X ~ B(20, 0.5)。在 5% 显著性水平下，求 c 使得 P(X ≥ c) ≤ 0.05。查表得 P(X ≥ 15) = 0.0207，P(X ≥ 14) = 0.0577，因此拒绝域为 X ≥ 15。观测值 15 落在拒绝域内 → 拒绝 H₀。有证据表明硬币偏向正面。
8. Type I and Type II Errors | 第一类错误与第二类错误
A Type I error occurs when the null hypothesis is rejected when it is actually true. The probability of a Type I error is exactly the significance level α. A Type II error occurs when H₀ is false but we fail to reject it; its probability is denoted β. Understanding these errors is critical when evaluating the power of a test (power = 1 − β). In exam questions, you may be asked to calculate the probability of a Type II error for a given alternative value.
第一类错误发生在零假设为真时却拒绝了它。第一类错误的概率恰好等于显著性水平 α。第二类错误发生在零假设为假时却未能拒绝它；其概率记作 β。理解这些错误对于评估检验的功效（功效 = 1 − β）至关重要。在考试中，可能会要求你针对给定的备择值计算第二类错误的概率。
Example response: For the coin test above with critical region X ≥ 15, find the probability of Type II error if true p = 0.7. Under H₁: p = 0.7, X ~ B(20, 0.7). Type II error means fail to reject H₀, i.e. X ≤ 14. P(Type II error) = P(X ≤ 14 | p=0.7) = 1 − P(X ≥ 15 | p=0.7) = 1 − (table value) ≈ 1 − 0.5836 = 0.4164. The power is 0.5836, meaning a 58.4% chance of correctly rejecting H₀.
示例讲解： 对于上述硬币检验，拒绝域为 X ≥ 15，若真实 p = 0.7，求第二类错误的概率。在 H₁: p = 0.7 下，X ~ B(20, 0.7)。第二类错误意味着未能拒绝 H₀，即 X ≤ 14。P(第二类错误) = P(X ≤ 14 | p=0.7) = 1 − P(X ≥ 15 | p=0.7) = 1 −（查表值）≈ 1 − 0.5836 = 0.4164。功效为 0.5836，即有 58.4% 的概率正确拒绝 H₀。
9. Continuous Distributions: Mean, Variance & Median | 连续分布：均值、方差与中位数
For a continuous random variable with pdf f(x), the expected value (mean) is E(X) = ∫ x f(x) dx over the domain, and E(X²) = ∫ x² f(x) dx. The variance is Var(X) = E(X²) − [E(X)]². The median m satisfies ∫ from lower bound to m f(x) dx = 0.5. Always set up the integrals carefully and evaluate them correctly, noting that integration by parts may be required for some pdfs.
对于具有概率密度函数 f(x) 的连续随机变量，期望值（均值）为 E(X) = ∫ x f(x) dx（在整个定义域上积分），E(X²) = ∫ x² f(x) dx。方差为 Var(X) = E(X²) − [E(X)]²。中位数 m 满足从下限到 m 的积分 ∫ f(x) dx = 0.5。务必仔细建立积分式并正确计算；注意某些 pdf 可能需要使用分部积分法。
Example response: f(x) = (3/8)x² for 0 ≤ x ≤ 2, 0 otherwise. Find mean and variance. E(X) = ∫₀² x × (3/8)x² dx = (3/8)∫₀² x³ dx = (3/8)×(16/4) = 1.5. E(X²) = ∫₀² x² × (3/8)x² dx = (3/8)∫₀² x⁴ dx = (3/8)×(32/5) = 12/5 = 2.4. Var(X) = 2.4 − (1.5)² = 2.4 − 2.25 = 0.15. Median: ∫₀ᵐ (3/8)x² dx = 0.5 ⇒ (3/8)×(m³/3) = m³/8 = 0.5 ⇒ m³ = 4 ⇒ m = ⁴√4 ≈ 1.587.
示例讲解： f(x) = (3/8)x²，0 ≤ x ≤ 2，其他区域为 0。求均值和方差。E(X) = ∫₀² x × (3/8)x² dx = (3/8)∫₀² x³ dx = (3/8)×(16/4) = 1.5。E(X²) = ∫₀² x² × (3/8)x² dx = (3/8)∫₀² x⁴ dx = (3/8)×(32/5) = 12/5 = 2.4。Var(X) = 2.4 − (1.5)² = 2.4 − 2.25 = 0.15。中位数：∫₀ᵐ (3/8)x² dx = 0.5 ⇒ (3/8)×(m³/3) = m³/8 = 0.5 ⇒ m³ = 4 ⇒ m = ⁴√4 ≈ 1.587。
10. Confidence Intervals for a Population Mean | 总体均值的置信区间
When the population variance σ² is known, a 95% confidence interval for the population mean μ based on a sample mean x̄ of size n is given by x̄ ± z₀.₀₂₅ × (σ/√n), where z₀.₀₂₅ = 1.96. If σ² is unknown and the sample is large, you may use the sample standard deviation s as an estimate, but the interval is then approximate. In S2, the emphasis is on interpretation: we are 95% confident that the interval contains the true mean μ.
当总体方差 σ² 已知时，根据样本均值 x̄ 和样本量 n，总体均值 μ 的 95% 置信区间为 x̄ ± z₀.₀₂₅ × (σ/√n)，其中 z₀.₀₂₅ = 1.96。如果 σ² 未知且样本量很大，可以使用样本标准差 s 作为估计值，但此时区间是近似的。在 S2 中，重点在于解释：我们有 95% 的信心认为该区间包含真实均值 μ。
CI = x̄ ± 1.96 × (σ/√n)
Example response: A sample of 50 bulbs has mean lifetime 1020 hours. The population standard deviation is known to be 80 hours. Construct a 95% confidence interval. Margin of error = 1.96 × (80/√50) = 1.96 × 11.314 ≈ 22.18. Interval: (1020 − 22.18, 1020 + 22.18) = (997.8, 1042.2). Interpretation: We are 95% confident that the mean lifetime of all bulbs is between 997.8 and 1042.2 hours.
示例讲解： 对 50 个灯泡进行抽样，平均寿命为 1020 小时。已知总体标准差为 80 小时。构建 95% 置信区间。误差幅度 = 1.96 × (80/√50) = 1.96 × 11.314 ≈ 22.18。区间为 (1020 − 22.18, 1020 + 22.18) = (997.8, 1042.2)。解释：我们有 95% 的信心认为所有灯泡的真实平均寿命介于 997.8 小时和 1042.2 小时之间。
Published by TutorHao | A-Level Mathematics 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