Year 13 AQA Statistics: Complete Specification Breakdown | Year 13 AQA 统计：课程大纲全面解析

📚 Year 13 AQA Statistics: Complete Specification Breakdown | Year 13 AQA 统计：课程大纲全面解析

The Year 13 AQA Statistics specification extends the foundations laid at AS level, equipping students with the tools to model real-world randomness through a range of discrete and continuous distributions, conduct rigorous hypothesis tests, and draw meaningful conclusions from data. From the binomial and Poisson models to the chi-squared test for independence, every topic is designed to deepen statistical reasoning and prepare learners for further study in mathematics, sciences, or social sciences. This article breaks down the entire syllabus into key learning areas, providing paired English–Chinese explanations for each concept.

Year 13 AQA 统计课程大纲在 AS 阶段的基础上进一步深化，通过一系列离散与连续分布帮助学生建模现实中的随机现象，并开展严谨的假设检验，从数据中得出有意义的结论。从二项分布、泊松分布到独立性卡方检验，每一个专题都旨在强化统计推理能力，为数学、科学或社会科学方向的后续学习做好准备。本文把整个大纲拆分为核心学习模块，并以中英对照的方式对每个概念加以解析。

1. Overview of the Year 13 Curriculum | Year 13 课程大纲概览

The Year 13 AQA Statistics curriculum covers several big themes: probability distributions (binomial, Poisson, normal), continuous random variables, linear combinations of random variables, normal approximations, hypothesis testing for binomial, Poisson and the mean, correlation and regression, chi‑squared tests, and work with a large data set. Each theme builds directly on the descriptive statistics, basic probability and the normal distribution introduced in Year 12.

Year 13 AQA 统计课程包含几大核心主题：概率分布（二项、泊松、正态）、连续随机变量、随机变量的线性组合、正态近似、二项与泊松的假设检验、均值的假设检验、相关与回归、卡方检验以及大数据集应用。每一个主题都直接建立在 Year 12 描述统计、基础概率和正态分布的知识之上。

2. Advanced Probability Distributions | 高级概率分布

Binomial distribution: X ~ B(n, p), probability P(X=r) = ⁿCᵣ pʳ (1−p)ⁿ⁻ʳ. Conditions: fixed number of trials, two outcomes, constant probability, independence. Poisson distribution: X ~ Po(λ), P(X=r) = e⁻ʸ λʳ / r!. It models events occurring randomly in time or space, with mean = variance = λ. Normal distribution: X ~ N(μ, σ²), probability density function f(x) = 1/(σ√(2π)) exp(−(x−μ)²/(2σ²)). The standard normal Z ~ N(0,1) uses tables to find probabilities.

二项分布：X ~ B(n, p)，概率 P(X=r) = ⁿCᵣ pʳ (1−p)ⁿ⁻ʳ。适用条件：固定试验次数、两种结果、每次概率恒定、独立性。泊松分布：X ~ Po(λ)，P(X=r) = e⁻ʸ λʳ / r!。用于描述时间或空间中随机发生的事件，均值与方差都等于 λ。正态分布：X ~ N(μ, σ²)，概率密度函数为 f(x) = 1/(σ√(2π)) exp(−(x−μ)²/(2σ²))。标准正态 Z ~ N(0,1) 可查表求概率。

P(X=r) = ⁿCᵣ pʳ (1−p)ⁿ⁻ʳ

P(X=r) = e⁻ʸ λʳ / r!

3. Continuous Random Variables | 连续随机变量

A continuous random variable is described by a probability density function (PDF) f(x). The total area under the curve equals 1: ∫ₐᵇ f(x)dx = 1 over the domain. The cumulative distribution function (CDF) is F(x) = P(X ≤ x) = ∫ₐˣ f(t)dt. The median m satisfies F(m) = 0.5. Expectation E(X) = ∫ x f(x)dx and Var(X) = E(X²) − [E(X)]².

连续随机变量由概率密度函数（PDF）f(x) 描述。曲线下方总面积为 1：定义域上 ∫ₐᵇ f(x)dx = 1。累积分布函数（CDF）为 F(x) = P(X ≤ x) = ∫ₐˣ f(t)dt。中位数 m 满足 F(m) = 0.5。期望 E(X) = ∫ x f(x)dx，方差 Var(X) = E(X²) − [E(X)]²。

Median: F(m) = 0.5

中位数：F(m) = 0.5

4. Linear Combinations of Random Variables | 随机变量的线性组合

For random variables X and 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). Any linear combination of independent normal variables is also normally distributed. For example, if X ~ N(μ₁, σ₁²) and Y ~ N(μ₂, σ₂²) are independent, then aX + bY ~ N(aμ₁ + bμ₂, a²σ₁² + b²σ₂²).

对于随机变量 X、Y 和常数 a、b：E(aX ± bY) = aE(X) ± bE(Y)。若 X、Y 独立，则 Var(aX ± bY) = a²Var(X) + b²Var(Y)。独立正态变量的任何线性组合仍服从正态分布。例如，若 X ~ N(μ₁, σ₁²)、Y ~ N(μ₂, σ₂²) 且独立，则 aX + bY ~ N(aμ₁ + bμ₂, a²σ₁² + b²σ₂²)。

If X and Y are independent: Var(aX + bY) = a²Var(X) + b²Var(Y)

若 X 与 Y 独立：Var(aX + bY) = a²Var(X) + b²Var(Y)
The sum of independent Poissons: X₁ ~ Po(λ₁), X₂ ~ Po(λ₂) ⇒ X₁ + X₂ ~ Po(λ₁ + λ₂)

独立泊松变量之和：X₁ ~ Po(λ₁), X₂ ~ Po(λ₂) ⇒ X₁ + X₂ ~ Po(λ₁ + λ₂)

5. Normal Approximations to Binomial and Poisson | 二项和泊松的正态近似

When n is large and p is not too extreme, the binomial B(n, p) can be approximated by N(np, np(1−p)). The usual condition is np > 5 and n(1−p) > 5. For the Poisson Po(λ), when λ > 10, it can be approximated by N(λ, λ). A continuity correction must be applied: for binomial, P(X ≤ x) ≈ P(Y < x + 0.5) where Y ~ N(np, np(1−p)).

当 n 很大且 p 不过于极端时，二项分布 B(n, p) 可用 N(np, np(1−p)) 近似。常用条件是 np > 5 且 n(1−p) > 5。对于泊松分布 Po(λ)，当 λ > 10 时可用 N(λ, λ) 近似。必须使用连续性校正：对二项分布，P(X ≤ x) ≈ P(Y < x + 0.5)，其中 Y ~ N(np, np(1−p))。

Binomial approx: X ~ B(n,p) → Y ~ N(np, np(1−p))

二项近似：X ~ B(n,p) → Y ~ N(np, np(1−p))

6. Binomial and Poisson Hypothesis Testing | 二项与泊松假设检验

A hypothesis test for the parameter p in a binomial distribution or λ in a Poisson model follows the same structure: state H₀ and H₁, identify the test statistic (the observed count), find the critical region or p-value using the assumed distribution under H₀, and draw a conclusion in context. For a two‑tailed test, the significance level is split equally between the tails; the actual significance level is often calculated due to discrete boundaries.

二项分布参数 p 或泊松模型参数 λ 的假设检验遵循相同框架：陈述 H₀ 与 H₁，确定检验统计量（观测频数），利用 H₀ 假设下的分布求出临界域或 p 值，并结合背景得出结论。双尾检验时，显著性水平平均分配到两侧尾部；由于离散边界，通常需要计算实际显著性水平。

p‑value = P(observed or more extreme | H₀ true)

p 值 = P(观测值及更极端 | H₀ 为真)

One‑tailed test: H₁: p > 0.3, critical region upper tail.

单尾检验：H₁: p > 0.3，临界域在上尾。

Two‑tailed test: H₁: p ≠ 0.3, significance level α/2 each tail.

双尾检验：H₁: p ≠ 0.3，每尾显著性水平 α/2。

7. Hypothesis Tests for the Mean | 均值假设检验

When testing a population mean μ, the test statistic depends on whether the population variance σ² is known. For known σ², use the z‑test: Z = (x̄ − μ₀) / (σ/√n) ~ N(0,1). For unknown σ² with a large sample (n ≥ 30), the sample standard deviation s can replace σ, and the same normal approximation applies. The conclusion is stated in terms of evidence against H₀.

检验总体均值 μ 时，检验统计量取决于总体方差 σ² 是否已知。若 σ² 已知，使用 z 检验：Z = (x̄ − μ₀) / (σ/√n) ~ N(0,1)。若 σ² 未知而样本量很大（n ≥ 30），可用样本标准差 s 代替 σ，仍采用相同的正态近似方法。结论需说明是否有足够证据拒绝 H₀。

Test statistic: Z = (x̄ − μ₀) / (σ/√n)

检验统计量：Z = (x̄ − μ₀) / (σ/√n)

One‑tailed: reject H₀ if Z > zᵅ (or Z < −zᵅ)

单尾：若 Z > zᵅ（或 Z < −zᵅ）拒绝 H₀
Two‑tailed: reject H₀ if |Z| > zᵅ⁄₂

双尾：若 |Z| > zᵅ⁄₂ 拒绝 H₀

8. Correlation and Regression Analysis | 相关与回归分析

Pearson’s product moment correlation coefficient r measures linear association. Spearman’s rank correlation coefficient rₛ is used for monotonic relationships or ranked data. Hypothesis tests for ρ = 0 use critical values from tables. The least‑squares regression line of y on x is y = a + bx, where b = Sxy/Sxx and a = ȳ − bx̄. Residuals (observed − predicted) can be plotted to check model fit.

皮尔逊积矩相关系数 r 度量线性关联。斯皮尔曼秩相关系数 rₛ 用于单调关系或等级数据。检验 ρ = 0 时需要查表获得临界值。y 对 x 的最小二乘回归线为 y = a + bx，其中 b = Sxy/Sxx，a = ȳ − bx̄。残差（观测值 − 预测值）可用于诊断模型拟合效果。

Regression slope: b = Sxy / Sxx

回归斜率：b = Sxy / Sxx

Interpretation: a significant r indicates evidence of linear correlation; the regression line should only be used for prediction within the range of the data.

解读：显著的 r 表明存在线性相关的证据；回归线只应用于数据范围内进行预测。

9. Chi‑Squared Tests | 卡方检验

Chi‑squared tests assess whether observed frequencies differ significantly from expected frequencies. Goodness‑of‑fit test: H₀ – the data follow a specified distribution. Test statistic: χ² = Σ (Oᵢ − Eᵢ)² / Eᵢ, with degrees of freedom ν = number of classes − number of estimated parameters − 1. Test for independence in a contingency table: expected frequencies are calculated as (row total × column total) / grand total; ν = (rows − 1)(columns − 1).

卡方检验用于评估观测频数与期望频数是否存在显著差异。拟合优度检验：H₀ – 数据来自某一指定分布。检验统计量：χ² = Σ (Oᵢ − Eᵢ)² / Eᵢ，自由度 ν = 类别数 − 估计参数个数 − 1。列联表独立性检验：期望频数 = (行合计 × 列合计) / 总计；ν = (行数 − 1)(列数 − 1)。

χ² = Σ (O − E)² / E

卡方统计量：χ² = Σ (O − E)² / E

Goodness‑of‑fit: dice fairness, genetic ratios.

拟合优度：骰子公平性、遗传比例。

Independence: association between gender and subject choice.

独立性：性别与科目选择的关联。

10. Working with the Large Data Set | 处理大数据集

AQA provides a pre‑released large data set (for example, traffic or weather records). Students must be able to clean data by identifying missing values, outliers, and errors, calculate summary statistics, and produce graphical representations. They should also interpret patterns in context, recognise limitations of sampling methods, and discuss how findings can be generalised to the wider population.

AQA 提供预发布的大数据集（例如交通或气象记录）。学生需要能够清洗数据，识别缺失值、异常值和错误，计算汇总统计量并绘制图表。同时还需结合背景解读模式，认识抽样方法的局限性，并讨论如何将结论推广到更广泛的总体。

Identify outliers using IQR or z‑scores.

用四分位距或 z 分数识别异常值。
Understand the sampling method used (e.g. random, stratified) and potential bias.

理解所用抽样方法（如随机、分层）及潜在偏差。

Published by TutorHao | Statistics Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）

Year 13 AQA Statistics: Complete Specification Breakdown | Year 13 AQA 统计：课程大纲全面解析