📚 AQA A2 Maths with Statistics: Essential Topic Review | AQA 数学：A2 统计知识点精讲
This article provides a thorough, bilingual revision guide for the AQA A2 Mathematics with Statistics component. We cover discrete and continuous random variables, key probability distributions, hypothesis testing, correlation, and regression, all aligned to the AQA specification.
本文为AQA A2数学统计部分提供一份全面的中英双语复习指南。涵盖离散与连续随机变量、核心概率分布、假设检验、相关性及回归，所有内容均紧扣AQA考纲要求。
1. Discrete Random Variables | 离散随机变量
A discrete random variable takes a countable number of possible values. The probability mass function P(X = x) lists each value and its probability, where ΣP(X = x) = 1.
离散随机变量取可数个可能值。概率质量函数 P(X = x) 列出每个取值及其概率，满足总概率 ΣP(X = x) = 1。
The expected value E(X) = Σx·P(X = x) gives a measure of location, while variance Var(X) = E(X²) – [E(X)]² describes spread. E(aX + b) = aE(X) + b and Var(aX + b) = a² Var(X) hold for any constants a and b.
期望 E(X) = Σx·P(X = x) 衡量位置，方差 Var(X) = E(X²) – [E(X)]² 描述离散程度。对常数 a 和 b 有 E(aX + b) = aE(X) + b，Var(aX + b) = a² Var(X)。
2. Binomial Distribution | 二项分布
A binomial model X ~ B(n, p) applies when there are n independent trials, each with constant probability p of success. The probability of exactly r successes is P(X = r) = ⁿCᵣ pʳ (1 – p)ⁿ⁻ʳ, where ⁿCᵣ is the binomial coefficient.
二项分布 X ~ B(n, p) 适用于 n 次独立试验，每次成功概率恒为 p。恰好 r 次成功的概率为 P(X = r) = ⁿCᵣ pʳ (1 – p)ⁿ⁻ʳ。
For the binomial distribution, E(X) = np and Var(X) = np(1 – p). You must be able to use cumulative binomial tables or a calculator to find P(X ≤ x) and to work backwards in unknown probability problems.
二项分布中，E(X) = np，Var(X) = np(1–p)。必须能够利用累积二项分布表或计算器求 P(X ≤ x)，并在未知成功概率问题中反向推算。
3. Poisson Distribution | 泊松分布
The Poisson distribution X ~ Po(λ) models the number of events occurring in a fixed interval when events happen independently at a constant average rate λ. The probability function is P(X = r) = (e⁻λ λʳ) / r!.
泊松分布 X ~ Po(λ) 用于事件以恒定平均速率 λ 独立发生的固定区间内的事件计数。概率函数为 P(X = r) = (e⁻λ λʳ) / r!。
Mean and variance are both λ. The Poisson can approximate a binomial B(n, p) when n is large and p is small: λ ≈ np. Typical conditions are n > 50 and np < 5, using Poisson tables directly.
均值和方差均为 λ。当 n 大且 p 小时，泊松可近似二项分布 B(n, p)：λ ≈ np。典型条件为 n > 50 且 np < 5，可直接使用泊松分布表。
4. Continuous Random Variables | 连续随机变量
A continuous random variable has a probability density function f(x) defined over an interval. Probabilities are found by integration: P(a < X < b) = ∫ₐᵇ f(x) dx. The total area under the curve must equal 1.
连续随机变量在区间上定义概率密度函数 f(x)。概率通过积分计算：P(a < X < b) = ∫ₐᵇ f(x) dx，曲线下总面积必须为 1。
The cumulative distribution function F(x) = P(X ≤ x) = ∫₋∞ˣ f(t) dt. Expectation is E(X) = ∫ x f(x) dx and variance Var(X) = E(X²) – [E(X)]², similar to the discrete case but using integration.
累积分布函数 F(x) = ∫₋∞ˣ f(t) dt。期望 E(X) = ∫ x f(x) dx，方差 Var(X) = E(X²) – [E(X)]²，与离散情况类似但使用积分。
5. Normal Distribution | 正态分布
The normal distribution N(μ, σ²) is a symmetric bell-shaped curve defined by mean μ and variance σ². The standardised variable Z = (X – μ) / σ follows N(0, 1) and allows the use of standard normal tables.
正态分布 N(μ, σ²) 为关于均值 μ 和方差 σ² 的对称钟形曲线。标准化变量 Z = (X – μ) / σ 服从 N(0, 1)，便于使用标准正态表。
To find P(X < a), standardise to P(Z < (a – μ)/σ). For inverse problems, use given probabilities to find Z-values and then convert back to X-values. Conditions such as P(X > k) = p are solved using symmetry of the normal curve.
求 P(X < a) 时，标准化为 P(Z < (a – μ)/σ)。反向问题时，利用给定概率找到 Z 值，再转换回 X 值。求解 P(X > k) = p 之类的问题可用正态曲线的对称性。
6. Normal Approximation to the Binomial | 二项分布的正态近似
When n is large and p is not too close to 0 or 1, the distribution B(n, p) can be approximated by N(np, np(1–p)). The typical checks are np > 5 and n(1–p) > 5. A continuity correction is required because a discrete distribution is being approximated by a continuous one.
当 n 大且 p 不接近 0 或 1 时，B(n, p) 可用 N(np, np(1–p)) 近似。典型检查条件为 np > 5 且 n(1–p) > 5。由于离散分布被连续分布近似，必须做连续性校正。
For example, P(X ≤ x) is approximated by P(Y < x + 0.5) where Y ~ N(np, np(1–p)). Similarly, P(X ≥ x) becomes P(Y > x – 0.5). Applying the half-unit adjustment is essential for accuracy in exam questions.
例如，P(X ≤ x) 近似为 P(Y < x + 0.5)，其中 Y ~ N(np, np(1–p))。同理，P(X ≥ x) 变为 P(Y > x – 0.5)。正确应用 0.5 校正对考试中的精确性至关重要。
7. Hypothesis Testing: Core Concepts | 假设检验核心概念
A hypothesis test uses sample data to assess a claim about a population parameter. The null hypothesis H₀ is the default position, while the alternative hypothesis H₁ states what we suspect. The significance level α gives the probability of a Type I error – rejecting H₀ when it is true.
假设检验利用样本数据评估关于总体参数的某种断言。零假设 H₀ 是默认立场，备择假设 H₁ 陈述所怀疑的情形。显著性水平 α 给出第一类错误（H₀ 为真时被拒绝）的概率。
A Type II error occurs when a false H₀ is not rejected. The power of a test is 1 – P(Type II error). The p‑value is the probability of obtaining a test statistic at least as extreme as the observed one, assuming H₀ is true; if p‑value < α, reject H₀.
当错误的 H₀ 未被拒绝时发生第二类错误。检验功效为 1 – P(第二类错误)。p 值是在 H₀ 为真的条件下，获得至少与观测值一样极端的检验统计量的概率；若 p 值 < α，则拒绝 H₀。
| Type I error | Rejecting true H₀ (false positive) |
| Type II error | Not rejecting false H₀ (false negative) |
常见错误类型表有助于记忆。检验时需明确写出结论的上下文，并说明是否显著。
8. Hypothesis Tests for Binomial | 二项分布假设检验
When testing a population proportion p, the test statistic is the number of successes X ~ B(n, p₀) under H₀: p = p₀. For a one‑tailed test, H₁ could be p > p₀ or p < p₀; for a two‑tailed test, H₁: p ≠ p₀.
当检验总体比例 p 时，检验统计量为成功次数 X ~ B(n, p₀)，其中 H₀: p = p₀。单尾检验的 H₁ 可为 p > p₀ 或 p < p₀；双尾检验 H₁: p ≠ p₀。
The critical region is determined by finding the smallest x such that P(X ≥ x) ≤ α (upper tail) or largest x with P(X ≤ x) ≤ α (lower tail). For two‑tailed tests, halve α in each tail. Alternatively, compute the p‑value and compare with α.
临界区域由满足 P(X ≥ x) ≤ α（上尾）的最小 x 或满足 P(X ≤ x) ≤ α（下尾）的最大 x 决定。双尾检验时在每尾取 α/2。也可计算 p 值并与 α 比较。
9. Hypothesis Tests for the Mean (Normal) | 正态均值假设检验
When the population variance σ² is known and data come from a normal distribution (or large samples), the sample mean X̄ follows N(μ, σ²/n). The test statistic is Z = (X̄ – μ₀) / (σ/√n) under H₀: μ = μ₀.
当总体方差 σ² 已知且数据来自正态分布（或大样本），样本均值 X̄ ~ N(μ, σ²/n)。检验统计量 Z = (X̄ – μ₀) / (σ/√n)，零假设为 H₀: μ = μ₀。
Compare the calculated Z with critical values from N(0,1). For a two‑tailed test at 5% significance, critical values are ±1.96. When σ is unknown and must be estimated by s, the t‑distribution is used in further statistical inference, but at A2 AQA the normal test with known variance is the standard requirement.
将计算出的 Z 值与 N(0,1) 临界值比较。5% 显著性水平下双尾检验的临界值为 ±1.96。当 σ 未知而需以 s 估计时，后续统计推断会用 t 分布，但在 A2 AQA 考纲中，已知方差的正态检验是标准要求。
10. Product Moment Correlation Coefficient | 积差相关系数
The Pearson product moment correlation coefficient r measures the strength and direction of a linear relationship between two variables. Its formula uses sums of deviations: r = Sxy / √(Sxx Syy), where Sxx = Σx² – (Σx)²/n, Syy is analogous, and Sxy = Σxy – (Σx)(Σy)/n.
皮尔逊积差相关系数 r 衡量两个变量间线性关系的强度和方向。公式使用离差平方和：r = Sxy / √(Sxx Syy)，其中 Sxx = Σx² – (Σx)²/n，Syy 类似，Sxy = Σxy – (Σx)(Σy)/n。
r always lies between –1 and 1. A value near +1 indicates strong positive correlation; near –1 indicates strong negative correlation; near 0 suggests no linear correlation. AQA expects you to test H₀: ρ = 0 against ρ ≠ 0 (or one‑tailed) using the test statistic t = r √[(n – 2)/(1 – r²)] on n – 2 degrees of freedom, or compare r with critical values from tables.
r 总在 –1 与 1 之间。接近 +1 表明强正相关；接近 –1 为强负相关；接近 0 则无线性相关。AQA 要求会用检验统计量 t = r √[(n – 2)/(1 – r²)]（自由度为 n – 2）检验 H₀: ρ = 0 对 ρ ≠ 0（或单尾），或直接查临界值表比较 r。
11. Linear Regression | 线性回归
A regression line y = a + b x can be fitted to bivariate data by the method of least squares. The slope b = Sxy / Sxx and the intercept a = ȳ – b x̄, making the line pass through (x̄, ȳ). This line minimises the sum of squared vertical distances.
可用最小二乘法对双变量数据拟合回归直线 y = a + b x。斜率 b = Sxy / Sxx，截距 a = ȳ – b x̄，使直线通过点 (x̄, ȳ)。该直线使铅垂距离平方和最小。
The line is used to predict values of y from x (interpolation is safer than extrapolation). Residuals = observed y – predicted y; a residual plot showing no clear pattern supports the linear model’s appropriateness. The coefficient of determination r² indicates the proportion of variation in y explained by x.
该直线用于从 x 预测 y（内插比外推更可靠）。残差 = 观测值 y – 预测值 y；残差图若无明显模式则支持线性模型的适用性。决定系数 r² 表示 y 的变异中被 x 解释的比例。
12. Connecting Distributions and Data | 分布与数据的联系
A solid grasp of A2 Statistics comes from linking theoretical distributions with data analysis. Check whether a binomial or Poisson model is appropriate by examining context and independence. When using the normal distribution, always verify the conditions (normality or large sample size) and clearly document standardisation steps.
透彻掌握 A2 统计需要将理论分布与数据分析联系起来。通过检查背景和独立性判断二项或泊松模型是否适用。使用正态分布时，务必验证条件（正态性或大样本）并清晰记载标准化步骤。
In hypothesis tests, always state the conclusion in words, supporting it with numbers. Words like “sufficient evidence” must be linked to the significance level. Master calculator skills for binomial and normal CDF, but also know how to extract critical values manually from tables for the exam.
在假设检验中，始终用文字陈述结论，并用数字支持。“足够证据”等措辞必须与显著性水平关联。既要娴熟使用计算器求二项和正态 CDF，又要学会在考试中手动从表格查临界值。
Published by TutorHao | 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