📚 OxfordAQA International AS Mathematics 9660 Statistics: Key Topic Revision | 牛津AQA国际AS数学9660统计知识点精讲
This article provides a structured walk‑through of the essential statistical topics covered in the OxfordAQA International AS Mathematics 9660 specification. It is designed to help you consolidate core concepts, from data summarisation and probability to discrete distributions and hypothesis testing. Each section pairs concise English explanations with parallel Chinese translations, ensuring clarity for bilingual learners.
本文系统梳理了牛津AQA国际AS数学9660大纲中的统计核心知识点，帮助你在数据概括、概率、离散分布和假设检验等方面打下坚实基础。每个小节均提供简洁的中英双语讲解，便于双语学习者准确掌握概念。
1. Summarising Data: Measures of Central Tendency | 数据概括：中心趋势度量
The mean, median and mode are the three principal measures of central tendency. For a data set x₁, x₂, …, xₙ, the sample mean is x̄ = (Σx)/n. The median is the middle value when data are ordered, and the mode is the most frequent value. In a symmetric distribution these three measures coincide, but in skewed data the median is often more representative than the mean.
均值、中位数和众数是三种主要的中心趋势度量。对于数据集 x₁, x₂, …, xₙ，样本均值 x̄ = (Σx)/n。中位数是将数据排序后位于中间的值，众数则是出现频率最高的值。在对称分布中这三者重合，但在偏态数据中，中位数通常比均值更具代表性。
For grouped frequency data, the mean is estimated using midpoints: x̄ ≈ Σ(f·m) / Σf, where m is the class midpoint and f is the frequency. The median class is found by cumulative frequency, and the modal class is the class with the highest frequency density.
对于分组频数数据，均值用组中点估算：x̄ ≈ Σ(f·m) / Σf，其中 m 为组中点，f 为频数。中位数通过累计频数确定所在组，众数组则为频数密度最高的组。
2. Summarising Data: Measures of Spread | 数据概括：离散程度度量
Spread is quantified by range, interquartile range (IQR), variance and standard deviation. The range is simply the maximum minus the minimum, but it is highly sensitive to outliers. The IQR, defined as Q₃ – Q₁, describes the middle 50% of data and is robust to extreme values.
离散程度用极差、四分位距（IQR）、方差和标准差来量化。极差简单等于最大值减最小值，但对异常值非常敏感。IQR 定义为 Q₃ – Q₁，涵盖中间50%的数据，对极端值不敏感。
The sample variance s² measures average squared deviation from the mean: s² = Σ(x – x̄)² / (n – 1). The divisor (n – 1) corrects bias when estimating a population variance. The standard deviation s = √s² shares the same units as the data and is commonly used alongside the mean.
样本方差 s² 衡量数据与均值偏差平方的平均：s² = Σ(x – x̄)² / (n – 1)。分母 (n – 1) 在校正总体方差估计时的偏差。标准差 s = √s² 与原数据单位相同，常与均值配合使用。
Key formula: s = √[ Σ(x – x̄)² / (n – 1) ]
3. Data Representation: Stem‑and‑Leaf Diagrams | 数据表示：茎叶图
A stem‑and‑leaf diagram preserves raw data while showing its shape. Each value is split into a stem (all digits except the last) and a leaf (the final digit). The stems are listed vertically in ascending order, and leaves are written horizontally in order beside each stem. A key must be provided — for example, 5 | 3 means 5.3 or 53, depending on units.
茎叶图既能显示数据分布形态，又保留了原始数值。每个数据分为茎（除最后一位外的全部数字）和叶（最后一位数字）。茎按升序纵向排列，叶子在对应茎旁横向有序书写。必须提供图例，例如 5|3 根据单位表示 5.3 或 53。
To compare two related data sets, a back‑to‑back stem‑and‑leaf plot places leaves for one group to the left and for the other to the right of a common stem. This makes it easy to compare centres and spreads simultaneously.
比较两组相关数据时，可用背靠背茎叶图，一组叶子放于茎的左侧，另一组放在右侧，共用同一茎，便于同时比较中心位置和离散程度。
4. Data Representation: Box Plots and Outliers | 数据表示：盒形图和异常值
A box plot (box‑and‑whisker diagram) displays the five‑number summary: minimum, Q₁, median, Q₃, and maximum. The box spans the IQR, and whiskers extend to the most extreme non‑outlying values. Outliers are marked individually, often as asterisks or dots.
盒形图（箱线图）展示五数概括：最小值、Q₁、中位数、Q₃ 和最大值。盒子覆盖 IQR 范围，须线延伸至最远的非异常值。异常值通常用星号或圆点单独标出。
One common rule for identifying outliers uses the IQR: a value is an outlier if it is below Q₁ – 1.5 × IQR or above Q₃ + 1.5 × IQR. Box plots are highly effective for comparing distributions across different categories.
识别异常值的常用规则基于 IQR：低于 Q₁ – 1.5×IQR 或高于 Q₃ + 1.5×IQR 的值为异常值。盒形图在比较不同类别的分布时非常有效。
5. Probability: Basic Concepts and Rules | 概率：基本概念和法则
Probability P(A) measures the chance of an event A, satisfying 0 ≤ P(A) ≤ 1. For a sample space S, P(S) = 1. The complement of A is A’ with P(A’) = 1 – P(A). The addition rule for mutually exclusive events A and B is P(A ∪ B) = P(A) + P(B). If events can overlap, the general formula becomes P(A ∪ B) = P(A) + P(B) – P(A ∩ B).
概率 P(A) 度量事件 A 发生的可能性，满足 0 ≤ P(A) ≤ 1。样本空间 S 有 P(S)=1。A 的互补事件 A’ 满足 P(A’) = 1 – P(A)。互斥事件 A 与 B 的加法法则为 P(A ∪ B) = P(A) + P(B)；若事件可重叠，则通用公式为 P(A ∪ B) = P(A) + P(B) – P(A ∩ B)。
Conditional probability P(A|B) is the probability of A given that B has occurred. It is calculated as P(A ∩ B) / P(B), provided P(B) > 0. Multiplication rule follows: P(A ∩ B) = P(A|B) × P(B) = P(B|A) × P(A). Independence is defined by P(A ∩ B) = P(A) × P(B) or equivalently P(A|B) = P(A).
条件概率 P(A|B) 是在 B 已发生的条件下 A 的概率，计算公式为 P(A ∩ B) / P(B)，前提是 P(B) > 0。乘法法则为 P(A ∩ B) = P(A|B)×P(B) = P(B|A)×P(A)。独立性定义为 P(A ∩ B)=P(A)×P(B)，等价于 P(A|B)=P(A)。
6. Discrete Random Variables: Expectation and Variance | 离散随机变量：期望和方差
A discrete random variable X takes values x with probabilities P(X=x). The probability distribution must sum to 1: Σ P(X=x) = 1. The expected value E(X) is the long‑run average: E(X) = Σ [x · P(x)]. It is also called the mean μ.
离散随机变量 X 以概率 P(X=x) 取值 x。概率分布必须满足 Σ P(X=x)=1。期望值 E(X) 是长期平均值：E(X) = Σ [x · P(x)]，也称为均值 μ。
The variance Var(X) measures spread: Var(X) = E[(X − μ)²] = Σ (x − μ)² P(x). A useful computation formula is Var(X) = E(X²) – [E(X)]². The standard deviation is σ = √Var(X). For a linear function aX + b, E(aX + b) = a E(X) + b and Var(aX + b) = a² Var(X).
方差 Var(X) 衡量离散程度：Var(X) = E[(X−μ)²] = Σ (x−μ)² P(x)。实用计算公式为 Var(X) = E(X²) – [E(X)]²。标准差 σ = √Var(X)。对于线性函数 aX + b，有 E(aX+b) = aE(X)+b，Var(aX+b) = a² Var(X)。
7. The Binomial Distribution | 二项分布
When a fixed number n of independent trials each have the same probability of success p, the number of successes X follows a binomial distribution: X ~ B(n, p). The probability of exactly r successes is P(X = r) = ⁿCᵣ pʳ (1 − p)ⁿ⁻ʳ, where ⁿCᵣ = n! / [r!(n−r)!].
当进行固定次数 n 的独立试验，每次试验成功的概率 p 相同，成功次数 X 服从二项分布：X ~ B(n, p)。恰好获得 r 次成功的概率为 P(X=r) = ⁿCᵣ pʳ (1−p)ⁿ⁻ʳ，其中 ⁿCᵣ = n! / [r!(n−r)!]。
The mean and variance of a binomial variable are E(X) = np and Var(X) = np(1 − p). This distribution is appropriate when trials are independent and the probability of success remains constant, for example in repeated coin tosses or quality‑control inspections.
二项变量的期望与方差为 E(X) = np，Var(X) = np(1−p)。该分布适用于试验独立且成功概率保持不变的情形，如重复抛硬币或质检抽样。
To find cumulative probabilities P(X ≤ r) use tables or sums of individual probabilities. The distribution is symmetric when p = 0.5 and skewed otherwise, becoming more symmetric as n increases.
计算累积概率 P(X ≤ r) 可查表或加总各概率值。当 p=0.5 时分布对称，否则呈偏态；随着 n 增大，偏态逐渐减弱。
8. The Normal Distribution | 正态分布
A continuous random variable X that follows a normal distribution with mean μ and variance σ² is written X ~ N(μ, σ²). Its probability density function is bell‑shaped and symmetric about μ. The total area under the curve equals 1, and probabilities correspond to areas in specified intervals.
服从均值为 μ、方差为 σ² 的正态分布的连续随机变量 X 记作 X ~ N(μ, σ²)。其概率密度函数呈钟形，关于 μ 对称。曲线下总面积为1，概率对应特定区间内的面积。
To standardise, transform to Z = (X − μ) / σ, giving Z ~ N(0, 1). Standard normal tables provide cumulative probabilities Φ(z) = P(Z ≤ z). For a problem given X, find P(X < a) = Φ((a−μ)/σ). When working backwards from a given probability, use inverse normal tables to find the corresponding z‑score and then solve for x.
进行标准化：Z = (X−μ)/σ，则 Z ~ N(0,1)。标准正态表给出累积概率 Φ(z) = P(Z ≤ z)。对 X 求解时，P(X < a)=Φ((a−μ)/σ)。若给定概率反求 x，先用逆正态表找到对应 z 值，再反解 x。
Standardisation: Z = (X − μ) / σ
9. Sampling and the Sample Mean | 抽样与样本均值
When random samples of size n are drawn from a population with mean μ and variance σ², the sample mean X̄ is a random variable. Its expected value is μ, making X̄ an unbiased estimator of the population mean. The variance of X̄ is σ²/n, so the standard deviation of the sample mean (standard error) is σ/√n.
从均值为 μ、方差为 σ² 的总体中抽取容量为 n 的随机样本，样本均值 X̄ 是一个随机变量。其期望值为 μ，故 X̄ 是总体均值的无偏估计量。X̄ 的方差为 σ²/n，样本均值的标准差（标准误）为 σ/√n。
If the population is normally distributed, then X̄ ~ N(μ, σ²/n) exactly. For non‑normal populations, the Central Limit Theorem states that, for sufficiently large n (typically n ≥ 30), the sampling distribution of X̄ is approximately normal. This allows normal‑based inference about means even when raw data are skewed.
若总体服从正态分布，则 X̄ 精确服从 N(μ, σ²/n)。对于非正态总体，中心极限定理指出，当 n 足够大（通常 n ≥ 30）时，X̄ 的抽样分布近似正态。即使原始数据偏态，也可应用基于正态的均值推断。
10. Hypothesis Testing for a Proportion (Binomial Test) | 比例假设检验（二项检验）
A hypothesis test evaluates a claim about a population parameter. For a binomial proportion p, the null hypothesis H₀ usually specifies p = p₀, while the alternative H₁ may be one‑tailed (p < p₀ or p > p₀) or two‑tailed (p ≠ p₀). The test statistic is the observed number of successes X, and binomial probabilities are calculated assuming H₀ is true.
假设检验用于评估关于总体参数的主张。对于二项比例 p，原假设 H₀ 通常设定 p = p₀，备择假设 H₁ 可以是单侧（p < p₀ 或 p > p₀）或双侧（p ≠ p₀）。检验统计量为观测成功次数 X，并基于 H₀ 为真计算二项概率。
The p‑value is the probability of obtaining a result at least as extreme as the observed value, under H₀. If the p‑value is less than the significance level α (often 0.05), H₀ is rejected in favour of H₁. For a two‑tailed test, double the smaller tail probability or use specific critical regions.
p 值是在 H₀ 下，得到至少与观测值同样极端结果的概率。若 p 值小于显著性水平 α（常用 0.05），则拒绝 H₀ 而接受 H₁。双侧检验时，将较小尾部的概率加倍，或使用特定临界域。
Critical regions can be determined from binomial tables: for a lower‑tail test at α = 0.05, find the largest r such that P(X ≤ r) ≤ 0.05; the critical region is X ≤ r. Always state a conclusion in the context of the original claim.
可利用二项分布表确定临界域：例如对 α=0.05 的下尾检验，找出满足 P(X≤r)≤0.05 的最大 r，则临界域为 X≤r。结论务必结合原问题背景表述。
11. Correlation and Linear Regression | 相关与线性回归
The product‑moment correlation coefficient r measures the strength and direction of a linear relationship between two variables x and y. Its range is −1 ≤ r ≤ 1, with r = 1 indicating perfect positive linear correlation and r = −1 perfect negative correlation. A value near 0 suggests little or no linear association.
积差相关系数 r 衡量两个变量 x 与 y 之间线性关系的强度和方向。其取值范围为 −1 ≤ r ≤ 1，r = 1 表示完全正线性相关，r = −1 表示完全负线性相关。接近 0 则表明几乎无线性关联。
The least‑squares regression line of y on x has equation y = a + bx, where b = Sxy / Sxx and a = ȳ − b x̄. Here Sxy = Σ(x−x̄)(y−ȳ) and Sxx = Σ(x−x̄)². This line minimises the sum of squared vertical deviations, and can be used to predict y for a given x, but extrapolation beyond the data range is unreliable.
y 对 x 的最小二乘回归直线方程为 y = a + bx，其中 b = Sxy / Sxx，a = ȳ − b x̄。Sxy = Σ(x−x̄)(y−ȳ)，Sxx = Σ(x−x̄)²。该直线使垂直偏差平方和最小，可用于对给定 x 预测 y，但不建议外推超出数据范围。
b = Sxy / Sxx, a = ȳ − b x̄
12. Statistical Enquiry Cycle and Data Collection | 统计探究循环与数据收集
A sound statistical investigation follows a cycle: formulating a question, planning data collection, gathering data, analysing and interpreting results, and communicating conclusions. Understanding sampling methods (random, stratified, systematic, quota) and potential sources of bias is vital for the planning stage.
良好的统计探究遵循循环：提出问题、制定数据收集计划、收集数据、分析和解释结果并传达结论。理解随机抽样、分层抽样、系统抽样、配额抽样等方法以及潜在偏误来源，对计划阶段至关重要。
Data can be classified as categorical (nominal or ordinal) or numerical (discrete or continuous). The choice of summary statistics and graphical displays depends on data type and the question of interest. In the OxfordAQA AS exam, you are expected to interpret given data, critique sampling designs and suggest improvements.
数据可分为类别型（名义或有序）或数值型（离散或连续）。统计摘要和图表的选择取决于数据类型和研究问题。在牛津AQA AS考试中，你需要能解释给定数据、评价抽样方案并提出改进建议。
Published by TutorHao | Statistics 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