A-Level OCR Maths: Statistics Key Points | A-Level OCR 数学：统计考点精讲

📚 A-Level OCR Maths: Statistics Key Points | A-Level OCR 数学：统计考点精讲

Statistics in OCR A-Level Mathematics equips students with essential tools for collecting, analysing, and interpreting data, forming the backbone of informed decision-making. This revision guide consolidates the key topics — from sampling methods and data representation to probability, discrete and continuous distributions, and hypothesis testing. We focus on the precise specification requirements, ensuring you can confidently tackle exam questions with both conceptual clarity and computational accuracy.

OCR A-Level 数学中的统计模块为学生提供了收集、分析和解读数据的基本工具，是理性决策的基础。这份考点精讲梳理了核心主题——从抽样方法、数据表达到概率、离散与连续分布以及假设检验。我们紧扣考纲要求，帮助你以清晰的概念理解和准确的计算能力自信应对各类考题。

1. Statistical Sampling | 统计抽样

A population is the entire set of items or individuals of interest, while a sample is a subset selected to represent it. A census observes every member but is often impractical due to cost, time, or accessibility. Simple random sampling gives every member an equal chance of selection, removing bias; however, a sampling frame is required. Systematic sampling selects every k-th item from an ordered list, which can introduce periodicity bias if the list has a hidden pattern. Stratified sampling divides the population into groups (strata) and samples proportionally from each, ensuring representativeness across key characteristics. Quota sampling, widely used in market research, relies on interviewers filling pre-set quotas without a sampling frame, making it cheap and quick but prone to interviewer bias. Understanding sampling methods is vital because biased samples lead to invalid inferences.

总体是所有感兴趣的个体或项目的集合，样本则是用于代表总体的子集。普查观察每个成员，但常因成本、时间或可达性而不切实际。简单随机抽样让每个成员被抽中的概率相等，可消除偏差，但需要抽样框。系统抽样从有序列表中每隔固定间隔抽取一项，若列表存在隐藏周期则可能引入周期性偏差。分层抽样将总体分为不同层，然后在各层内按比例抽取，确保关键特征的充分代表性。配额抽样常用于市场调查，调查员无需抽样框，只需按预设配额选择对象，成本低、速度快，但容易受到调查员偏差干扰。理解抽样方法至关重要，因为不具代表性的样本会导致无效推断。

2. Data Presentation & Interpretation | 数据呈现与解读

Data must be summarised visually and numerically to reveal patterns. Histograms display grouped continuous data, where frequency is proportional to the area of each bar, and the vertical axis shows frequency density (frequency / class width). A cumulative frequency curve shows the running total of frequencies; its steepness indicates density. Box plots (box-and-whisker diagrams) display the minimum, lower quartile Q₁, median Q₂, upper quartile Q₃, and maximum, providing a clear picture of central tendency and spread. Outliers are commonly defined as values lying more than 1.5 × interquartile range (IQR = Q₃ – Q₁) below Q₁ or above Q₃, and they should be investigated rather than automatically removed. Scatter graphs help visualise the relationship between two variables, but in OCR Statistics we focus on single-variable data representation.

数据需要通过可视化和数值方式总结，以揭示规律。直方图用于展示分组的连续数据，每个条形的面积与频率成正比，纵轴为频率密度（频率 ÷ 组距）。累积频率曲线显示频率的累计总和，斜率陡峭处对应高频率的区域。箱形图（盒须图）展示最小值、下四分位数 Q₁、中位数 Q₂、上四分位数 Q₃ 和最大值，清晰体现了中心与离散特征。离群值通常定义为小于 Q₁ – 1.5 × IQR 或大于 Q₃ + 1.5 × IQR（其中 IQR = Q₃ – Q₁）的数值，遇离群值应仔细考察，不可盲目删除。散点图有助于观察两个变量间的关系，但 OCR 统计侧重于单变量数据的呈现。

3. Measures of Central Tendency & Spread | 集中趋势与离散程度度量

The three common measures of central tendency are the mean, median and mode. For raw data, the sample mean x̄ = Σx / n. The median is the middle value when data are ordered, unaffected by extreme values, while the mode is the most frequent value. Spread is measured by the variance and standard deviation. For a population, variance σ² = Σ(x − μ)² / N; for a sample, s² = Σ(x − x̄)² / (n − 1), and the standard deviation is the square root of variance. The interquartile range IQR = Q₃ − Q₁ is robust against outliers. When comparing data sets, always cite both a measure of location and a measure of spread; for skewed distributions, median and IQR are preferable, while for symmetric distributions, mean and standard deviation are more informative.

常用的集中趋势度量有平均数、中位数和众数。对于原始数据，样本均值 x̄ = Σx / n。中位数是排序后居于中间位置的数值，不受极端值影响；众数则是出现频率最高的值。离散程度用方差与标准差衡量。总体方差 σ² = Σ(x − μ)² / N；样本方差 s² = Σ(x − x̄)² / (n − 1)，标准差为方差的平方根。四分位距 IQR = Q₃ − Q₁ 对离群值稳健。比较数据集时，务必同时提供位置度量和离散度量；偏态分布宜用中位数和 IQR，对称分布则用均值和标准差更加合适。

4. Probability Basics | 概率基础

Probability quantifies uncertainty on a scale from 0 (impossible) to 1 (certain). Two events A and B are mutually exclusive if they cannot occur together, so P(A ∩ B) = 0 and P(A ∪ B) = P(A) + P(B). They are independent if the occurrence of one does not affect the probability of the other, so P(A ∩ B) = P(A) × P(B). Many exam questions involve applying these rules to tables or tree diagrams. The complementary event A’ satisfies P(A’) = 1 − P(A). Use Venn diagrams to visualise unions, intersections and complements, especially when solving problems involving three events.

概率用 0（不可能）到 1（必然）之间的数值来衡量不确定性。如果两个事件 A 与 B 互斥（不能同时发生），则 P(A ∩ B) = 0 且 P(A ∪ B) = P(A) + P(B)。若两者独立，即一个事件的发生不影响另一个的概率，则 P(A ∩ B) = P(A) × P(B)。许多试题需要将这些规则应用于表格或树状图。对立事件 A’ 满足 P(A’) = 1 − P(A)。维恩图可直观呈现交集、并集与补集，处理涉及三个事件的问题时尤为有用。

5. Conditional Probability & Venn Diagrams | 条件概率与维恩图

Conditional probability, denoted P(A | B), is the probability of A occurring given that B has occurred, and is defined as P(A | B) = P(A ∩ B) / P(B) provided P(B) > 0. Tree diagrams are powerful tools for sequential events, where probabilities along branches are multiplied for intersections and summed for unions. The total probability law states that P(A) = P(A | B)P(B) + P(A | B’)P(B’). In OCR exams, you may need to use a two-way table or a Venn diagram to identify conditional or joint probabilities. Always check whether events are independent: if P(A | B) = P(A), then A and B are independent.

条件概率 P(A | B) 表示在事件 B 已发生的条件下 A 发生的概率，定义为 P(A ∩ B) / P(B)（要求 P(B) > 0）。树状图是处理顺序事件的利器，沿分支概率相乘得交集概率，不同分支概率相加得并集概率。全概率公式为 P(A) = P(A | B)P(B) + P(A | B’)P(B’)。OCR 考试中，可能需要利用双向表格或维恩图确定条件概率或联合概率。检验独立性时，若 P(A | B) = P(A)，则可断定 A 与 B 独立。

6. Discrete Random Variables | 离散随机变量

A discrete random variable X takes a finite or countable set of values with associated probabilities. The probability distribution is specified by a table or function such that Σ P(X = x) = 1. The expected value E(X) = μ = Σ x · P(X = x) represents the long-run average. The variance Var(X) = σ² = E(X²) − [E(X)]², where E(X²) = Σ x² · P(X = x). Linear transformations follow E(aX + b) = a E(X) + b and Var(aX + b) = a² Var(X). Understanding these core formulas enables you to answer questions about games of chance, discrete cost models and expected profit.

离散随机变量 X 取有限个或可数个值，各值对应一定的概率。概率分布以表格或函数形式给出，必须满足 Σ P(X = x) = 1。期望值 E(X) = μ = Σ x · P(X = x) 代表了长期平均结果。方差 Var(X) = σ² = E(X²) − [E(X)]²，其中 E(X²) = Σ x² · P(X = x)。线性变换满足 E(aX + b) = a E(X) + b，Var(aX + b) = a² Var(X)。掌握这些核心公式，就能解答关于赌博游戏、离散成本模型和期望利润等问题。

7. The Binomial Distribution | 二项分布

A binomial distribution arises when a fixed number of independent trials n are conducted, each with the same probability of success p. The random variable X counts the number of successes, and X ~ B(n, p). The probability of obtaining exactly k successes is:

固定次数的独立试验中，每次成功概率 p 不变，这就衍生出二项分布。随机变量 X 表示成功的次数，记作 X ~ B(n, p)。恰好得到 k 次成功的概率为：

P(X = k) = ⁿCₖ pᵏ (1 − p)ⁿ⁻ᵏ

The expected value is E(X) = np, and variance Var(X) = np(1 − p). Binomial probabilities can be calculated using the formula or looked up in cumulative tables. Always check the assumptions: fixed n, constant p, and independence of trials. Common pitfalls include misreading ‘at least’ or ‘more than’ wording, so pay careful attention to inequalities and complement rules.

期望值 E(X) = np，方差 Var(X) = np(1 − p)。二项概率可直接用公式计算或查阅累积分布表。务必检查假设：试验次数固定，p 恒定，各次试验独立。常见的陷阱包括误解“至少”或“超过”等措辞，因此要特别留意不等关系和补集规则。

8. The Normal Distribution | 正态分布

The normal distribution, N(μ, σ²), is a continuous symmetrical bell-shaped curve characterised by its mean μ and standard deviation σ. Since the distribution is continuous, P(X = x) is always zero; we work with intervals. To find probabilities, we standardise to the standard normal variable Z ~ N(0, 1) using the transformation:

正态分布 N(μ, σ²) 是一种连续对称的钟形曲线，由其均值 μ 和标准差 σ 决定。因为是连续分布，P(X = x) 总是零；我们必须处理区间概率。计算概率时，将原变量标准化为标准正态变量 Z ~ N(0, 1)，变换公式为：

Z = (X − μ) / σ

Standard normal tables give Φ(z) = P(Z ≤ z). Reverse normal calculations find an unknown mean, standard deviation, or the value x corresponding to a given probability. In OCR exams, you may need to use symmetry (e.g., P(Z > z) = 1 − Φ(z); P(Z < −z) = Φ(−z) = 1 − Φ(z)). Always sketch a diagram to avoid sign errors.

标准正态表给出 Φ(z) = P(Z ≤ z)。逆向正态计算用于求解未知的均值、标准差或已知概率对应的 x 值。OCR 考试中需灵活运用对称性（如 P(Z > z) = 1 − Φ(z)；P(Z < −z) = Φ(−z) = 1 − Φ(z)）。画出分布图是避免符号错误的最佳方法。

9. Normal Approximation to the Binomial | 二项分布的正态近似

When n is large, the binomial distribution X ~ B(n, p) can be approximated by a normal distribution with the same mean and variance: X ∼ N(np, np(1 − p)) approximately. The usual conditions for a valid approximation are np > 5 and n(1 − p) > 5. Because we approximate a discrete distribution with a continuous one, a continuity correction is applied. For example, P(X ≤ k) is approximated by P(Y < k + 0.5), where Y ~ N(np, np(1 − p)). Similarly, P(X ≥ k) becomes P(Y > k − 0.5). Missing the continuity correction is the most common source of error in such questions.

当 n 很大时，二项分布 X ~ B(n, p) 可用具有相同均值与方差的正态分布近似：X ∼ N(np, np(1 − p))。有效的近似通常要求 np > 5 且 n(1 − p) > 5。由于用连续分布近似离散分布，必须进行连续性校正。例如，P(X ≤ k) 近似为 P(Y < k + 0.5)，其中 Y ~ N(np, np(1 − p))；类似地，P(X ≥ k) 变为 P(Y > k − 0.5)。遗漏连续性校正是此类题目中最常见的错误来源。

10. Hypothesis Testing | 假设检验

Hypothesis testing provides a formal framework for deciding whether evidence supports a claim. The null hypothesis H₀ assumes no effect or no difference, while the alternative hypothesis H₁ represents what we suspect. The test statistic is calculated from the sample, and the p‑value — the probability of obtaining a result at least as extreme as observed, assuming H₀ is true — is compared with the significance level α. If p-value < α, we reject H₀. For binomial tests, you find the cumulative probability directly or find the critical region. For a normal test of the population mean, when σ is known, use:

假设检验为判断证据是否支持某个主张提供了规范框架。原假设 H₀ 假定没有差别或效应，备择假设 H₁ 则代表我们所怀疑的。检验统计量由样本计算得到，而 p 值（在原假设成立的前提下得到至少与观测结果同等极端结果的概率）与显著性水平 α 比较。若 p 值 < α，则拒绝 H₀。对于二项检验，可直接求累积概率或确定拒绝域。当总体方差 σ 已知时，对总体均值的正态检验使用：

Z = (x̄ − μ₀) / (σ / √n)

For one-tailed tests, attention to the sign of the critical value is essential; two‑tailed tests halve the significance level for each tail. Conclude by writing a contextualised statement, such as ‘There is sufficient evidence at the 5% level to suggest that the mean has increased.’ Never claim ‘the null hypothesis is true’; state that we do not reject it. OCR questions often ask for the conclusion in context, so always link back to the problem statement.

单尾检验必须注意临界值的正负方向；双尾检验则须将显著性水平平分到两侧。结论应写出结合上下文的陈述，例如“在 5% 显著性水平下有足够证据表明均值已提高”。切忌声称“原假设是正确的”，而应说我们不拒绝它。OCR 试题常要求用上下文引出结论，因此务必紧扣问题背景。

Published by TutorHao | Statistics Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）

A-Level OCR Maths: Statistics Key Points | A-Level OCR 数学：统计 考点精讲