📚 OCR Year 13 Statistics: Comprehensive Syllabus Breakdown | OCR 十三年级统计：课程大纲全面解析
The OCR A Level Statistics qualification (H248) is designed to give Year 13 students a deep understanding of statistical methods, data analysis, and inferential reasoning. This syllabus builds on AS content and introduces advanced topics such as Poisson and normal hypothesis testing, chi-squared tests, and regression analysis. In this article we break down every major topic area, explain key concepts, and highlight what examiners expect. Whether you are revising for the final exams or seeking clarity on a particular topic, this guide will help you navigate the full syllabus with confidence.
OCR A Level 统计资格 (H248) 旨在让十三年级学生深刻理解统计方法、数据分析以及推断性推理。该课程大纲在 AS 内容的基础上引入了泊松分布假设检验、正态假设检验、卡方检验以及回归分析等高级主题。本文将逐一拆解每个主要知识模块，解释关键概念，并指明考官所期望的能力。无论你是在为期末考试复习，还是想理清某个特定主题，这篇指南都能帮助你自信地掌握整个课程大纲。
1. Overview of OCR Statistics | 课程概述
The OCR A Level Statistics course is assessed through two externally examined papers: Statistics 1 (H248/01) and Statistics 2 (H248/02). Each paper is 1 hour 30 minutes and carries equal weight. The content covers data handling, probability, discrete distributions, the normal distribution, hypothesis testing, correlation, regression, and chi-squared tests. Year 13 candidates must also apply statistical models to real-world contexts and interpret results critically.
OCR A Level 统计课程通过两份外部考试卷进行评估：统计 1 (H248/01) 和统计 2 (H248/02)。每份试卷时长 1 小时 30 分钟，权重相同。课程内容涵盖数据处理、概率、离散分布、正态分布、假设检验、相关性、回归以及卡方检验。十三年级考生还必须将统计模型应用于真实情境，并批判性地解读结果。
Calculators with statistical functions are allowed, but candidates must show method and reasoning. Understanding the limitations of models, such as when the normal approximation to the binomial is valid, is frequently examined. The syllabus encourages a data-led approach, where exploratory analysis precedes formal inference.
考试允许使用具有统计功能的计算器，但考生必须展示方法和推理过程。理解模型的局限性（例如二项分布的正态近似何时有效）是常考内容。该课程大纲鼓励以数据为主导的方法，即在正式推断之前先进行探索性分析。
2. Sampling and Data Collection | 抽样与数据收集
Methodical data collection is the foundation of statistics. The OCR syllabus expects you to know the advantages and disadvantages of simple random sampling, stratified sampling, systematic sampling, quota sampling, and opportunity sampling. You must also understand the distinction between a population and a sample, and why bias must be avoided.
有条理的数据收集是统计学的基础。OCR 大纲要求你了解简单随机抽样、分层抽样、系统抽样、定额抽样和便利抽样的优缺点。你还必须理解总体与样本之间的区别，以及为什么要避免偏差。
Questions may ask you to describe a suitable sampling frame or identify a sampling method from a scenario. The concepts of pilot surveys and questionnaires are also included. You should be able to critique a data collection process, suggesting improvements to reduce bias and increase representativeness.
考题可能会要求你描述合适的抽样框，或根据情景识别抽样方法。试行调查和问卷的概念也包括在内。你应该能够评价数据收集过程，提出减少偏差和提高代表性的改进建议。
Types of data — quantitative (discrete and continuous) and qualitative — must be confidently distinguished. Understanding how data type affects the choice of statistical analysis is crucial for later topics.
必须自信地区分数据类型——定量数据（离散和连续）和定性数据。理解数据类型如何影响统计分析的选择，对后续主题至关重要。
3. Probability and Discrete Random Variables | 概率与离散随机变量
Probability underpins all inferential statistics. You need to apply the addition and multiplication rules, including for mutually exclusive and independent events. Tree diagrams and Venn diagrams remain useful tools for calculating compound probabilities.
概率是所有推断性统计的基础。你需要运用加法和乘法规则，包括互斥事件和独立事件的情形。树形图和维恩图仍是计算复合概率的有用工具。
A discrete random variable X has a probability distribution that lists each possible value with its probability. The expectation E(X) and variance Var(X) are calculated using formulas:
E(X) = Σ x P(X = x) Var(X) = E(X²) – [E(X)]²
离散随机变量 X 有一个概率分布，列出了每个可能取值及其概率。期望 E(X) 和方差 Var(X) 可用以下公式计算：
E(X) = Σ x P(X = x) Var(X) = E(X²) – [E(X)]²
You must be able to find the distribution of a function of a random variable, such as Y = aX + b, and calculate E(Y) and Var(Y) using linear transformation rules. These ideas recur when standardising normal variables.
你必须能够求出随机变量函数的分布，例如 Y = aX + b，并利用线性变换规则计算 E(Y) 和 Var(Y)。这些思想在标准化正态变量时会再次出现。
4. Binomial and Poisson Distributions | 二项分布与泊松分布
The binomial distribution models the number of successes in a fixed number of independent trials, each with probability p of success. Notation: X ~ B(n, p). You must be able to calculate probabilities using the formula:
P(X = r) = ⁿCᵣ pʳ (1 – p)ⁿ⁻ʳ
二项分布对固定次数独立试验中成功次数进行建模，每次试验的成功概率为 p。记号：X ~ B(n, p)。你必须能够使用公式计算概率：
P(X = r) = ⁿCᵣ pʳ (1 – p)ⁿ⁻ʳ
The Poisson distribution models the number of events occurring in a fixed interval of time or space, given a constant mean rate λ. Notation: X ~ Po(λ). Its probability mass function is:
P(X = r) = e⁻ʰ λʳ / r!
泊松分布对固定时间或空间区间内发生的事件次数进行建模，给定恒定平均率 λ。记号：X ~ Po(λ)。其概率质量函数为：
P(X = r) = e⁻ʰ λʳ / r!
You are expected to know the conditions for each distribution: binomial requires independence and constant p; Poisson requires randomness, independence, and a constant mean rate. The Poisson approximation to the binomial is valid when n is large and p is small; typically np < 5 with n > 20, but the syllabus focuses on using λ = np.
你需要了解每种分布的条件：二项分布要求独立性和恒定的 p；泊松分布要求随机性、独立性和恒定的平均率。当 n 很大而 p 很小时，可使用泊松分布近似二项分布；通常 np < 5 且 n > 20，但大纲重点在于使用 λ = np。
5. The Normal Distribution | 正态分布
The normal distribution N(μ, σ²) is a continuous distribution symmetric about its mean μ. Its standard deviation is σ. You need to be able to standardise a normal variable to Z ~ N(0, 1²) using:
Z = (X – μ) / σ
正态分布 N(μ, σ²) 是一种关于均值 μ 对称的连续分布。其标准差为 σ。你需要能够使用以下公式将正态变量标准化为 Z ~ N(0, 1²)：
Z = (X – μ) / σ
Probability tables are provided for the standard normal distribution. You must be able to find probabilities such as P(X > a) or P(a < X < b) using tables or inverse normal functions. Calculations with two independent normal variables, including sums and differences, are also examinable: X₁ ± X₂ ~ N(μ₁ ± μ₂, σ₁² + σ₂²).
标准正态分布的概率表会在考试中提供。你必须能够使用表格或逆正态函数求出 P(X > a) 或 P(a < X < b) 等概率。两个独立正态变量的和与差也可在考试范围内：X₁ ± X₂ ~ N(μ₁ ± μ₂, σ₁² + σ₂²)。
Normal approximation to the binomial and Poisson distributions requires a continuity correction. For binomial: X ~ B(n, p) approximated as N(np, np(1-p)), applying the half-unit correction. For Poisson: X ~ Po(λ) approximated as N(λ, λ) for λ > 15 typically.
二项分布和泊松分布的正态近似需要连续性校正。对二项分布：X ~ B(n, p) 近似为 N(np, np(1-p))，应用半个单位的校正。对泊松分布：通常 λ > 15 时，X ~ Po(λ) 近似为 N(λ, λ)。
6. Hypothesis Testing: Discrete Variables | 假设检验：离散变量
Hypothesis testing is a core skill. For discrete distributions (binomial and Poisson), you set up null and alternative hypotheses: H₀: p = p₀ or H₀: λ = λ₀, with one-tailed or two-tailed alternatives. The test statistic is the observed number of successes or events.
假设检验是一项核心技能。对于离散分布（二项和泊松），你需要建立原假设和备择假设：H₀: p = p₀ 或 H₀: λ = λ₀，以及单尾或双尾的备择假设。检验统计量是观测到的成功次数或事件次数。
Using the distribution of the test statistic under H₀, you calculate the probability of obtaining a result at least as extreme as the observed value. Compare this probability (the p-value) with the significance level α, typically 5% or 1%. If p-value < α, reject H₀. You must also be able to find critical regions and critical values from tables.
利用 H₀ 下检验统计量的分布，计算得到至少与实际观测值一样极端的结果的概率。将此概率（p 值）与显著性水平 α 进行比较，α 通常为 5% 或 1%。若 p 值 < α，则拒绝 H₀。你还必须能够从表中找出拒绝域和临界值。
Questions may provide a table of binomial or Poisson probabilities, requiring you to interpret them to conduct the test. Clear, step-by-step conclusions in context are essential for full marks.
考题可能提供二项或泊松概率表，要求你解读它们以进行检验。得分的要点是步骤清晰、在情境中得出结论。
7. Hypothesis Testing for the Mean (Normal) | 均值假设检验（正态）
When the population is normally distributed with known variance σ², you can test for the mean μ using the Z-test. The test statistic is:
Z = (x̄ – μ₀) / (σ / √n)
当总体服从正态分布且方差 σ² 已知时，你可以使用 Z 检验对均值 μ 进行检验。检验统计量为：
Z = (x̄ – μ₀) / (σ / √n)
If the variance is unknown, the t-test is used with the sample standard deviation s. The test statistic then follows a t-distribution with n – 1 degrees of freedom:
t = (x̄ – μ₀) / (s / √n)
若方差未知，则使用 t 检验，并用样本标准差 s。此时检验统计量服从自由度为 n – 1 的 t 分布：
t = (x̄ – μ₀) / (s / √n)
Paired t-test scenarios are included. Here you work with differences d = X – Y, test whether the mean difference is zero, and use the mean and standard deviation of the differences. This test is essential for before-and-after experiments.
配对 t 检验的情况也包括在内。此时你处理差值 d = X – Y，检验均值差是否为零，并使用差值的均值和标准差。该检验对于前后对照实验至关重要。
8. Confidence Intervals | 置信区间
A confidence interval gives a range of plausible values for a population parameter. For the mean of a normal population with known variance:
x̄ ± zₐ/₂ × (σ / √n)
置信区间给出了总体参数的可能值范围。对于方差已知的正态总体均值：
x̄ ± zₐ/₂ × (σ / √n)
When the variance is unknown, use the t-distribution critical value:
x̄ ± tₙ₋₁,α/₂ × (s / √n)
当方差未知时，使用 t 分布的临界值：
x̄ ± tₙ₋₁,α/₂ × (s / √n)
Interpretation of confidence intervals is frequently tested. A 95% confidence interval means that if the experiment were repeated many times, 95% of such intervals would contain the true mean. It does not mean there is a 95% probability that the true mean lies in the computed interval.
置信区间的解释经常被考查。95% 置信区间意味着，如果重复进行多次实验，这样得到的区间中有 95% 会包含真实的均值。它并不意味着真实均值有 95% 的概率落在计算出的区间内。
9. Correlation and Regression | 相关与回归
OCR requires calculation and interpretation of the product moment correlation coefficient (PMCC), r. The formula uses corrected sums of squares and products, assessed via calculator but you may be shown summary statistics to compute r. Values close to 1 or –1 indicate strong linear correlation.
OCR 要求计算和解释积矩相关系数 (PMCC) r。公式使用校正后的平方和与乘积和，考试中可利用计算器计算，但你可能需要根据汇总统计量求出 r。r 值接近 1 或 –1 表示存在强线性相关。
The least squares regression line y = a + bx is fitted, with:
b = Sₓᵧ / Sₓₓ a = ȳ – b x̄
拟合最小二乘回归线 y = a + bx，其中：
b = Sₓᵧ / Sₓₓ a = ȳ – b x̄
You must know how to interpret the slope and intercept in context. The regression line is only appropriate for prediction within the range of the data; extrapolation should be avoided. Hypothesis testing for the population correlation coefficient ρ is also examined: H₀: ρ = 0 against H₁: ρ ≠ 0 (or one-tailed), using tables of critical values for r.
你必须知道如何在具体情境中解释斜率和截距。回归线仅适用于在数据范围内进行预测；应避免外推。总体相关系数 ρ 的假设检验也会考查：H₀: ρ = 0，备择 H₁: ρ ≠ 0（或单尾），使用 r 的临界值表。
10. Chi-Squared Tests | 卡方检验
Chi-squared (χ²) tests are used for categorical data. The goodness-of-fit test checks whether observed frequencies conform to a specified distribution. The test statistic is:
χ² = Σ (O – E)² / E
卡方 (χ²) 检验用于分类数据。拟合优度检验可检验观测频数是否符合特定分布。检验统计量为：
χ² = Σ (O – E)² / E
Degrees of freedom for goodness-of-fit depend on the number of categories and any estimated parameters. For a test of association in a contingency table, degrees of freedom = (r – 1)(c – 1). You must merge categories if any expected frequency is less than 1, or if more than 20% of expected frequencies are below 5.
拟合优度检验的自由度取决于类别数量和所估计的参数个数。对于列联表中的独立性检验，自由度 = (r – 1)(c – 1)。如果任何期望频数小于 1，或者超过 20% 的期望频数低于 5，则必须合并类别。
OCR candidates must be able to state hypotheses clearly: for association, H₀: variables are independent; H₁ they are not independent. Interpretation of the test, including using critical values from χ² tables, is required.
OCR 考生必须能够清晰地陈述假设：对于关联性，H₀：变量独立；H₁：变量不独立。需要对检验进行解释，包括使用 χ² 分布表的临界值。
11. Exam Techniques and Assessment | 考试技巧与评估方式
Both Statistics 1 and Statistics 2 papers mix short, structured questions with longer problem-solving tasks. Time management is vital. Always show working even when using a calculator — OCR awards method marks. Read the question carefully to state your conclusion in context, not simply ‘reject H₀’.
统计 1 和统计 2 这两份试卷都混合了简短的、结构化的题目以及较长的解决问题的任务。时间管理至关重要。即使使用计算器，也要始终展示推导过程——OCR 会为方法得分。仔细读题，在具体情境中陈述结论，而不仅仅是“拒绝 H₀”。
Typical mark allocations: setting up hypotheses (2 marks), calculating test statistic (2-3 marks), comparing to critical value or finding p-value (2 marks), contextual conclusion (1 mark). Diagrams for normal distribution problems help avoid errors with tails.
典型的分数分配：建立假设（2 分），计算检验统计量（2-3 分），与临界值比较或求 p 值（2 分），带情境的结论（1 分）。在正态分布问题中画示意图有助于避免尾部错误。
Revising through past papers is the most effective strategy. Focus on areas where the syllabus specifies ‘knowledge’ and ‘understanding of limitations’, such as conditions for a Poisson model or the effect of outliers on regression. Use the OCR formula booklet to become familiar with conventions.
通过过去的试卷进行复习是最有效的策略。重点复习大纲中指定“知识”和“理解局限性”的领域，例如泊松模型的条件或异常值对回归的影响。使用 OCR 的公式手册，熟悉其中的惯例。
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Cancel reply