📚 Core Concepts in WJEC Pre-U Statistics | WJEC Pre-U 统计核心知识点梳理
The WJEC Pre-U Statistics course builds a rigorous foundation in statistical thinking, from data collection to inference. Mastery of these core concepts not only prepares students for the final examination but also equips them with analytical skills essential for further study in science, social science, and beyond. This article reviews the key topics in a structured, bilingual format.
WJEC Pre-U 统计课程为学生打下从数据收集到统计推断的严谨基础。掌握这些核心概念不仅有助于学生应对最终考试，也为他们在科学、社会科学等领域的深造提供了必要的分析技能。本文以结构化、双语对照的形式回顾这些关键主题。
1. Data Types and Collection | 数据类型与收集
In statistics, data are classified as qualitative (categorical) or quantitative (numerical). Qualitative data can be nominal, where categories have no natural order, or ordinal, where an order exists. Quantitative data are discrete if they take isolated values, and continuous if they can take any value within an interval. Collecting unbiased data requires careful design: experiments impose treatments, surveys use questionnaires, and observational studies record without intervention. All methods rely on random sampling, such as simple random sampling, stratified sampling, or cluster sampling, to obtain a representative sample from the target population.
在统计中，数据分为定性（分类）和定量（数值）两类。定性数据可以是无自然顺序的名义数据，或存在顺序的有序数据；定量数据若只取孤立的值则为离散型，若在一区间内可取任意值则为连续型。收集无偏数据需要精心设计：实验施加处理，调查使用问卷，观察研究则不加干预地记录。所有方法都依赖随机抽样——如简单随机抽样、分层抽样或整群抽样——以便从目标总体中获得代表性样本。
A key distinction is between population and sample. A parameter describes a population characteristic, while a statistic describes a sample. A sampling frame lists the population, and careful sampling minimises selection bias. In Pre-U, you will also meet the concepts of quota sampling and systematic sampling, understanding their strengths and limitations.
总体与样本之间的区别至关重要。参数描述总体特征，而统计量描述样本。抽样框列出总体成员，精心抽样可最大限度地减少选择偏差。在 Pre-U 课程中，你还会接触到配额抽样和系统抽样，并理解各自的优势与局限。
2. Data Presentation and Summary Statistics | 数据呈现与概括性统计量
Graphical summaries include bar charts and pie charts for categorical data, and histograms, box plots, and cumulative frequency curves for numerical data. Histograms use area to represent frequency, so class width matters. Box plots display the median, quartiles, and any potential outliers. Cumulative frequency curves allow estimation of percentiles and the median.
图形概括包括适用于分类数据的条形图和饼图，以及适用于数值数据的直方图、箱线图和累积频率曲线。直方图用面积表示频数，因此组距很重要。箱线图显示中位数、四分位数及可能的异常值。累积频率曲线可用于估计百分位数和中位数。
Numerical summaries measure central tendency and spread. The sample mean is x̄ = Σxᵢ/n, the median is the middle value, and the mode is the most frequent value. Spread is measured by range, interquartile range (IQR = Q₃ – Q₁), and variance. The sample variance is s² = Σ(xᵢ – x̄)²/(n – 1), with standard deviation s. Outliers can be identified using the 1.5 × IQR rule. Understanding these measures is fundamental before moving to probability and inference.
数值概括测量集中趋势和离散程度。样本均值为 x̄ = Σxᵢ/n，中位数为中间值，众数为出现最频繁的值。离散程度由极差、四分位距（IQR = Q₃ – Q₁）和方差衡量。样本方差为 s² = Σ(xᵢ – x̄)²/(n – 1)，标准差为 s。异常值可用 1.5 × IQR 准则识别。在接触概率与推断之前，理解这些度量至关重要。
3. Fundamentals of Probability | 概率论基础
Probability quantifies uncertainty. The sample space S contains all possible outcomes of an experiment. For any event A, 0 ≤ P(A) ≤ 1, and P(S) = 1. Addition rule: P(A ∪ B) = P(A) + P(B) – P(A ∩ B). Mutually exclusive events have P(A ∩ B) = 0. Conditional probability is P(A | B) = P(A ∩ B)/P(B). Two events are independent if P(A ∩ B) = P(A)P(B), or equivalently P(A | B) = P(A).
概率量化不确定性。样本空间 S 包含试验的所有可能结果。对任何事件 A，有 0 ≤ P(A) ≤ 1 且 P(S) = 1。加法法则：P(A ∪ B) = P(A) + P(B) – P(A ∩ B)。互斥事件满足 P(A ∩ B) = 0。条件概率为 P(A | B) = P(A ∩ B)/P(B)。若 P(A ∩ B) = P(A)P(B)，或等价地 P(A | B) = P(A)，则两事件独立。
Bayes’ theorem is a central result: P(A | B) = [P(B | A)P(A)] / P(B). It allows updating probabilities when new information is available. Tree diagrams and two-way tables are invaluable tools for structuring multi-stage probability problems, particularly in WJEC examinations.
贝叶斯定理是一个核心结论：P(A | B) = [P(B | A)P(A)] / P(B)。它可用于在获得新信息后更新概率。树形图和双向表格是解决多阶段概率问题的宝贵工具，尤其在 WJEC 考试中。
4. Discrete Random Variables | 离散随机变量
A discrete random variable X takes a finite or countably infinite number of values. Its probability mass function (PMF) is P(X = x), which satisfies P(X = x) ≥ 0 and Σ P(X = x) = 1. The cumulative distribution function (CDF) is F(x) = P(X ≤ x). The expected value, or mean, is E(X) = Σ x·P(X = x). The variance is Var(X) = E(X²) – [E(X)]² = Σ(x – μ)²P(X = x).
离散随机变量 X 取有限或可数无限个值。其概率质量函数（PMF）为 P(X = x)，满足 P(X = x) ≥ 0 且 Σ P(X = x) = 1。累积分布函数（CDF）为 F(x) = P(X ≤ x)。期望值（即均值）为 E(X) = Σ x·P(X = x)。方差为 Var(X) = E(X²) – [E(X)]² = Σ(x – μ)²P(X = x)。
For a linear transformation Y = aX + b, we have E(Y) = aE(X) + b and Var(Y) = a² Var(X). These properties are used frequently when standardising variables or dealing with coded data. The concept of expectation is later extended to continuous random variables.
对于线性变换 Y = aX + b，有 E(Y) = aE(X) + b 和 Var(Y) = a² Var(X)。这些性质在变量标准化或处理编码数据时经常使用。期望的概念随后会推广到连续随机变量。
5. 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 Bernoulli trials. If X ~ B(n, p), its PMF is P(X = k) = ⁿCₖ pᵏ (1 – p)ⁿ⁻ᵏ for k = 0,1,…,n. Here E(X) = np and Var(X) = np(1 – p). The assumptions are: fixed n, independent trials, constant p, and binary outcomes. The distribution is symmetric when p = 0.5 and skewed otherwise.
二项分布描述在固定次数的独立伯努利试验中成功次数的分布。若 X ~ B(n, p)，其概率质量函数为 P(X = k) = ⁿCₖ pᵏ (1 – p)ⁿ⁻ᵏ，k = 0,1,…,n。此时期望 E(X) = np，方差 Var(X) = np(1 – p)。其假设为：固定的 n、独立试验、常数 p 以及二元结果。当 p = 0.5 时该分布对称，否则偏斜。
The Poisson distribution models rare events occurring independently in a fixed interval. If X ~ Po(λ), then P(X = k) = e⁻λ λᵏ / k! for k = 0,1,2,… . Both mean and variance equal λ. It can approximate the binomial distribution when n is large and p is small, with λ = np. WJEC Pre-U often asks students to justify such approximations and to use cumulative Poisson tables.
泊松分布描述在固定区间内独立发生的稀有事件。若 X ~ Po(λ)，则 P(X = k) = e⁻λ λᵏ / k!，k = 0,1,2,…。其均值和方差均等于 λ。当 n 很大而 p 很小时，可由二项分布近似，此时 λ = np。WJEC Pre-U 常要求学生说明该近似的合理性并使用泊松累积表。
6. Continuous Random Variables and the Normal Distribution | 连续随机变量与正态分布
A continuous random variable has a probability density function (PDF) f(x) that satisfies f(x) ≥ 0 and total area under the curve equals 1. Probabilities are found by integration: P(a < X < b) = ∫ₐᵇ f(x) dx. The cumulative distribution function is F(x) = P(X ≤ x). Expectation and variance are defined analogously to the discrete case but with integrals.
连续随机变量具有概率密度函数（PDF）f(x)，满足 f(x) ≥ 0 且曲线下总面积为 1。概率由积分求得：P(a < X < b) = ∫ₐᵇ f(x) dx。累积分布函数为 F(x) = P(X ≤ x)。期望与方差的定义与离散情形类似，但使用积分。
The normal distribution is the most important continuous distribution. If X ~ N(μ, σ²), its PDF is f(x) = (1/(σ√(2π))) exp(–½[(x – μ)/σ]²). Standardising gives Z = (X – μ)/σ ~ N(0,1). The standard normal table provides Φ(z) = P(Z < z). Calculations involve finding probabilities for intervals, working backwards to find quantiles, and applying the 68–95–99.7 empirical rule. In Pre-U, you may also meet the normal approximation to binomial or Poisson with continuity correction.
正态分布是最重要的连续分布。若 X ~ N(μ, σ²)，其概率密度函数为 f(x) = (1/(σ√(2π))) exp(–½[(x – μ)/σ]²)。标准化得 Z = (X – μ)/σ ~ N(0,1)。标准正态表给出 Φ(z) = P(Z < z)。计算包括求区间概率、反向求分位数以及应用 68–95–99.7 经验法则。在 Pre-U 中，你还会遇到使用连续性校正的正态近似二项或泊松分布。
7. Sampling and Sampling Distributions | 抽样与抽样分布
A statistic is a random variable because its value varies from sample to sample. The sampling distribution of a statistic describes its probability distribution over all possible samples of the same size. For the sample mean x̄, if the parent population has mean μ and variance σ², then E(x̄) = μ and Var(x̄) = σ²/n. If the population is normal, x̄ is exactly normal for any n.
统计量是随机变量，因为其值随样本变化。统计量的抽样分布描述了在所有相同容量的可能样本中该统计量的概率分布。对于样本均值 x̄，若原始总体的均值为 μ、方差为 σ²，则 E(x̄) = μ，Var(x̄) = σ²/n。若总体本身正态，则对任意 n，x̄ 都精确服从正态分布。
The Central Limit Theorem (CLT) states that, for a non-normal population with finite variance, the sampling distribution of x̄ becomes approximately normal as n increases, typically for n ≥ 30. Similarly, for a sample proportion p̂, the sampling distribution is approximately N(p, p(1 – p)/n) under certain conditions. These results underpin confidence intervals and hypothesis tests.
中心极限定理（CLT）指出，对于具有有限方差的非正态总体，当 n 增大时（通常 n ≥ 30），x̄ 的抽样分布近似正态。类似地，对于样本比例 p̂，在特定条件下其抽样分布近似为 N(p, p(1 – p)/n)。这些结果奠定了置信区间和假设检验的基础。
8. Estimation | 参数估计
Point estimation uses a single statistic to estimate a population parameter. An estimator is unbiased if its expectation equals the parameter, e.g., E(x̄) = μ and E(s²) = σ². The standard error (SE) measures the variability of an estimator. For the mean, SE(x̄) = σ/√n.
点估计使用单一统计量估计总体参数。若估计量的期望值等于参数，则它是无偏的，例如 E(x̄) = μ，E(s²) = σ²。标准误（SE）衡量估计量的变异性。对于均值，SE(x̄) = σ/√n。
Interval estimation provides a confidence interval (CI). For a normal population with known σ, a 95% CI for μ is x̄ ± z* × σ/√n, where z* = 1.96. When σ is unknown, we use the t-distribution with n – 1 degrees of freedom: x̄ ± t* × s/√n. For proportions, the large-sample CI is p̂ ± z* × √[p̂(1 – p̂)/n]. The interpretation of a CI and the required conditions are commonly tested in WJEC Pre-U.
区间估计给出置信区间（CI）。对于已知 σ 的正态总体，μ 的 95% 置信区间为 x̄ ± z* × σ/√n，其中 z* = 1.96。当 σ 未知时，使用自由度为 n – 1 的 t 分布：x̄ ± t* × s/√n。对于比例，大样本置信区间为 p̂ ± z* × √[p̂(1 – p
Published by TutorHao | Pre-U 统计 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