Core Knowledge Review for CAIE Year 11 Statistics | CAIE 11年级统计核心知识点梳理

📚 Core Knowledge Review for CAIE Year 11 Statistics | CAIE 11年级统计核心知识点梳理

Statistics for CAIE Year 11 (IGCSE/O Level) builds a solid foundation in handling data, understanding probability, and applying statistical methods to real-world problems. This guide breaks down the essential topics you must master, from organising raw data to carrying out a chi-squared test. Each concept is outlined with key definitions and practical tips to help you excel in examinations.

CAIE 11年级（IGCSE/O Level）统计课程旨在帮助学生掌握处理数据、理解概率以及将统计方法应用于实际问题的基础技能。本文梳理了你必须掌握的核心知识点，从整理原始数据到进行卡方检验，每个概念都配有定义与实用技巧，助你在考试中取得佳绩。

1. Types of Data and Data Collection | 数据类型与数据收集

Data can be classified as qualitative (categorical, e.g. eye colour) or quantitative (numerical). Quantitative data is further split into discrete (countable values, such as number of students) and continuous (measurable values, such as height). Understanding the data type is crucial because it determines which statistical techniques are appropriate.

数据可分为定性数据（分类数据，如眼睛颜色）和定量数据（数值数据）。定量数据又分为离散型（可数的值，如学生人数）和连续型（可测量的值，如身高）。理解数据类型至关重要，因为它决定了适用的统计方法。

Data collection methods include surveys, experiments, and observational studies. A census surveys every member of a population, while a sample surveys only a subset. Random sampling avoids bias; stratified sampling ensures subgroups are represented proportionally. Avoid leading questions and non-response bias when designing questionnaires.

数据收集方法包括调查、实验和观察性研究。普查针对总体的每一个成员，而抽样仅调查一个子集。随机抽样可避免偏差；分层抽样确保各子组按比例被代表。设计问卷时应避免诱导性问题和无回答偏差。

2. Presenting Data with Charts and Tables | 用图表展示数据

Effective data presentation reveals patterns at a glance. For categorical data, use bar charts or pie charts. For discrete quantitative data, a bar chart or vertical line graph is suitable. For continuous data, histograms (with frequency density on the vertical axis) are essential. In a histogram, area of a bar is proportional to frequency, so frequency density = frequency / class width.

有效的数据展示能一眼看出规律。分类数据可使用条形图或饼图；离散定量数据适合用条形图或垂线图；连续数据则必须使用直方图（纵轴为频率密度）。直方图中，每个矩形的面积与频数成比例，因此频率密度 = 频数 ÷ 组距。

Stem-and-leaf diagrams preserve original values and show the shape of a distribution. Cumulative frequency curves (ogives) help estimate medians, quartiles, and percentiles. Box-and-whisker plots summarise a data set using the five-number summary: minimum, lower quartile, median, upper quartile, and maximum.

茎叶图既能保留原始数据，又能展现分布形态。累积频率曲线（累计频数图）可用于估计中位数、四分位数和百分位数。箱线图通过五数概括（最小值、下四分位数、中位数、上四分位数、最大值）总结数据。

Chart Type	Best for	Key feature
Histogram	Continuous grouped data	Area equals frequency
Cumulative frequency curve	Finding quartiles	Smooth curve through upper class boundaries
Box plot	Comparing distributions	Shows spread and skewness

3. Measures of Central Tendency | 集中趋势的度量

The three principal measures are the mean, median, and mode. The mean (x̄ = Σx/n) uses all values but is affected by outliers. The median is the middle value when data are ordered; it is resistant to outliers. The mode is the most frequent value, useful for categorical data. For grouped data, the modal class is the class with the highest frequency density.

三种主要的集中趋势度量是均值、中位数和众数。均值（x̄ = Σx/n）使用了所有数据，但易受异常值影响。中位数是排序后位于中间的值，不受异常值干扰。众数是出现次数最多的值，适用于分类数据。对于分组数据，众数组是频率密度最高的组。

An average on its own can be misleading. Always consider the shape of the distribution. In a symmetric distribution, the mean, median, and mode coincide. In a positively skewed distribution, mean > median > mode; in a negatively skewed distribution, mean < median < mode.

单独使用平均数可能产生误导。应始终考虑分布形态。在对称分布中，均值、中位数和众数重合。在正偏态分布中，均值 > 中位数 > 众数；在负偏态分布中，均值 < 中位数 < 众数。

4. Measures of Dispersion | 离散程度的度量

Dispersion describes how spread out the data are. Range (maximum – minimum) is simple but highly sensitive to outliers. The interquartile range (IQR = Q₃ – Q₁) is robust and captures the spread of the middle 50% of data. Percentiles divide data into 100 equal parts; the 10th and 90th percentiles define an interpercentile range.

离散程度描述数据的分散情况。极差（最大值减最小值）简单但极易受异常值影响。四分位距（IQR = Q₃ – Q₁）稳健，反映中间50%数据的散布。百分位数将数据分为100等份；第10和第90百分位数可定义百分位距。

Variance and standard deviation are the most widely used measures. For a population: σ² = Σ(x – μ)² / N. For a sample, divide by n-1 to get an unbiased estimate. Standard deviation is the square root of variance and has the same units as the data. The larger the standard deviation, the more the data deviate from the mean.

方差和标准差是最常用的度量。总体方差：σ² = Σ(x – μ)² / N。样本方差除以 n-1 得到无偏估计。标准差是方差的平方根，与数据单位相同。标准差越大，数据越偏离均值。

Variance (sample): s² = Σ(x – x̄)² / (n – 1)

5. Basic Probability Concepts | 概率基础概念

Probability quantifies the chance of an event occurring, expressed as a number between 0 and 1. For a fair, equally likely sample space, P(A) = number of favourable outcomes / total number of outcomes. The complement rule: P(not A) = 1 – P(A). Events are mutually exclusive if they cannot occur simultaneously.

概率量化事件发生的可能性，用一个0到1之间的数表示。对于等可能样本空间，P(A) = 有利结果数 / 总结果数。补集规则：P(非A) = 1 – P(A)。如果两事件不可能同时发生，则它们互斥。

For independent events, P(A and B) = P(A) × P(B). For dependent events, use conditional probability: P(A and B) = P(A) × P(B|A). Venn diagrams and tree diagrams are powerful tools. When events are not mutually exclusive, apply the addition rule: P(A or B) = P(A) + P(B) – P(A and B).

对于独立事件，P(A且B) = P(A) × P(B)。对于非独立事件，使用条件概率：P(A且B) = P(A) × P(B|A)。维恩图和树状图是强大的工具。当事件不互斥时，应用加法法则：P(A或B) = P(A) + P(B) – P(A且B)。

6. Discrete Probability Distributions | 离散概率分布

A probability distribution lists all possible outcomes of a discrete random variable together with their probabilities. The sum of all probabilities must equal 1. The expected value E(X) = Σ [x · P(X = x)] gives the long-run average. The variance Var(X) = E(X²) – [E(X)]² measures the spread.

概率分布列出了离散随机变量的所有可能取值及其对应概率。所有概率之和必须等于1。期望值 E(X) = Σ [x · P(X = x)] 给出了长期平均值。方差 Var(X) = E(X²) – [E(X)]² 衡量离散程度。

The binomial distribution applies when there are a fixed number n of independent trials, each with only two possible outcomes (success/failure) and a constant probability of success p. Notation: X ~ B(n, p). Key formulas: P(X = r) = ⁿCᵣ pʳ (1-p)ⁿ⁻ʳ, Mean = np, Variance = np(1-p). Conditions: independence, fixed n, constant p, binary outcomes.

二项分布适用于固定试验次数n、每次试验独立且只有两种可能结果（成功/失败）、成功概率p恒定的情况。记作 X ~ B(n, p)。关键公式：P(X = r) = ⁿCᵣ pʳ (1-p)ⁿ⁻ʳ，均值 = np，方差 = np(1-p)。使用条件：独立、固定n、p恒定、二元结果。

When n is large and p is small, the Poisson distribution may be approximated. For CAIE Year 11, the focus is on binomial calculations using tables or a calculator. Recognise the shape: symmetric for p = 0.5, skewed for p ≠ 0.5.

当n很大且p很小时，可用泊松分布近似。CAIE 11年级重点在于使用表格或计算器进行二项分布计算。识别分布形状：p=0.5时对称，p≠0.5时呈偏态。

7. The Normal Distribution | 正态分布

The normal distribution is a continuous probability distribution with a bell-shaped curve symmetric about the mean μ. It is completely defined by its mean and standard deviation σ. The total area under the curve equals 1. Standard scores (z-scores) standardise any normal value: z = (x – μ) / σ.

正态分布是一种连续型概率分布，曲线呈钟形，关于均值μ对称。分布完全由均值和标准差σ决定。曲线下总面积为1。标准分数（z分数）可将任意正态值标准化：z = (x – μ) / σ。

The standard normal distribution has μ = 0, σ = 1. Use standard normal tables to find probabilities. For a range, find the area between two z-values. For inverse problems, locate the z-value corresponding to a given probability and solve for x. The 68-95-99.7 rule is a handy approximation: about 68% of data lie within 1σ, 95% within 2σ, 99.7% within 3σ of the mean.

标准正态分布的均值为0，标准差为1。使用标准正态表查找概率。对于区间，找出两个z值之间的面积。对于反向问题，根据给定概率找出z值，再解出x。68-95-99.7法则是一个便捷的近似：约68%的数据落在均值±1σ内，95%落在±2σ内，99.7%落在±3σ内。

Many real-world variables, such as heights or examination scores, approximately follow a normal distribution. Continuity correction may be needed when approximating a binomial distribution with a normal distribution.

许多现实变量，如身高或考试成绩，近似服从正态分布。在用正态分布近似二项分布时，可能需要连续性校正。

8. Sampling and Estimation | 抽样与估计

A sample must be representative of the population. Random sampling gives each member an equal chance of selection. Stratified sampling divides the population into strata and samples proportionally. Systematic sampling selects every kth member. Quota sampling fills pre-set categories without randomness. Understand the strengths and weaknesses of each method regarding bias and feasibility.

样本必须能代表总体。随机抽样使每个成员被选中的机会均等。分层抽样将总体分层并按比例抽样。系统抽样每隔k个抽取一个。配额抽样按照预设类别选取样本，但无随机性。需了解各方法在偏差和可行性方面的优缺点。

The sampling distribution of the sample mean has mean μ and standard deviation σ/√n (standard error). If the population is normal, the sample mean is normal for any n. For large n (Central Limit Theorem), the sample mean is approximately normal regardless of the population shape. This underpins confidence intervals and hypothesis testing.

样本均值的抽样分布具有均值μ和标准差σ/√n（标准误差）。若总体为正态，无论n大小，样本均值都呈正态分布。对于大样本（中心极限定理），无论总体形状，样本均值均近似正态。这是置信区间和假设检验的理论基础。

9. Hypothesis Testing and Chi-Squared Tests | 假设检验与卡方检验

Hypothesis testing involves a null hypothesis H₀ (status quo) and an alternative hypothesis H₁. A significance level (α, often 5%) sets the threshold for rejecting H₀. The p-value is the probability of obtaining a result at least as extreme as observed, assuming H₀ is true. If p-value < α, reject H₀.

假设检验包括原假设H₀（现状）和备择假设H₁。显著性水平（α，常取5%）设定拒绝H₀的阈值。p值是在H₀成立的条件下，得到至少与观测结果一样极端的概率。若p值 < α，则拒绝H₀。

The chi-squared test for independence assesses whether two categorical variables are associated. Compute expected frequencies E = (row total × column total) / grand total. The test statistic χ² = Σ (O – E)² / E. Compare to a critical value from the chi-squared table with (rows-1)×(columns-1) degrees of freedom. If χ² > critical value, reject H₀ of independence. Validity conditions: all expected frequencies should be at least 5.

独立性卡方检验用于判断两个分类变量是否有关联。计算期望频数 E = (行总计 × 列总计) / 总计。检验统计量 χ² = Σ (O – E)² / E。与自由度为 (行数-1)×(列数-1) 的卡方临界值比较。若 χ² > 临界值，则拒绝独立性的原假设。有效条件：所有期望频数至少为5。

Goodness-of-fit test uses the same chi-squared formula to check if data follow a specified distribution. Degrees of freedom depend on the number of categories minus constraints. These tests appear frequently in CAIE Statistics papers, so practicing with contingency tables is vital.

拟合优度检验使用相同的卡方公式，检查数据是否来自某一指定分布。自由度取决于类别数减去约束条件数量。这类题目在CAIE统计卷中频繁出现，务必多练习列联表题目。

10. Bivariate Data: Correlation and Regression | 双变量数据：相关与回归

Scatter diagrams reveal the relationship between two variables. Correlation describes the strength and direction of a linear association. The product-moment correlation coefficient r ranges from -1 to +1; r = 1 indicates perfect positive linear correlation, r = -1 perfect negative, r = 0 no linear correlation. Always interpret r in context—correlation does not imply causation.

散点图揭示两个变量的关系。相关性描述线性关联的强度与方向。积矩相关系数 r 的取值范围在 -1 到 +1 之间；r = 1 表示完全正线性相关，r = -1 表示完全负相关，r = 0 表示无线性相关。务必结合背景解读 r —— 相关不意味因果。

The least squares regression line has the form y = a + bx, where b = Sxy / Sxx and a = ȳ – bx̄. Sxx = Σ(x – x̄)², Sxy = Σ(x – x̄)(y – ȳ). This line minimises the sum of squared vertical distances. Use it to make predictions, but be cautious about extrapolation beyond the given data range.

最小二乘回归线公式为 y = a + bx，其中 b = Sxy / Sxx，a = ȳ – bx̄。Sxx = Σ(x – x̄)²，Sxy = Σ(x – x̄)(y – ȳ)。该直线使竖直距离平方和最小。可使用回归线作预测，但需谨慎外推到给定数据范围之外。

Spearman’s rank correlation coefficient is an alternative that does not require a linear relationship; it assesses monotonic association. Rank both variables, compute the difference d in ranks, then use rs = 1 – (6Σd²) / (n(n²-1)). It is useful when data are skewed or contain outliers.

斯皮尔曼秩相关系数是另一种不要求线性关系的度量；它评估单调关联。分别对两个变量排秩，计算秩差d，然后使用 rs = 1 – (6Σd²) / (n(n²-1))。当数据偏斜或含异常值时，该方法尤其实用。

11. Practical Tips for Examination Success | 考试成功的实用建议

Always read the question carefully to identify the data type and what is being measured. Show your working clearly, especially when computing means, standard deviations, and χ² values. Label diagrams fully—axes on histograms must show frequency density, not frequency. On cumulative frequency graphs, draw lines to estimate medians and quartiles. Check assumptions: for binomial, verify independence and constant p; for chi-squared, ensure expected frequencies ≥ 5. Manage your time; complex probability questions may be tackled with tree diagrams.

务必仔细审题，明确数据类型和测量目标。清晰展示计算过程，尤其是均值、标准差和卡方值的运算。图表要完整标注——直方图的纵轴必须是频率密度而非频数。在累积频率图上画出线段以估计中位数和四分位数。检查假设条件：对于二项分布，验证独立性和恒定p；对于卡方检验，确保期望频数 ≥ 5。合理安排时间；复杂概率题可借助树状图解决。

Practice past papers under timed conditions. Familiarity with statistical tables (normal, chi-squared, binomial) saves precious minutes. Remember that in regression, the line always passes through (x̄, ȳ). Use this as a quick check. Review the formula booklet and know which formulas are provided.

限时练习历年真题。熟悉统计表（正态、卡方、二项）能节省宝贵时间。记住回归直线必过点 (x̄, ȳ)，这可作为快速检验。通读公式手册，清楚哪些公式会在考试中提供。

Published by TutorHao | Statistics Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）

Core Knowledge Review for CAIE Year 11 Statistics | CAIE 11年级统计核心知识点梳理