📚 CAIE GCSE Statistics: Core Knowledge Compilation | CAIE GCSE 统计：核心知识点梳理
Statistics in the CAIE GCSE course equips students with the tools to collect, organise, analyse and interpret data. A solid grasp of these core concepts is essential for tackling both exam questions and real‑world problems. This article distils the key topics, from data types to probability, into a clear revision guide.
CAIE GCSE 统计课程帮助学生掌握收集、整理、分析和解读数据的工具。扎实掌握这些核心概念对于应对考试和解决实际问题都至关重要。本文将数据、概率等关键主题浓缩成一份清晰的复习指南。
1. Data Collection and Sources | 数据收集与来源
Data can be obtained through primary sources, such as experiments, surveys or direct measurements, where you collect the information yourself. Alternatively, secondary data comes from existing records, publications or databases gathered by others.
数据可以通过第一手来源获得，例如实验、调查或直接测量，由你自己收集信息。第二手数据则来自他人已整理好的记录、出版物或数据库。
When designing a data collection task, it is important to consider the population of interest and to avoid bias. A census studies every member of the population, while a sample selects a subset. The sampling method must be clearly described to ensure the data is representative.
在设计数据收集任务时，必须明确目标总体并避免偏差。普查研究总体中的每一个成员，而抽样只选取一个子集。抽样方法需清晰描述以确保数据具有代表性。
2. Classifying Data | 数据类型
Data can be qualitative (categorical) or quantitative (numerical). Qualitative data describes attributes like eye colour or type of car. Quantitative data is either discrete, taking only particular values (e.g. number of students), or continuous, which can take any value in a range (e.g. height or time).
数据可分为定性（分类）数据和定量（数值）数据。定性数据描述特征，如眼睛颜色或汽车型号。定量数据分为离散型（只取特定值，如学生人数）和连续型（可取某个范围内的任意值，如身高或时间）。
Understanding the data type is crucial because it determines which diagrams and summary statistics are appropriate. For instance, bar charts are used for qualitative data, while histograms are designed for continuous data.
理解数据类型至关重要，因为它决定了使用哪种图表和汇总统计量。例如，条形图适用于定性数据，而直方图则专门用于连续数据。
3. Sampling Methods | 抽样方法
Random sampling ensures every member of the population has an equal chance of being chosen, reducing selection bias. Simple random sampling can be carried out using random number tables or generators.
随机抽样确保总体中每个成员都有相等的机会被选中，从而减少选择偏差。简单随机抽样可以使用随机数表或生成器进行。
Stratified sampling divides the population into distinct groups (strata) and then takes a random sample from each stratum in proportion to its size. This method improves representativeness when the population contains subgroups.
分层抽样将总体划分为不同的组（层），然后从每一层按比例随机抽取样本。当总体包含子群时，这种方法能提高代表性。
Systematic sampling selects every k‑th item from a list after a random start, while quota sampling sets a target number for each category but does not use randomness, which can introduce bias.
等距抽样在随机起点后从列表中每隔k个单位选取一个样本；定额抽样则为每个类别设定目标数量，但不采用随机方法，可能引入偏差。
4. Frequency Tables and Diagrams | 频数表与统计图
A frequency table organises raw data by counting how often each value or group occurs. For continuous data, we often group the data into class intervals, noting the class boundaries carefully to avoid gaps.
频数表通过统计每个取值或组出现的次数来整理原始数据。对于连续数据，我们通常将数据分组形成区间，并仔细确定组界以避免空隙。
Bar charts display qualitative data with bars separated by gaps; the height of each bar represents the frequency. Pie charts show proportions where each sector’s angle is (frequency ÷ total frequency) × 360°.
条形图用带有间隙的条形表示定性数据；条形的高度代表频数。饼图显示比例，每个扇形的角度为（频数÷频数总和）×360°。
Histograms are used for continuous data with no gaps between bars, and the area of each bar is proportional to the frequency. On a histogram, the vertical axis shows frequency density (frequency ÷ class width) when class widths are unequal.
直方图用于连续数据，条形之间无间隙，且每个长条的面积与频数成正比。在直方图中，若组距不等，纵轴表示频率密度（频数÷组距）。
5. Measures of Central Tendency | 集中趋势量数
The mean of a set of data is calculated by summing all values and dividing by the number of values. For ungrouped data: Mean = (Σx)/n. For grouped data, use the midpoints of intervals multiplied by their frequencies.
一组数据的平均数是将所有数值相加后除以数值个数。对于未分组数据：均值 = (Σx)/n。对于分组数据，需使用区间中点乘以对应频数。
The median is the middle value when the data are arranged in order. If there are n values, the median is at the (n+1)/2 th position. The mode is the most frequently occurring value or class. For grouped data, the modal class is the interval with the highest frequency.
中位数是将数据排序后的中间值。若有n个数值，中位数的位置在第 (n+1)/2 个。众数是出现频率最高的取值或组。对于分组数据，众数所在组是频数最高的区间。
Weighted mean is used when some values contribute more than others. Multiply each value by its weight, sum the products, then divide by the sum of the weights: x̄w = (Σwx)/(Σw).
加权平均数用于某些值具有更大权重的情形。将每个值乘以其权重，求和后除以权重总和：x̄w = (Σwx)/(Σw)。
6. Measures of Dispersion | 离散程度量数
The range is the simplest measure of spread: Range = maximum value − minimum value. It is easily affected by outliers and does not use all the data.
极差是最简单的离散程度量数：极差 = 最大值 − 最小值。它容易受异常值影响，且未利用全部数据。
The interquartile range (IQR) is the difference between the upper quartile (Q₃) and lower quartile (Q₁): IQR = Q₃ − Q₁. The IQR measures the spread of the middle 50% of the data and is more robust to outliers.
四分位距 (IQR) 是上四分位数 (Q₃) 与下四分位数 (Q₁) 之差：IQR = Q₃ − Q₁。IQR 衡量中间50%数据的散布情况，对异常值更加稳健。
Standard deviation quantifies how much the data values deviate from the mean. For a sample, s = √[ Σ(x − x̄)² / (n − 1) ]. A small standard deviation indicates data are clustered closely around the mean.
标准差用来衡量数据值偏离平均数的程度。对于样本，s = √[ Σ(x − x̄)² / (n − 1) ]。标准差小表明数据紧密聚集在均值附近。
7. Cumulative Frequency and Box Plots | 累积频数与箱线图
A cumulative frequency table adds up the frequencies as you move through the ordered intervals. The cumulative frequency curve (or ogive) is drawn by plotting the upper class boundary against the cumulative frequency and joining with a smooth curve.
累积频数表在按序经过每个区间时将频数累加起来。累积频数曲线（或称为拱形图）以区间上限为横坐标、累积频数为纵坐标描点，再用光滑曲线连接。
Quartiles and percentiles can be estimated from the cumulative frequency graph. The median corresponds to the 50th percentile, Q₁ to the 25th percentile and Q₃ to the 75th percentile.
四分位数和百分位数可以从累积频数图中估计。中位数对应第50百分位数，Q₁ 对应第25百分位数，Q₃ 对应第75百分位数。
A box‑and‑whisker plot displays the minimum, Q₁, median, Q₃ and maximum. It provides a clear visual summary of the distribution, highlighting symmetry, skewness and potential outliers.
箱线图显示最小值、Q₁、中位数、Q₃ 和最大值。它能清晰地呈现数据分布的对称性、偏态和潜在异常值。
8. Scatter Diagrams and Correlation | 散点图与相关
A scatter diagram plots paired data (x, y) and helps to identify the relationship between two variables. The pattern of points reveals whether the correlation is positive, negative or zero.
散点图描绘成对数据 (x, y)，有助于识别两个变量之间的关系。点的排列形态揭示了相关是正相关、负相关还是零相关。
The line of best fit is drawn by eye, balancing the points above and below the line. Using the line, you can estimate unknown values: interpolation within the data range and extrapolation outside it, though extrapolation is less reliable.
最佳拟合线通过目测绘制，使线上方和线下方的点数大致平衡。利用该线可以估计未知值：在数据范围内为内插，超出范围为外推，但外推可靠性较低。
Be aware that correlation does not imply causation. A strong correlation may be caused by a third factor or be purely coincidental.
要注意相关关系并不意味因果关系。强相关可能由第三个因素导致，也可能纯属巧合。
9. Time Series and Moving Averages | 时间序列与移动平均
A time series plots data points in chronological order. Key features to identify include the general trend (long‑term increase or decrease), seasonal variation (regular fluctuations over fixed periods) and irregular fluctuations (random noise).
时间序列图按时间顺序描绘数据点。需识别的主要特征包括基本趋势（长期上升或下降）、季节性波动（固定周期内有规律的变动）和不规则波动（随机噪声）。
Moving averages smooth out short‑term fluctuations to reveal the underlying trend. For an odd‑point moving average, each average is placed in the middle of the time interval it covers. A 3‑point moving average for values y₁, y₂, y₃ is (y₁ + y₂ + y₃)/3.
移动平均可以平滑短期波动，揭示基本趋势。对于奇数点移动平均，每个平均值放在所覆盖时间段的中间。三个数值 y₁, y₂, y₃ 的三点移动平均为 (y₁ + y₂ + y₃)/3。
Seasonal effects can be estimated by calculating the average deviation from the trend for each season. This allows forecasts to be adjusted for expected seasonal variation.
季节效应可以通过计算每个季节相对于趋势的平均偏差来估计。这样便可对预测值根据预期的季节性波动进行调整。
10. Probability Basics | 概率基础
Probability measures the chance of an event occurring, taking values between 0 (impossible) and 1 (certain). The probability of event A is written P(A). All possible outcomes form the sample space, and the sum of probabilities of all mutually exclusive outcomes is 1.
概率衡量事件发生的可能性，取值介于0（不可能）和1（必然）之间。事件A的概率写作 P(A)。所有可能结果构成样本空间，所有互斥结果的概率之和为1。
For equally likely outcomes, P(A) = number of favourable outcomes ÷ total number of outcomes. The complement of A, written A’, has P(A’) = 1 − P(A).
对于等可能结果，P(A) = 有利结果数÷所有可能结果数。A 的互补事件记作 A’，其概率为 P(A’) = 1 − P(A)。
Two events are mutually exclusive if they cannot occur together; then P(A or B) = P(A) + P(B). For non‑mutually exclusive events, P(A or B) = P(A) + P(B) − P(A and B).
两个事件如果不可能同时发生，则称互斥；此时 P(A或B) = P(A) + P(B)。对于非互斥事件，P(A或B) = P(A) + P(B) − P(A且B)。
11. Probability Trees and Conditional Probability | 概率树与条件概率
A tree diagram helps visualise multiple stages of a probability experiment. Branches from each node represent possible outcomes with their probabilities; the probabilities on branches from a single node sum to 1. To find the probability of a combination of events, multiply along the branches.
树形图可将多阶段的概率实验可视化。每个节点发出的分支代表可能结果及其概率；同一节点各分支的概率之和为1。要计算组合事件的概率，沿分支相乘即可。
Conditional probability is the probability of event A given that event B has occurred, written P(A|B) = P(A and B) / P(B). Tree diagrams are particularly helpful for conditional problems, where the probabilities on the second set of branches depend on the first outcome.
条件概率是在事件B已发生的条件下事件A发生的概率，记作 P(A|B) = P(A且B) / P(B)。树形图对于条件问题尤其有用，因为第二层分支的概率依赖于第一层的结果。
Events A and B are independent if P(A|B) = P(A) or, equivalently, P(A and B) = P(A) × P(B). Always check for independence before applying the multiplication rule.
若 P(A|B) = P(A) 或等价地 P(A且B) = P(A) × P(B)，则事件A和B相互独立。在应用乘法规则前，请务必检验独立性。
12. Statistical Calculations and Interpretation | 统计计算与解读
Throughout the syllabus, emphasis is placed on interpreting statistical measures and diagrams in context. It is not enough to compute the mean or draw a histogram; you must explain what the results tell you about the data.
整个课程大纲强调结合具体情境解释统计量数和图表。仅仅计算出平均值或绘制直方图是不够的，你必须说明结果揭示了数据的什么信息。
Comparing data sets often involves commenting on both the central tendency (mean, median) and the spread (IQR, standard deviation). For example, ‘Class A has a higher median score and a smaller IQR, suggesting more consistent performance.’
比较数据集时，通常需要对集中趋势（平均数、中位数）和离散程度（IQR、标准差）两方面进行评论。例如，“A班中位数分数更高且IQR更小，表明成绩更稳定。”
Beware of misleading graphs where the axis scales are chopped or distorted, or where pictograms use disproportionate areas. Always check the labels and scales before drawing conclusions.
要警惕具有误导性的图表，例如坐标轴刻度被截断或扭曲，或象形图使用了不成比例的面积。在得出结论前，请始终检查标签和刻度。
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