📚 IGCSE Statistics Core Concepts Review | IGCSE 统计核心知识点梳理
Statistics provides the tools to collect, organise, analyse, interpret, and present data in a meaningful way. In the CAIE IGCSE syllabus, students explore how statistical thinking helps us make informed decisions in real-world contexts, from business and science to everyday life. This article reviews the core topics Year 10 learners need to master, covering types of data, sampling, graphical displays, measures of centre and spread, probability, distributions, correlation, regression, and time series.
统计学为我们提供了收集、整理、分析、解释和有意义地呈现数据的工具。在 CAIE IGCSE 大纲中，学生将探索统计思维如何帮助我们在商业、科学乃至日常生活中做出明智决策。本文梳理了 Year 10 学生需要掌握的核心主题，涵盖数据类型、抽样、图表展示、集中趋势与离散程度的度量、概率、分布、相关性、回归以及时间序列。
1. Types of Data | 数据类型
Data can be classified as qualitative (categorical) or quantitative (numerical). Qualitative data describe qualities or characteristics, such as eye colour or type of car, while quantitative data represent amounts or measurements. Quantitative data are further divided into discrete (countable, e.g. number of siblings) and continuous (measurable, e.g. height, time).
数据可分为定性数据（分类数据）和定量数据（数值数据）。定性数据描述特性或类别，例如眼睛颜色或汽车类型；定量数据则表示数量或测量值。定量数据进一步分为离散数据（可数，例如兄弟姐妹的数量）和连续数据（可测量，例如身高、时间）。
Recognising data type is the first step in choosing appropriate statistical tools. For example, we can calculate a mean for quantitative data but not for qualitative categories. Categorical data are often summarised using frequencies and modes, while numerical data support a wider range of summary statistics.
识别数据类型是选择合适统计工具的第一步。例如，我们可以计算定量数据的平均数，但不能计算定性类别的平均数。分类数据常用频数和众数进行汇总，而数值数据则支持更丰富的数据汇总量。
2. Sampling Techniques | 抽样方法
Because collecting data from an entire population is often impractical, we rely on samples. A sample must be representative and free from bias. Common sampling methods include simple random sampling (every member has an equal chance), stratified sampling (population divided into subgroups, then random samples taken proportionally), systematic sampling (selecting every k-th item), and quota sampling (non-random, meeting fixed quotas in each subgroup).
由于从全体总体收集数据往往不切实际，我们依赖样本。样本必须具有代表性且没有偏差。常见的抽样方法包括简单随机抽样（每个成员被抽中的概率相等）、分层抽样（将总体划分为子群，再按比例随机抽样）、系统抽样（每隔 k 个单位抽取一个）以及配额抽样（非随机抽样，满足每个子群的固定配额）。
Each method has strengths: random and stratified sampling reduce bias, while systematic sampling is easy to implement. Quota sampling is quick and cheap but can introduce subjectivity. In the exam, you may be asked to recognise the method used, evaluate its suitability, and suggest improvements.
每种方法都有优势：随机抽样和分层抽样能减少偏差，系统抽样易于实施。配额抽样快速且成本低，但可能会引入主观性。在考试中，你可能会被要求识别所采用的方法、评价其适用性并提出改进建议。
3. Presenting Data | 数据展示
Data are communicated effectively through tables and diagrams. Frequency tables list values or class intervals with their frequencies. Tallies help when counting raw data. A typical grouped frequency table for continuous data might look like this:
通过表格和图示可以有效传达数据。频数表列出数值或组距及其频数。计数时可用划记法。对于连续数据，一个典型的分组频数表可能如下所示：
| Height (cm) | Tally | Frequency |
|---|---|---|
| 150 ≤ h < 160 | IIII | 4 |
| 160 ≤ h < 170 | IIII IIII | 9 |
| 170 ≤ h < 180 | IIII II | 7 |
| 180 ≤ h < 190 | III | 3 |
Graphical displays include bar charts for categorical or discrete data, histograms for continuous data (where area represents frequency), pie charts for proportions, and stem-and-leaf diagrams to preserve original values while showing shape. Box-and-whisker plots provide a five-number summary: minimum, lower quartile, median, upper quartile, and maximum.
图形展示包括用于分类或离散数据的条形图，用于连续数据的直方图（面积代表频数），用于比例的饼图，以及既能显示分布形状又能保留原始数值的茎叶图。箱形图则提供了五数概括：最小值、下四分位数、中位数、上四分位数和最大值。
4. Averages and Measures of Central Tendency | 平均数与集中趋势度量
The three main measures of centre are mean, median, and mode. The mean is the sum of all values divided by the count:
三种主要的集中趋势度量是平均数、中位数和众数。平均数等于所有数值之和除以数值的个数：
Mean x̄ = Σx / n
For grouped data, the mean is estimated using midpoints of intervals: x̄ = Σ(f × midpoint) / Σf.
对于分组数据，平均数用组中点进行估计：x̄ = Σ(频数 × 组中点) / 总频数。
The median is the middle value when data are ordered. If n is odd, it is the ((n+1)/2)-th value; if n is even, it is the average of the (n/2)-th and (n/2 +1)-th values. The mode is the most frequent value. The median is not affected by outliers, making it useful for skewed distributions.
中位数是排序后居于中间位置的数据。如果 n 为奇数，则是第 ((n+1)/2) 个值；如果 n 为偶数，则是第 n/2 和 (n/2 +1) 个值的平均数。众数是出现次数最多的值。中位数不受极端值影响，因此适用于偏态分布。
5. Measures of Dispersion | 离散程度的度量
Dispersion describes how spread out the data are. The simplest measures are the range (max − min) and the interquartile range (IQR = Q₃ − Q₁), which covers the middle 50% of data. The IQR is resistant to outliers.
离散程度描述数据分散的程度。最简单的度量是极差（最大值 − 最小值）和四分位距（IQR = Q₃ − Q₁），它涵盖了中间 50% 的数据。IQR 不受极端值影响。
More sophisticated measures involve the deviation from the mean. The variance is the average of squared deviations, and the standard deviation is its square root:
更复杂的度量涉及与平均数的偏差。方差是偏差平方的平均数，标准差则是方差的平方根：
Population variance: σ² = Σ(xi − μ)² / N
Sample variance: s² = Σ(xi − x̄)² / (n − 1)
The standard deviation is widely used because it is in the same units as the data. A smaller standard deviation indicates data are closer to the mean.
标准差是广泛使用的度量，因为它与数据的单位相同。标准差越小，表示数据越集中在平均数附近。
6. Probability Theory | 概率基础
Probability measures the chance of an event occurring on a scale from 0 (impossible) to 1 (certain). The theoretical probability of event A is:
概率衡量事件发生的可能性，取值范围从 0（不可能）到 1（必然）。事件 A 的理论概率为：
P(A) = number of favourable outcomes / total number of outcomes
When probabilities are estimated from experiments, we call it experimental probability or relative frequency.
当概率通过实验进行估计时，我们称之为实验概率或相对频数。
Events can be mutually exclusive (cannot happen together) or independent (one does not affect the other). Key rules include the addition rule for mutually exclusive events, P(A ∪ B) = P(A) + P(B), and the multiplication rule for independent events, P(A ∩ B) = P(A) × P(B).
事件可以是互斥的（不能同时发生）或独立的（一个事件的发生不影响另一个）。关键规则包括互斥事件的加法法则 P(A ∪ B) = P(A) + P(B)，以及独立事件的乘法法则 P(A ∩ B) = P(A) × P(B)。
7. Probability Distributions | 概率分布
A probability distribution lists all possible outcomes of a random variable together with their probabilities. For discrete variables, the sum of all probabilities equals 1. The binomial distribution models the number of successes in a fixed number of independent trials, each with the same probability of success p:
概率分布列出了随机变量的所有可能取值及其对应的概率。对于离散变量，所有概率之和等于 1。二项分布用于描述固定次数独立试验中成功次数的分布，每次试验的成功概率为 p：
P(X = r) = ⁿCᵣ × pʳ × (1 − p)ⁿ⁻ʳ
For IGCSE Statistics, you should be able to calculate binomial probabilities using the formula and also recognise the shape of the normal distribution, a continuous, bell-shaped curve defined by mean μ and standard deviation σ. Key properties: symmetric about the mean, about 68% of data lie within 1σ of the mean, 95% within 2σ, and 99.7% within 3σ.
在 IGCSE 统计中，你需要能够使用公式计算二项概率，同时也要能识别正态分布的形状——这是一种由均值 μ 和标准差 σ 确定的连续型钟形曲线。关键性质：关于均值对称；大约 68% 的数据落在均值 ±1σ 内，95% 落在 ±2σ 内，99.7% 落在 ±3σ 内。
8. Scatter Diagrams and Correlation | 散点图与相关性
A scatter diagram is used to display the relationship between two quantitative variables. Each point represents a pair (x, y). The overall pattern reveals the correlation: positive (as x increases, y tends to increase), negative (as x increases, y tends to decrease), or zero (no clear pattern).
散点图用于展示两个定量变量之间的关系。每个点代表一组 (x, y) 数据。整体形态显示出相关性：正相关（x 增大时 y 也倾向于增大）、负相关（x 增大时 y 倾向于减小）或零相关（无明显规律）。
The strength of linear correlation is measured by the product-moment correlation coefficient, often denoted r. The value of r lies between −1 and +1. A value close to 1 indicates strong positive correlation, close to −1 indicates strong negative correlation, and around 0 indicates weak or no linear correlation. Outliers can greatly influence r.
线性相关性的强度用积矩相关系数（通常记为 r）衡量。r 的值介于 −1 与 +1 之间。接近 1 表示强正相关，接近 −1 表示强负相关，接近 0 表示线性相关性弱或不存在。异常值会显著影响 r。
9. Linear Regression | 线性回归
When a scatter diagram shows a linear trend, we can model the relationship with a regression line (line of best fit) of the form y = a + bx. The slope b gives the change in y for a unit increase in x. The coefficients are calculated as:
当散点图呈现线性趋势时，我们可以用一条形如 y = a + bx 的回归直线（最佳拟合线）来建模。斜率 b 表示 x 每增加一个单位时 y 的变化量。系数计算公式如下：
b = Σ((xi − x̄)(yi − ȳ)) / Σ((xi − x̄)²)
a = ȳ − b x̄
Once the equation is obtained, it can be used to estimate values. Interpolation (predicting within the data range) is reliable, while extrapolation (predicting beyond the range) is risky because the linear relationship may not hold.
得到方程后，就可以用它进行估算。内插（在数据范围内预测）比较可靠，而外推（预测超出范围的值）则存在风险，因为线性关系可能不成立。
It is customary to write the regression line in the form y = a + bx and to interpret the coefficients in context. In the IGCSE Statistics exam, you may be asked to plot the line, calculate a and b from summary statistics, and comment on the reliability of predictions.
通常我们会将回归直线写成 y = a + bx 的形式，并结合实际背景解释系数。在 IGCSE 统计考试中，你可能会被要求画出回归直线、根据汇总统计量计算 a 和 b，并就预测的可靠性进行评论。
10. Time Series and Moving Averages | 时间序列与移动平均
A time series is a set of observations recorded at regular intervals over time (e.g. monthly sales). It can show a trend (long-term movement), seasonal variation (regular pattern within a year), and random fluctuations.
时间序列是随时间按固定间隔记录的一组观测值（例如月度销售额）。它能够显示出趋势（长期变动）、季节性波动（一年内的规律性模式）以及随机波动。
To smooth out short-term fluctuations and reveal the trend, we calculate moving averages. For quarterly data, a four-point moving average is commonly used: average the first four values, then drop the first and add the fifth, and so on. These averages can then be centred to align with time points. The smoothed trend line helps with forecasting future values, though such forecasts assume the past pattern continues.
为了消除短期波动并揭示趋势，我们会计算移动平均数。对于季度数据，常使用四点移动平均：先求前四个值的平均数，然后去掉第一个值并加入第五个值，依此类推。这些平均数可再通过居中处理以对准时间点。平滑后的趋势线有助于预测未来值，但这样的预测基于历史模式会持续下去的假设。
Understanding time series prepares students for more advanced statistical work and supports data interpretation in economics, business, and science.
理解时间序列不仅为学生进行更高级的统计学习打下基础，也能帮助他们解释经济学、商业和科学领域中的数据。
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