📚 GCSE Eduqas Statistics: Core Knowledge Summary | GCSE Eduqas 统计：核心知识点梳理
Statistics is about collecting, organising, analysing and interpreting data in order to make informed decisions. In the GCSE Eduqas Statistics specification, you will learn how to handle different types of data, choose appropriate sampling methods, summarise data using averages and measures of spread, create and interpret various diagrams, analyse relationships between variables, and understand probability to make predictions. This article brings together all the core knowledge you need to master, structured for effective revision.
统计学研究的是如何收集、整理、分析和解释数据，从而做出明智的决策。在 GCSE Eduqas 统计课程中，你将学习如何处理不同类型的数据、选择合适的抽样方法、利用平均数和离散程度指标概括数据、绘制并解读各种统计图、分析变量间的关系，以及理解概率来进行预测。本文梳理了你需要掌握的全部核心知识点，助你高效复习。
1. Types of Data | 数据的类型
Data can be classified as qualitative (non-numerical, e.g. eye colour) or quantitative (numerical). Quantitative data is further divided into discrete (countable, e.g. number of pets) and continuous (measurable, e.g. height in cm). Understanding data types is essential because it determines which statistical tools and diagrams are appropriate.
数据可分为定性数据（非数值，如眼睛颜色）和定量数据（数值）。定量数据又分为离散型（可数的，例如宠物数量）和连续型（可测量的，例如身高厘米数）。理解数据类型至关重要，因为它决定了使用的统计工具和图表。
Primary data is collected directly by the researcher (e.g. a survey), while secondary data is obtained from existing sources (e.g. government reports). Primary data allows control over collection methods, but secondary data is often quicker to access.
一手数据由研究人员直接收集（如调查），二手数据则来自已有来源（如政府报告）。一手数据可以控制收集方式，但二手数据通常获取更快。
2. Data Collection and Questionnaires | 数据收集与问卷调查
Well-designed questionnaires are crucial for gathering reliable primary data. Questions should be clear, unbiased, and not leading. Avoid overlapping response options and ensure a pilot survey is carried out to test the design before full distribution.
设计良好的问卷是收集可靠一手数据的关键。问题应明确、无偏见且不具引导性。避免选项重叠，并确保在全面发放前进行试点调查来检验设计。
A sampling frame is a list of all members of the population. If the sampling frame is incomplete or biased, the results may not truly represent the population. Random sampling methods help reduce bias, but practical constraints often lead to non-random methods.
抽样框是总体所有成员的名单。如果抽样框不完整或带有偏见，结果可能无法真正代表总体。随机抽样方法有助于减少偏差，但实际限制常导致使用非随机方法。
3. Sampling Methods | 抽样方法
Simple random sampling gives every member of the population an equal chance of selection, often using random number generators. Systematic sampling selects items at regular intervals from an ordered list. Stratified sampling divides the population into groups (strata) and takes a proportional random sample from each, ensuring representation of key subgroups.
简单随机抽样让总体中每个成员都有同等被选中的机会，常用随机数生成器实现。系统抽样从有序列表中按固定间隔选择样本。分层抽样将总体划分为若干层，然后从每一层按比例随机抽取样本，确保了关键子群的代表性。
Non-random methods include quota sampling (selecting a fixed number from each category, often based on convenience) and opportunity sampling (choosing whoever is available). These are quicker and cheaper but more prone to bias. A key skill is to critique a sampling method for potential bias and suggest improvements.
非随机方法包括配额抽样（从每类中选取固定数量，常基于便利性）和机会抽样（选择任何可及的对象）。这些方法更快、成本更低，但更易产生偏差。批判抽样方法的潜在偏差并提出改进建议是一项关键技能。
4. Frequency Tables and Diagrams | 频率表与统计图
Data can be summarised in frequency tables, which may include tally marks. For discrete data, simple bar charts or pictograms are suitable. For continuous data, histograms with equal class intervals are drawn with frequency on the vertical axis. If class intervals are unequal, frequency density (frequency ÷ class width) must be used for the height of bars.
数据可以用频率表汇总，可包含画记符号。对于离散数据，适合使用简单条形图或象形图。对于连续数据，等组距的直方图以频率为纵轴。若组距不等，必须用频率密度（频率 ÷ 组距）作为条形高度。
0°), stem-and-leaf diagrams (retaining original values), and population pyramids. Scaled diagrams require careful labelling and titles.
其他图表包括饼图（扇区角度 = (频数/总数) × 360°）、茎叶图（保留原始数值）和人口金字塔。按比例绘制的图表需要仔细标注和加标题。
5. Measures of Central Tendency and Spread | 集中趋势与离散程度
The three main averages are mean, median, and mode. The mean (x̄ d by outliers. The median is the middle value when data is ordered, unaffected by outliers. The mode is the most frequent value. Choosing the best average to represent a dataset is a common exam question.
三个主要平均数是均值、中位数和众数。均值 (x̄ = Σx/n) 使用了所有数据，但受异常值影响。中位数是排序后中间的值，不受异常值影响。众数是出现次数最多的值。选择最合适的平均数代表数据集是常见考点。
Measures of spread include range (max – min), interquartile range (IQR = Q₃ – mple is calculated using squared deviations from the mean. For grouped data, midpoints are used.
离散程度指标包括极差（最大值 – 最小值）、四分位距 (IQR = Q₃ – Q₁) 和标准差。较小的 IQR 或标准差表示变异性较小。总体标准差 σ 或样本标准差 s 通过离均差平方和计算。对于分组数据，使用组中值进行计算。
| Measure | Formula | Sensitive to Outliers? |
|---|---|---|
| Mean | Σx/n | Yes |
| Median | Middle value | No |
| Range | max – min | Yes |
| IQR | Q₃ – Q₁ | No |
6. Cumulative Frequency and Box Plots | 累积频率与箱线图
A cumulative frequency table adds up frequencies as you go; a cumulative frequency graph plots the running total against the upper class boundary. This graph is used to estimate medians, quartiles and percentiles. Drawing a smooth curve is important for accurate reading.
累积频率表逐次累加频率；累积频率图以累计频数对上组界绘制。该图用于估计中位数、四分位数和百分位数。绘制平滑曲线对准确读取至关重要。
hting skewness, and identifying outliers. An outlier is often defined as a value lying more than 1.5 × IQR below Q₁ or above Q₃.
箱线图（箱须图）展示了最小值、Q₁、中位数、Q₃ 和最大值。它们非常适合比较分布、突出偏态和识别异常值。异常值通常定义为低于 Q₁ – 1.5×IQR 或高于 Q₃ + 1.5×IQR 的值。
7. Scatter Diagrams and Correlation | 散点图与相关性
A scatter diagram helps visualise the relationship between two variables. Positive correlation means as one variable increases, the other tends to increase. Negative correlation means one increases as the other decreases. No correlation shows no clear pattern. Correlation does not imply causation.
散点图用于可视化两个变量间的关系。正相关表示一个变量增加，另一个也趋向增加。负相关表示一个增加，另一个减少。无相关则无明显模式。相关性并不意味着因果关系。
A line of best fit (drawn by eye) can be used to make predictions (interpolation within the data range and extrapolation outside, which is less reliable). Spearman's rank correlation coefficient provides a numerical measure of correlation strength for monotonic relationships, especially with ranked data.
最佳拟合线（目测绘制）可用于预测（在数据范围内内插，外推较不可靠）。斯皮尔曼等级相关系数为单调关系提供了数值化的相关强度度量，特别适用于等级数据。
8. Time Series and Moving Averages | 时间序列与移动平均
A time series is a set of data recorded over time (e.g. monthly sales). Time series graphs often show seasonal fluctuations and long-term trends. To identify the trend, moving averages are calculated – typically for an odd number of periods so the average can be centred.
时间序列是一组按时间记录的数据（如月度销售额）。时间序列图常显示季节性波动和长期趋势。为识别趋势，需计算移动平均——通常取奇数期数，以便将平均值对中。
After plotting moving averages on the graph, a trend line can be drawn. Seasonal variation is the difference between the actual data and the trend line. Forecasting future values can be done by extending the trend line and adding average seasonal effects.
在图上标出移动平均后，可绘制趋势线。季节变异是实际数据与趋势线之差。预测未来值可通过延伸趋势线并加上平均季节效应来实现。
9. Basic Probability | 基础概率
ble outcomes / total number of outcomes. The sum of probabilities of all mutually exclusive outcomes in a sample space is 1.
概率衡量事件发生的可能性，范围从 0（不可能）到 1（必然）。对于等可能结果，P(事件) = 有利结果的数量 / 总结果数量。样本空间中所有互斥结果的概率总和为 1。
Relative frequency from an experiment can be used to estimate probability when theoretical calculations are not possible. The larger the number of trials, the closer the relative frequency tends to the theoretical probability (the law of large numbers).
实验得出的相对频率可用于估计概率（当无法理论计算时）。试验次数越多，相对频率越趋于理论概率（大数定律）。
10. Combined Events and Expectation | 组合事件与期望值
For combined events, sample space diagrams (listing outcomes) or two-way tables help find probabilities of 'and'/'or' scenarios. Tree diagrams are used for successive events, multiplying along branches for intersections and adding probabilities from different branches for unions.
对于组合事件，样本空间图（列出结果）或双向表有助于求出“且”/“或”情景的概率。树图用于相继事件，沿分支相乘求交集概率，将不同分支概率相加求并集概率。
umber of trials. This concept is used in scenarios like predicting how many times a specific outcome will occur. The simulation of random events using random digits can model real situations.
期望频数 = 概率 × 试验次数。该概念用于预测某特定结果将发生多少次。利用随机数字模拟随机事件可以建模真实情境。
11. Statistical Inference and Comparisons | 统计推断与比较
Inferential statistics allows conclusions about a population based on sample data. Students should be able to compare two data sets using averages and measures of spread, and draw conclusions in context. Phrases like “on average, … is higher, and more consistent because the IQR is smaller” show clear comparative reasoning.
推断统计学允许基于样本数据得出关于总体的结论。学生应能利用平均数和离散程度指标比较两个数据集，并在相应语境中得出结论。像“平均而言，……更高，且因 IQR 更小而更稳定”这样的表述展示清晰的比较推理。
Recognising bias in sampling, poorly worded questions, or non-responses is critical. Conclusions must not over-reach; they should reference the sample and acknowledge limitations.
识别抽样、问题措辞不当或无应答中的偏差至关重要。结论不能过分外推；应当提及样本并承认局限性。
12. Quality Assurance and Statistical Enquiry Cycle | 质量保证与统计探究循环
The statistical enquiry cycle (Problem, Plan, Data, Analysis, Conclusion) underpins every investigation. Starting with a clear hypothesis or question, planning what data to collect, collecting it cleanly, analysing with appropriate techniques, and forming a conclusion that relates back to the original problem are all essential.
统计探究循环（问题、计划、数据、分析、结论）是每一项调查的基础。从明确的假设或问题开始，计划收集什么数据，干净地收集数据，用适当技术分析，并形成与原始问题相关的结论，这些环节都至关重要。
Quality assurance includes data cleaning, checking for errors, and ensuring ethical practices. This may involve identifying rogue values and deciding whether to exclude them from analysis based on valid reasons.
质量保证包括数据清洗、错误检查及确保道德规范。这可能涉及识别异常值，并基于合理理由决定是否将其从分析中剔除。
Published by TutorHao | Statistics Revision Series | aleveler.com
更多咨询请联系16621398022（同微信）
或截图后用「扫一扫 → 相册」选择本图