📚 Year 10 Edexcel Statistics: High-Frequency Topics and Common Mistake Analysis | Year 10 Edexcel 统计：高频考点与易错题分析
Mastering Year 10 Edexcel Statistics requires a solid understanding of key topics and the ability to avoid common errors that often appear in assessments. This guide highlights the most frequently examined content areas - data types, sampling methods, presenting and summarising data, correlation, time series and probability - and breaks down the typical mistakes students make, helping you to focus your revision and improve exam performance.
掌握 Year 10 Edexcel 统计需要扎实理解重点内容，并能避开考试中反复出现的常见错误。本指南汇总了最高频的考点——数据类型、抽样方法、数据呈现与概括、相关性、时间序列和概率——并逐一分析学生容易失分的地方，帮助你更有针对性地复习，提升应试表现。
The advice below is written for the Pearson Edexcel GCSE Statistics specification, which is normally started in Year 10. Every section follows the same pattern: first the knowledge you must be able to recall, then the errors that examiners see most often, and finally a short strategy for avoiding them.
以下内容针对 Pearson Edexcel GCSE Statistics 考纲，这一课程通常在 Year 10 开始学习。每一节的思路一致：先讲必须掌握的知识点，再讲考官最常看到的错误，最后给出简短的避坑策略。
1. Types of Data and the Classification Checklist | 数据类型与分类清单
Understanding data types (qualitative, quantitative discrete, quantitative continuous) is the foundation of the whole course. Every later decision - which average to use, which graph to draw, which test is appropriate - depends on classifying the variable correctly.
理解数据类型（定性数据、定量离散数据、定量连续数据）是整门课程的基础。之后每一个决定——用哪种平均数、画哪种图、选哪种方法——都取决于你是否把变量分类正确。
- Qualitative (categorical) data: described by words or labels, e.g. eye colour, favourite subject, type of transport.
- Quantitative discrete data: obtained by counting, e.g. number of students in a class, number of goals scored.
- Quantitative continuous data: obtained by measuring, e.g. height, mass, time, temperature.
- 定性（类别）数据：用文字或标签描述，例如眼睛颜色、最喜欢的科目、出行方式。
- 定量离散数据：通过计数得到，例如班级学生人数、进球数。
- 定量连续数据：通过测量得到，例如身高、质量、时间、温度。
Remember that quantitative data can be either discrete (counted, e.g. number of students) or continuous (measured, e.g. height). Identifying this correctly affects how data is presented and analysed. Misclassifying continuous data as discrete often leads to inappropriate graph choices such as a bar chart instead of a histogram.
请记住，定量数据可以是离散的（计数，如学生人数）或连续的（测量值，如身高）。正确区分这一点会影响数据展示和分析的方式。错误地把连续数据当作离散数据处理，常会导致图表选择不当，比如该用直方图却画了条形图。
A good habit is to ask two questions in order: "Is the answer a word or a number?" and then "Was it counted or measured?" A quick mental test also helps - if the value could sensibly take a decimal such as 172.5 cm, the variable is almost certainly continuous.
一个好习惯是按顺序问自己两个问题："答案是文字还是数字？"然后是"它是数出来的还是量出来的？"再做一个小测试：如果这个数值可以合理地出现小数，比如 172.5 cm，那么它几乎一定是连续变量。
2. Sampling Methods: Random, Systematic, Stratified, Quota and Opportunity | 抽样方法：随机、系统、分层、配额与便利抽样
Exam questions often test the ability to identify the most appropriate sampling method for a given scenario, and to justify it in context. You should be able to name a method, describe exactly how to carry it out, and state one advantage and one disadvantage.
考试常会考查在特定场景中选择最合适的抽样方法，并结合情境说明理由。你需要能说出方法名称、准确描述操作步骤，并各写出一个优点和一个缺点。
| Method | 方法 | Key feature | 关键特征 | Typical weakness | 典型缺点 |
| Simple random | 简单随机 | Every member of the population has an equal chance | 总体中每个个体机会均等 | Needs a complete sampling frame | 需要完整的抽样框 |
| Systematic | 系统 | Choose every k-th item from an ordered list | 从有序名单中每隔 k 个抽取一个 | Can be biased if the list has a pattern | 若名单本身有规律，可能产生偏差 |
| Stratified | 分层 | Sample proportionally from each subgroup | 按比例从各子群中抽样 | Needs clear strata and their sizes | 需要明确的层及各层人数 |
| Quota | 配额 | Interviewer fills a fixed quota per group | 访问员按组别凑满固定配额 | Interviewer choice introduces bias | 访问员的选择会引入偏差 |
| Opportunity (convenience) | 便利（偶遇） | Take whoever is easiest to reach | 就近、就便选取对象 | Not representative of the population | 不能代表总体 |
A common mistake is using a sampling method that introduces bias. For example, choosing a convenience sample may appear quick but does not represent the population. Interviewing people outside a gym about exercise habits will clearly over-represent regular exercisers, no matter how many people you ask.
一个常见的错误是使用会引入偏差的抽样方法。比如，选择便利样本看似快捷，但不能代表总体。在健身房门口调查运动习惯，无论问多少人，都会明显过度代表经常锻炼的人群。
Another frequent slip is describing a method vaguely. "Pick 50 people randomly" earns little credit; "number the 600 students from 1 to 600 and use a random number generator to select 50 different numbers" does. Always state the sampling frame, the sample size and the exact selection rule.
另一个常见的失误是描述过于笼统。"随便挑 50 个人"几乎拿不到分；"把 600 名学生编号 1 至 600，用随机数生成器选出 50 个不重复的号码"才能得分。务必写明抽样框、样本量以及具体抽取规则。
3. Primary vs Secondary Data and Sources of Bias | 一手数据、二手数据与偏差来源
Primary data is collected first-hand by you for your own investigation; secondary data already exists, for example in a published report, a government database or a previous study. Both have advantages, and the choice depends on time, cost and the accuracy you need.
一手数据是你为自身调查直接收集的数据；二手数据是已经存在的数据，例如公开报告、政府数据库或前人研究。两者各有优势，选择取决于时间、成本和你所需的准确度。
- Primary data: controlled by you, fits your question exactly, but slow and expensive to collect.
- Secondary data: fast and often free, large in scale, but you cannot check how it was collected and it may be out of date.
- 一手数据：由你掌控，完全贴合你的问题，但收集慢、成本高。
- 二手数据：快速、常常免费、规模大，但你无法核实其收集方式，且可能已经过时。
A common mistake is confusing primary and secondary data, or using a sampling method that introduces bias. Knowing the definitions is not enough - you must be able to judge whether a given source is reliable, and to identify the specific weakness in a questionnaire or data-collection plan.
一个常见的错误是混淆一手数据和二手数据，或使用会引入偏差的抽样方法。仅仅知道定义还不够——你必须能判断某个数据来源是否可靠，并能指出问卷或数据收集方案中的具体缺陷。
Watch for these classic sources of bias: leading or emotive question wording ("Don't you agree that..."), overlapping or non-exhaustive response boxes, asking about the distant past, non-response (people who ignore the survey are often different from those who reply), and self-selection in online polls.
请注意这些经典偏差来源：带有引导性或情绪化的措辞（"难道你不认为……"）、选项重叠或未穷尽、询问过于久远的事情、无应答（不回复的人往往与回复者不同），以及网络投票中的自我选择。
4. Stratified Sampling Calculations | 分层抽样的计算
Stratified sampling is frequently required when the population contains clearly defined subgroups, yet students sometimes forget to calculate the correct number from each stratum using the fraction sample size ÷ population size. The rule is simple and should be memorised as a proportion.
当总体包含明显子群时，常需用分层抽样，但学生有时忘记用 (样本量 ÷ 总体量) 的比例去计算每层应抽取的正确数量。规则很简单，应把它记成比例关系。
Number from a stratum = (stratum size ÷ population size) × sample size
20 ÷ 720) × 90 = 40, Year 11 gives (240 ÷ 720) × 90 = 30, and Year 12 gives (160 ÷ 720) × 90 = 20. The three values sum to 90, which is the check that everything is correct.
例如，某校有 720 名学生：Year 10 有 320 人，Year 11 有 240 人，Year 12 有 160 人。需要抽取 90 人的分层样本。Year 10 为 (320 ÷ 720) × 90 = 40，Year 11 为 (240 ÷ 720) × 90 = 30，Year 12 为 (160 ÷ 720) × 90 = 20。三者相加正好等于 90，这就是检查计算是否正确的方法。
The most common errors are: dividing by the wrong total, rounding each stratum casually so the parts no longer add up to the sample size, and forgetting to explain that the sample is then selected randomly within each stratum. If rounding is unavoidable, adjust the stratum with the largest remainder so the total still matches.
最常见的错误有：除以了错误的总数；随意取整导致各层人数加不回样本量；忘记说明随后要在每一层内部再随机抽取。如果必须取整，就调整余数最大的那一层，使总数依然吻合。
5. Presenting Data: Bar Charts, Histograms and Frequency Density | 数据呈现：条形图、直方图与频率密度
The choice of diagram is decided by the type of data. Bar charts suit discrete or qualitative data and have gaps between the bars. Histograms suit continuous data, have no gaps, and the area of each bar - not its height - represents the frequency.
图表的选择取决于数据类型。条形图适用于离散数据或定性数据，柱与柱之间有间隔。直方图适用于连续数据，柱之间没有间隔，而且代表频数的是每个柱的面积，而不是高度。
Frequency density = frequency ÷ class width
When class widths are unequal, you must work out frequency density before drawing. A class with width 10 and frequency 40 has frequency density 4 and must be drawn twice as tall as a class with width 20 and frequency 40, which has frequency density 2. Plot continuous data against class boundaries, and always label both axes with units.
当组距不相等时，必须先算出频率密度再作图。组距为 10、频数为 40 的组，频率密度为 4，其柱高必须是组距为 20、频数为 40（频率密度为 2）那一组的两倍。连续数据应画在组界上，并且两个坐标轴都要标注单位。
Typical mistakes include drawing bars of equal width regardless of the class intervals, plotting bars at midpoints rather than class boundaries, leaving gaps in a histogram, and forgetting to add a key or axis scale. In cumulative frequency and histogram questions, using the midpoint instead of the upper class boundary is one of the most heavily penalised errors.
典型错误包括：不考虑组距而画出等宽的柱；把柱画在中点而不是组界上；在直方图中留下空隙；忘记加图例或坐标轴刻度。在累积频数与直方图题目中，用组中值代替上组界，是被扣分最严重的错误之一。
6. Averages: Mean, Median, Mode and the Weighted Mean | 平均数：均值、中位数、众数与加权平均
You must be able to find the mean, median and mode from raw data, from a frequency table and from grouped data, and to explain which average is most suitable in a given situation.
你需要能从原始数据、频数表和分组数据中求出均值、中位数和众数，并说明在特定情境下哪种平均数最合适。
Mean = Σ(f × x) ÷ Σf | Estimated mean from grouped data = Σ(f × midpoint) ÷ Σf
The mean uses every value and is affected by extreme values (outliers). The median is resistant to outliers and is preferred with skewed data such as house prices or incomes. The mode is the only average that can be used for qualitative data, and it is useful for identifying the most popular choice.
均值用到了每一个数值，会受极端值（离群值）影响。中位数不受离群值影响，适合房价、收入等偏态数据。众数是唯一可用于定性数据的平均数，适合用来找最受欢迎的选择。
idpoint is 25), dividing by the number of classes instead of Σf, forgetting that grouped data gives only an estimate, and muddling the median with the mean when interpreting a real-world context. Always finish with a sentence that refers back to the question, for example "the mean waiting time was 12.4 minutes".
这里常见错误很多：读错组中值（20 ≤ x < 30 这一组的组中值是 25）；除的是组数而不是 Σf；忘记分组数据只能给出估计值；以及在解释实际情境时把中位数和均值混为一谈。答题时最后一定要回到问题本身，例如"平均等待时间为 12.4 分钟"。
7. Measures of Spread: Range, Quartiles, IQR and Standard Deviation | 离散程度：极差、四分位数、四分位距与标准差
Averages alone never tell the whole story. Two classes may both average 60 marks while one is consistent and the other contains both very high and very low scores. Measures of spread describe that consistency.
只看平均数永远不够。两个班的平均分可能都是 60 分，但一个班成绩稳定，另一个班却高低分悬殊。离散程度就是用来描述这种稳定性的。
| Measure | 指标 | Formula | 公式 | Note | 说明 |
| Range | 极差 | highest − lowest | Uses only two values | 只用到两个数值 |
| Interquartile range | 四分位距 | IQR = Q₃ − Q₁ | Ignores the extreme 25% at each end | 忽略两端各 25% 的极端值 |
| Standard deviation | 标准差 | s = √(Σ(x − x̄)² ÷ n) | Uses every value | 用到每一个数值 |
Standard deviation is a measure of how far, on average, each value lies from the mean. A small standard deviation means the data are clustered close to the mean; a large one means they are widely spread. Because it uses every value, it is more sensitive than the range or IQR, and it is essential when comparing two distributions in a formal way.
标准差衡量的是各数值平均而言偏离均值多远。标准差小说明数据集中在均值附近；标准差大说明数据分散。由于它用到了每一个数值，它比极差或四分位距更敏感，在正式比较两组分布时不可或缺。
Frequent errors include: subtracting the mean before squaring instead of squaring first; forgetting the square root at the end; writing the IQR as Q₁ − Q₃ and obtaining a negative value; and quoting a range when the question asks about consistency, since a single extreme value can destroy the range as a useful measure.
常见错误包括：先减均值再平方（顺序反了）；最后忘记开平方；把四分位距写成 Q₁ − Q₃ 得出负值；以及题目问一致性时却报出极差——因为一个极端值就足以让极差失去参考价值。
8. Cumulative Frequency Graphs and Box Plots | 累积频数图与箱线图
Cumulative frequency is a running total of frequencies. You plot each cumulative total against the upper class boundary of its class, join the points with a smooth curve, and then read off values for the median, the lower quartile and the upper quartile.
累积频数是频数的累加。作图时把每个累积总数画在对应组的上组界上，用平滑曲线连接各点，然后从图上读出中位数、下四分位数和上四分位数。
Median at n ÷ 2 | Q₁ at n ÷ 4 | Q₃ at 3n ÷ 4
Box plots display the minimum, Q₁, median, Q₃ and maximum on a single scale, which makes them ideal for comparing two distributions quickly. When comparing, always comment on both an average and a measure of spread, and always in the context of the question.
箱线图把最小值、Q₁、中位数、Q₃ 和最大值画在同一条刻度上，非常适合快速比较两组分布。比较时既要谈平均数（中位数），也要谈离散程度，而且一定要结合题目情境。
Typical mistakes are plotting at the midpoint instead of the upper class boundary, using the wrong fraction of n, drawing a bar chart rather than a cumulative curve, forgetting to join the first point to the axis if the first class starts at 0, and giving a purely numerical comparison such as "the median is bigger" without saying what that means for the data.
典型错误包括：画在中点而不是上组界；用错 n 的比例；画成柱状图而不是累积曲线；若第一组从 0 开始却忘记把首个点连到坐标轴上；以及只作纯数字比较，例如"中位数更大"，却没有说明这对数据意味着什么。
9. Scatter Graphs, Correlation and Lines of Best Fit | 散点图、相关性与最佳拟合线
Scatter graphs show the relationship between two quantitative variables. Correlation may be positive or negative, and strong or weak; it can also be zero, meaning there is no linear relationship.
散点图展示两个定量变量之间的关系。相关性可以是正的或负的，可以是强的或弱的，也可能为零，即不存在线性关系。
A line of best fit should pass through the mean point (x̄, ȳ), have roughly the same number of points above and below it, and follow the general trend of the data. Use it to estimate values within the range of the data - that is interpolation. Extrapolation, estimating beyond the plotted range, is unreliable and should be avoided or explicitly questioned.
最佳拟合线应经过均值点 (x̄, ȳ)，上下两侧的点数大致相同，并顺着数据的整体趋势。用它来估计数据范围内的数值，这称为内插。而在已有数据范围之外进行外推则不可靠，应当避免，或明确指出其局限。
The single most important warning in this topic is that correlation does not imply causation. Ice-cream sales and sunburn cases rise together, but ice cream does not cause sunburn - hot weather drives both. Other errors include drawing the line through the origin by habit, joining the dots instead of drawing a single straight line, and describing a relationship as "positive" without any indication of strength.
本专题最重要的提醒是：相关不等于因果。冰淇淋销量与晒伤人数同向上升，但冰淇淋并不会导致晒伤——炎热的天气是共同原因。其他错误包括：习惯性地把直线画过原点；把点连成折线而不是画一条直线；以及只说关系是"正的"而不提强弱程度。
10. Time Series and Moving Averages | 时间序列与移动平均
A time series is a set of data recorded at regular intervals. Its two components are the trend, which is the underlying long-term direction, and seasonal variation, which is the repeating pattern within each cycle.
时间序列是按固定时间间隔记录的一组数据。它包含两个成分：趋势，即长期的潜在走向；以及季节变动，即每个周期内重复出现的规律。
A four-point moving average for quarterly data cancels the seasonal effect. Because four is an even number, the averages must be centred: take the mean of consecutive pairs of four-point totals and plot the result against the middle of the five quarters involved.
面对季度数据，四点移动平均可以消除季节影响。因为 4 是偶数，平均数必须居中处理：把相邻两组四点总和再取平均，并把结果画在这五个季度正中间的时点上。
Common mistakes include not centring an even-point moving average, plotting the moving average at the wrong time position, forgetting that the first and last two quarters of a four-point moving average cannot be calculated, and confusing the trend line with the original data. When asked to predict a future value, add the seasonal variation to the projected trend rather than reading the graph carelessly.
常见错误包括：偶数点移动平均未做居中处理；把移动平均数画在错误的时间位置；忘记四点移动平均中最初和最后两个季度的值无法计算；以及把趋势线与原始数据混为一谈。若要求预测未来数值，应把季节变动加到趋势预测值上，而不是随意读图。
11. Probability in a Statistics Context | 统计中的概率要点
Probability in GCSE Statistics is largely about expected frequency, mutual exclusivity and exhaustiveness, and the use of tree diagrams and two-way tables. The key relationship is simple and appears in almost every paper.
GCSE 统计中的
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