📚 Cambridge IGCSE Statistics Past Paper Deep Dive | 剑桥IGCSE统计学历年真题深度解析：掌握核心考点
Mastering Cambridge IGCSE Statistics requires more than just memorising formulas – it demands the ability to interpret exam questions, choose the right method, and present solutions clearly. This deep dive into past paper patterns covers the most frequent topics and typical pitfalls, helping Year 10 students build confidence for both Paper 1 and Paper 2.
掌握剑桥 IGCSE 统计学绝不只是背诵公式，还需要准确解读题意、选择正确方法并清晰呈现解答。这份对历年真题题型的深度解析涵盖了最高频的考点和常见失分点，帮助 Year 10 学生为 Paper 1 和 Paper 2 做好充分准备。
1. Cumulative Frequency Graphs | 累积频数图
Cumulative frequency questions appear almost every series. You are often given a table of grouped data and asked to construct a cumulative frequency curve. From the curve you must estimate the median, lower quartile (LQ), upper quartile (UQ) and interquartile range (IQR). A follow‑up question typically asks for the number of items above or below a particular value.
累积频数题目几乎每套试卷都会出现。通常会给出分组数据表，要求绘制累积频数曲线，并从曲线中估计中位数、下四分位数 (LQ)、上四分位数 (UQ) 和四分位距 (IQR)。后续问题往往会问有多少个数据项高于或低于某个特定值。
Example: The table shows the cumulative frequencies for the heights of 80 plants. Plot the curve and estimate the median height and the interquartile range. How many plants are taller than 25 cm?
例题：表格显示了 80 株植物高度的累积频数。请绘制曲线并估计高度中位数和四分位距。有多少株植物高于 25 cm？
To tackle this, set up your axes: the upper class boundaries on the horizontal axis and cumulative frequency (0 to total) on the vertical axis. Plot points at the end of each interval and join with a smooth curve. Do not use a ruler to connect points – a smooth freehand curve is expected. For the median, find the 40th value on the vertical axis, draw across to the curve and down to the horizontal axis. UQ is at the 60th value, LQ at the 20th. The IQR = UQ – LQ. To count plants taller than 25 cm, read the cumulative frequency at 25 cm and subtract from the total.
处理这类题目时，设置坐标轴：横轴为区间上限，纵轴为累积频数（0 到总数）。在每个区间末端描点，并用光滑曲线连接。不要用直尺连接点——考官期望看到手绘光滑曲线。求中位数时，在纵轴上找到第 40 个数据点，水平引线到曲线后垂直下落到横轴。UQ 在第 60 个值，LQ 在第 20 个。IQR = UQ – LQ。要数出高于 25 cm 的株数，先从曲线上读出 25 cm 处对应的累积频数，再用总数相减。
2. Histograms and Frequency Density | 直方图与频数密度
When class intervals are unequal, you must use frequency density to draw a histogram. Cambridge examiners frequently set questions where you calculate missing frequencies or complete a histogram. Remember: frequency density = frequency ÷ class width.
当组距不相等时，必须使用频数密度来绘制直方图。剑桥考官常出题要求计算缺失频数或补全直方图。记住：频数密度 = 频数 ÷ 组距。
Typical task: A histogram of journey times has bars of varying widths. The bar for 0 ≤ t < 10 has width 10 and height 2.5 cm. The bar for 10 ≤ t < 30 has width 20 and area 60 cm². Find the frequencies and construct the remaining bars.
典型任务：某行车时间直方图条形宽度不同。区间 0 ≤ t < 10 的条形宽为 10，高为 2.5 cm。区间 10 ≤ t < 30 的条形宽为 20，面积为 60 cm²。求出频数并补全其余条形。
In a histogram, the area of each bar is proportional to the frequency. The scale is usually given by a key, e.g. ‘1 cm² represents 2 journeys’. For the first bar, area = width × height = 10 × 2.5 = 25 cm². If 1 cm² = 2 units, frequency = 25 × 2 = 50. For the second bar, area = 60 cm², so frequency = 60 × 2 = 120. Once all frequencies are found, check that they sum to the total given. To draw a new bar, first calculate the required frequency density, then divide by the width to obtain the height in cm.
在直方图中，每个条形的面积与频数成比例。比例尺通常会给出，如‘1 cm² 代表 2 次行程’。第一条形的面积 = 宽 × 高 = 10 × 2.5 = 25 cm²。若 1 cm² = 2 个单位，则频数 = 25 × 2 = 50。第二条形面积 60 cm²，频数 = 60 × 2 = 120。求出所有频数后，核实总和是否等于给定总数。要绘制新条形，先计算所需的频数密度，再除以组宽得出条形在纸上的高度 (cm)。
3. Mean, Median and Mode for Grouped Data | 分组数据的平均数、中位数与众数
Grouped data questions require you to estimate the mean using midpoints. The modal class is the interval with the highest frequency. The median class is found by locating the n/2th value in the cumulative frequency column.
分组数据题目要求用组中值来估算平均数。众数所在组是频数最高的区间。中位数所在组可通过累积频数列定位第 n/2 个值找到。
Estimating the mean: Create a table with columns: class, midpoint (x), frequency (f), and fx. Use the formula Mean = Σfx / Σf. Give your answer to an appropriate degree of accuracy – usually to one or two decimal places more than the original data.
估算平均数：制作一个表格，列出：组别、组中值 (x)、频数 (f) 和 f × x。用公式 平均数 = Σfx / Σf 计算。答案的精密度通常比原始数据多一至两位小数。
For example, with intervals 10–19, 20–29 etc., the midpoint of the first is (10+19)/2 = 14.5. Multiply each midpoint by its frequency, sum the products and divide by the total frequency. Watch out: if the data are given as ‘0–9, 10–19’, the real class boundaries may be –0.5 to 9.5, but using the stated limits is usually acceptable unless told otherwise.
例如，区间为 10–19、20–29 等，第一组中值为 (10+19)/2 = 14.5。将每个组中值乘以该组频数，求总和再除以总频数。注意：如果数据表示为‘0–9, 10–19’，实际组界可能是 –0.5 到 9.5，但除非有说明，通常使用给定界限计算即可。
4. Calculating Standard Deviation Step by Step | 标准差逐步计算
Standard deviation is a regular feature in Cambridge Statistics papers. You may be asked to calculate it from raw data, a frequency table, or even to interpret it. The formula for a sample is s = √[ Σ(x – x̄)² / (n-1) ]. For a population it is σ = √[ Σ(x – μ)² / n ]. Learn to use your calculator’s statistics mode efficiently.
标准差是剑桥统计卷中的常客。考题可能要求根据原始数据、频数表计算，甚至要求解释其含义。样本标准差公式为 s = √[ Σ(x – x̄)² / (n-1) ]。总体标准差则为 σ = √[ Σ(x – μ)² / n ]。学会高效使用计算器的统计模式。
Worked example: The masses (g) of five eggs are 62, 58, 64, 60, 56. Calculate the mean and the sample standard deviation. Show clearly the sums of squares.
解答示例：五枚鸡蛋的质量 (g) 为 62, 58, 64, 60, 56。计算平均数和样本标准差，并清楚展示平方和。
Mean x̄ = (62+58+64+60+56)/5 = 300/5 = 60 g. Then find the deviations: 2, –2, 4, 0, –4. Square them: 4, 4, 16, 0, 16. Sum of squares Σ(x – x̄)² = 40. Sample standard deviation s = √(40 / (5-1)) = √(10) ≈ 3.16 g (3 s.f.). Always state formula, substitution and final value. Marks are awarded for method.
平均数 x̄ = (62+58+64+60+56)/5 = 300/5 = 60 g。然后求离差：2, –2, 4, 0, –4。平方得：4, 4, 16, 0, 16。平方和 Σ(x – x̄)² = 40。样本标准差 s = √(40 / (5-1)) = √(10) ≈ 3.16 g (保留三位有效数字)。务必写出公式、代入过程和最终结果，过程分同样重要。
5. Scatter Diagrams and Correlation | 散点图与相关性
Scatter diagram questions test your ability to plot points, describe correlation, and draw a line of best fit. Statements about correlation must be set in context: ‘There is a strong negative correlation between age and reaction time’ is better than ‘negative correlation’.
散点图类题目考查描点、描述相关性和绘制最佳拟合线的能力。对相关性的陈述必须结合背景：‘年龄与反应时间之间存在强负相关’比仅仅说‘负相关’得分更高。
A common past paper task gives a scatter graph and asks you to use the line of best fit to make an estimate. Distinguish between interpolation (within the range of data) and extrapolation (outside the range), which is unreliable. Show your working by drawing dashed lines on the graph.
常见的真题任务会给出散点图，要求利用最佳拟合线进行估算。要区分内插法（在数据范围内）和外推法（超出数据范围），外推结果不可靠。作答时在图上画出虚线以展示步骤。
When describing correlation, also comment on the strength (strong, moderate, weak) and direction (positive or negative). If the question asks ‘What does the scatter graph suggest about the relationship?’ your answer should mention both variables and any outliers.
描述相关性时，还应评论强度（强、中等、弱）和方向（正或负）。如果题目问‘散点图暗示了变量间怎样的关系？’你的回答需要提及两个变量以及任何异常值。
6. Linear Regression and the Least Squares Line | 线性回归与最小二乘线
The equation of the regression line is given in the form y = a + bx, where b = Sxy / Sxx and a = ȳ – b x̄. Past papers often test the interpretation of ‘a’ and ‘b’ in real-life terms. For example, ‘b’ represents the increase in y for each unit increase in x.
回归直线方程为 y = a + bx，其中 b = Sxy / Sxx，a = ȳ – b x̄。历年真题常考查对 a 和 b 的现实含义解释。例如，b 表示 x 每增加一个单位时 y 的增加量。
When using the regression equation for prediction, substitute the given x-value carefully. Always state that the prediction is only reliable if the value lies within the original data range. Cambridge mark schemes reward the comment about reliability.
用回归方程进行预测时，仔细代入给定的 x 值。一定要指出，只有当该值落在原始数据范围内时预测才可靠。剑桥评分标准对提及可靠性这一点给予加分。
Be comfortable with calculating Sxy = Σxy – (Σx Σy)/n and Sxx = Σx² – (Σx)²/n. Many errors happen when students forget to divide by n. Setting out a table with columns for x, y, xy, x², y² helps organise the work and reduces mistakes.
熟练掌握 Sxy = Σxy – (Σx Σy)/n 和 Sxx = Σx² – (Σx)²/n 的计算。很多错误发生在忘记除以 n 时。用表格列出 x, y, xy, x², y² 各列有助于组织计算、减少失误。
7. Probability Tree Diagrams | 概率树形图
Tree diagrams are essential for modelling successive events, especially ‘without replacement’ scenarios. Examiners want you to label branches with their probabilities, multiply along the branches for combined events, and add the probabilities of mutually exclusive outcomes.
树形图是建模连续事件的关键工具，尤其是‘不放回’情境。考官要求各分支标上概率，沿分支相乘求联合事件的概率，再将互斥结果的概率相加。
Classic question: A bag contains 4 red and 6 blue marbles. Two marbles are drawn at random without replacement. Find the probability that they are of different colours.
经典题目：一个袋子里有 4 个红色和 6 个蓝色弹珠。随机抽取两个且不放回。求两个弹珠颜色不同的概率。
Draw two sets of branches. First draw: P(R) = 4/10, P(B) = 6/10. Second draw: If red taken first, remaining are 3R, 6B, so P(R|R) = 3/9, P(B|R) = 6/9. If blue taken first, P(R|B) = 4/9, P(B|B) = 5/9. Different colours = (R then B) or (B then R). P(different) = (4/10 × 6/9) + (6/10 × 4/9) = 24/90 + 24/90 = 48/90 = 8/15.
画两组分支。第一次抽取：P(R) = 4/10，P(B) = 6/10。第二次抽取：若第一次抽到红色，剩余 3R, 6B，故 P(R|R) = 3/9，P(B|R) = 6/9。若第一次抽到蓝色，P(R|B) = 4/9，P(B|B) = 5/9。颜色不同为 (先红后蓝) 或 (先蓝后红)。P(不同) = (4/10 × 6/9) + (6/10 × 4/9) = 24/90 + 24/90 = 48/90 = 8/15。
8. Normal Distribution: Standardising and Reading Tables | 正态分布：标准化与查表
Although Cambridge IGCSE Statistics does not include complex normal distribution calculations, past papers sometimes test the concept of z-score and using the standard normal table. You need to know the formula z = (x – μ) / σ and understand that approximately 68% of data lie within 1 standard deviation of the mean, 95% within 2, and 99.7% within 3.
虽然剑桥 IGCSE 统计不包括复杂的正态分布计算，但历年真题有时会考查 z 值的概念和标准正态分布表的运用。你需要掌握公式 z = (x – μ) / σ，并理解约 68% 的数据落在均值正负一倍标准差内，95% 在两倍内，99.7% 在三倍内。
Application: The heights of a population are normally distributed with mean 170 cm and standard deviation 8 cm. What proportion of heights are between 162 cm and 178 cm? (Use the 68–95–99.7 rule)
应用：某群体身高呈正态分布，均值为 170 cm，标准差为 8 cm。身高在 162 cm 与 178 cm 之间的比例是多少？（运用 68–95–99.7 法则）
The interval from 162 to 178 is exactly mean ± 1 standard deviation (170 ± 8). According to the empirical rule, about 68% of the data falls in this range. For a more precise calculation you standardise the boundaries: z₁ = (162-170)/8 = –1, z₂ = (178-170)/8 = 1, then use tables to find Φ(1) – Φ(–1) ≈ 0.6826. Always sketch a bell curve and shade the area.
区间 162 至 178 恰好是均值 ± 1 个标准差 (170 ± 8)。根据经验法则，约 68% 的数据落在此范围内。若需更精确计算，将边界标准化：z₁ = (162-170)/8 = –1，z₂ = (178-170)/8 = 1，然后查表得到 Φ(1) – Φ(–1) ≈ 0.6826。考试时务必画出钟形曲线并涂上阴影区域。
9. Sampling Methods and Bias | 抽样方法与偏差
Questions on sampling appear regularly in the multiple‑choice sections and in structured questions. You need to describe random, stratified, systematic, convenience and quota sampling. Recognising potential bias is equally important: selection bias, non‑response bias, and leading questions in a survey.
关于抽样的题目经常出现在选择题和结构化问答中。你需要描述随机抽样、分层抽样、系统抽样、便利抽样和定额抽样。识别潜在偏差同样重要：选择偏差、无回应偏差以及调查中的引导性问题。
Stratified sampling example: A school has 600 boys and 400 girls. A stratified sample of 50 students is required. How many boys and girls should be chosen?
分层抽样示例：某学校有 600 名男生和 400 名女生。需抽取一个 50 名学生的分层样本。应抽取多少男生和女生？
Boys: (600/1000) × 50 = 30; Girls: (400/1000) × 50 = 20. Within each stratum, use simple random sampling. Explain why stratified sampling is better than simple random: it ensures the sample accurately reflects the proportion of each gender in the population, making the estimate more representative.
男生：(600/1000) × 50 = 30；女生：(400/1000) × 50 = 20。在各个层内采用简单随机抽样。解释为什么分层抽样优于简单随机抽样：它能保证样本准确反映总体中各类别的比例，使估计更具代表性。
10. Exam Technique: Reading the Question and Showing Work | 考试技巧：审题与展示步骤
Many marks are lost by students who rush past key words. Circle command words like ‘estimate’, ‘calculate’, ‘explain’ or ‘interpret’. If the question says ‘give your answer to 3 significant figures’, make sure you do exactly that. For graph questions, use a sharp pencil and label axes with units.
许多失分源于学生匆忙略过关键词。圈出像‘estimate’、‘calculate’、‘explain’或‘interpret’这样的指令词。如果题目要求‘答案保留三位有效数字’，务必照做。在图形题中，使用尖铅笔并给坐标轴标上单位。
Always show your working, even if you use a calculator. For example, in standard deviation calculations, write the sum of squares before taking the square root. If you make an arithmetic slip, the examiner can still award method marks. In probability, leave answers as fractions in their simplest form unless told otherwise.
无论是否使用计算器，务必展示计算过程。例如，在标准差计算中，先写出平方和再开方。即使出现计算失误，考官仍可给步骤分。在概率题中，除非另有说明，答案应以最简分数形式保留。
Finally, manage your time: do not spend 20 minutes on a 4‑mark graph plot. Move on and return if needed. Practising with real past papers under timed conditions is the single most effective revision strategy.
最后，合理分配时间：不要在一个 4 分的画图题上耗掉 20 分钟。继续做后面的题，有时间再回来检查。在计时条件下练习真正的历年真题，是最高效的复习策略。
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