📚 Year 11 OCR Statistics: High-Frequency Topics and Common Error Analysis | Year 11 OCR 统计：高频考点与易错题分析
Mastering GCSE Statistics requires not only understanding key concepts but also recognising where students most often lose marks. This revision guide covers the high-frequency topics in the OCR Year 11 Statistics specification and pinpoints the typical errors that examiners report year after year. By focusing on these areas, you can build accuracy and confidence before the final assessments.
掌握 GCSE 统计不仅需要理解核心概念，还需要清楚学生最容易在哪些地方丢分。这份复习指南覆盖 OCR Year 11 统计大纲中的高频考点，并一针见血地指出考官每年都会报告的典型错误。抓牢这些内容，你就能在最终考试前提高准确度、增强信心。
1. Data Types and Collection Methods | 数据类型与收集方法
Categorical (qualitative) data describe qualities or groups, while numerical (quantitative) data are numbers that can be discrete (counted) or continuous (measured). A census surveys every member of a population, but it is expensive and time-consuming. A sample is quicker and cheaper but can be biased if the sampling frame is flawed.
分类（定性）数据描述属性或组别，数值（定量）数据是可以计数（离散）或测量（连续）的数字。普查调查总体中的每一个成员，但成本高且耗时。抽样更快捷、更经济，但如果抽样框有缺陷就可能产生偏差。
Common mistake: treating postcodes or phone numbers as quantitative data, or assuming that any numbers collected are automatically continuous. Another frequent error is thinking a larger sample always eliminates bias – without randomisation, even a large sample can be heavily biased.
常见错误：把邮政编码或电话号码当作定量数据，或者想当然地认为任何收集到的数字都是连续的。另一个频繁出现的错误是认为样本越大就越能消除偏差——如果没有随机化，再大的样本也可能存在严重的偏差。
2. Sampling Techniques | 抽样方法
Simple random sampling gives each member an equal chance of being chosen. Systematic sampling selects every k‑th item from a list, but it can be skewed if there is a hidden pattern in the list. Stratified sampling divides the population into distinct groups (strata) and takes a proportional number from each, ensuring representation. Quota sampling is non‑random and relies on interviewers filling quotas, while convenience sampling picks easily available members and is the weakest method.
简单随机抽样让每个成员有同等机会被选中。系统抽样从名单中每隔 k 个抽取一个，但如果名单中存在隐蔽的规律，抽样结果可能产生偏斜。分层抽样先把总体分成不同的小组（层），再从每一层按比例抽取，以保证代表性。配额抽样是非随机方法，靠调查员完成配额；便利抽样则选择最容易接触到的成员，是最不可靠的方法。
Exam pitfall: when calculating the number needed from a stratum, students often forget to multiply the total sample size by the stratum proportion. For a population of 200 with 50 in a stratum, a sample of 40 requires (50/200)×40 = 10 from that stratum, not 50 or some other number.
考试陷阱：计算某一层需要的样本数量时，学生往往会忘记用总样本量乘上该层的比例。比如总体为 200，某一层有 50，样本量为 40，那么该层应抽取 (50/200)×40 = 10 个，而不是 50 或其他数字。
3. Statistical Diagrams: Cumulative Frequency, Box Plots & Histograms | 统计图表：累积频率图、箱线图与直方图
Histograms display grouped continuous data with area representing frequency. The vertical axis must show frequency density, calculated as frequency ÷ class width. Cumulative frequency diagrams plot running totals against upper class boundaries, allowing medians and quartiles to be estimated. Box plots display minimum, lower quartile, median, upper quartile and maximum, with outliers flagged by 1.5 × IQR rule.
直方图用面积表示频数，展示分组连续数据。纵轴必须是频率密度，由频数 ÷ 组距计算得到。累积频率图将累计频数画在上组界上，便于估计中位数和四分位数。箱线图展示了最小值、下四分位数、中位数、上四分位数和最大值，并用 1.5×IQR 规则标出异常值。
Top errors: using frequency instead of frequency density as the height of histogram bars; forgetting to subtract 0.5 from the class width when dealing with rounded data; misreading cumulative frequency curves by not interpolating between points; and treating an outlier as data below Q1−1.5×IQR or above Q3+1.5×IQR but applying the formula to non‑box‑plot contexts incorrectly.
最主要错误：用频数而不是频率密度作为直方图条形的高度；处理取整数据时忘记从组距中减去 0.5；在累积频率曲线上读数时不进行插值；把异常值规则记成 Q1−1.5×IQR 以下或 Q3+1.5×IQR 以上，却将其错误地套用到非箱线图的场景里。
4. Measures of Central Tendency and Dispersion | 集中趋势与离散程度的度量
The mean is the arithmetic average, the median is the middle value when data are ordered, and the mode is the most frequent value. Range is the difference between maximum and minimum. The interquartile range (IQR = Q3−Q1) measures the spread of the middle 50%. Standard deviation measures how spread out the data are from the mean. For a population, σ = √[ Σ(x − μ)2 ÷ n ]; for a sample, s = √[ Σ(x − x̄)2 ÷ (n−1) ].
平均值是算术平均数，中位数是排序后处于中间位置的数值，众数是出现次数最多的数值。极差是最大值与最小值之差。四分位距（IQR = Q3−Q1）用来衡量中间 50% 数据的离散程度。标准差则描述数据整体相对于平均值的分散程度。总体的标准差公式为 σ = √[ Σ(x − μ)2 ÷ n ]，样本的标准差为 s = √[ Σ(x − x̄)2 ÷ (n−1) ]。
Recurring slip: using the divisor n−1 for a whole population or using n for a sample. Also, when computing variance, students often forget to square the differences first, or they square the sum instead of summing the squares. Another trap is selecting the mean when outliers are present – the median would be more robust in such cases, but many learners still quote the mean.
反复出现的失误：总体数据用除数 n−1，或者样本数据用 n。计算方差时，学生经常忘记先把差值平方，或者把和平方而非平方后求和。另一个陷阱是数据中存在异常值时还在坚持用平均值——这种情况下中位数更稳健，但许多学生仍然引用平均值。
5. Probability: Rules, Trees and Misconceptions | 概率：规则、树状图与常见误解
For mutually exclusive events, P(A or B) = P(A) + P(B). For independent events, P(A and B) = P(A) × P(B). Tree diagrams multiply probabilities along branches and add outcomes at the ends. A frequent conceptual mistake is believing that mutually exclusive events must be independent – they cannot be, because if one occurs the other cannot, so they are the opposite of independent.
对于互斥事件，P(A 或 B) = P(A) + P(B)。对于独立事件，P(A 且 B) = P(A) × P(B)。树状图沿分枝相乘，在末端将结果相加。一个常见的概念错误是认为互斥事件一定是独立的——事实恰好相反，如果一件事情发生另一件就不能发生，那么它们完全不独立。
Practical errors: labelling tree branches with probabilities that do not sum to 1; forgetting to multiply along a second branch; misinterpreting ‘at least one’ by computing 1−P(none) incorrectly; and confusing the conditional probability P(A|B) with P(A and B) when reading a scenario.
实际操作中的错误：在树状图分枝上标出的概率之和不等于 1；忘记沿第二层分枝相乘；计算“至少一个”时，将 1−P(无) 的公式套错；在读题时把条件概率 P(A|B) 与 P(A 且 B) 混为一谈。
6. Binomial Distribution | 二项分布
A binomial distribution models the number of successes in a fixed number of independent trials, each with the same probability of success p. The probability of exactly r successes is P(X = r) = nCr pr (1−p)n−r. The mean is np and the variance is np(1−p). OCR questions often provide binomial tables or expect you to use the formula for small n.
二项分布描述在固定次数的独立试验中成功的次数，每次试验成功的概率 p 相同。恰好成功 r 次的概率为 P(X = r) = nCr pr (1−p)n−r。均值为 np，方差为 np(1−p)。OCR 试题中常提供二项分布表，或者在 n 较小时要求直接套用公式。
Where candidates stumble: computing combinations incorrectly, especially with larger n; swapping p and (1−p) so that the probability of success and failure are reversed; treating a trial without replacement as binomial – the distribution then becomes hypergeometric, not binomial. Also, stating the mean as n and the variance as p is a classic memory slip.
考生容易绊倒的地方：组合数计算错误，特别是 n 较大时；掉换 p 和 (1−p)，导致成功与失败的概率用反；把不放回试验当做二项分布处理——这时其实应该用超几何分布。将均值说成 n、方差说成 p 也是典型的记忆性失误。
7. Correlation and Spearman’s Rank | 相关性与斯皮尔曼秩相关系数
Scatter graphs reveal the nature of a relationship between two variables. Spearman’s rank correlation coefficient, rs, measures the strength of monotonic association. It is calculated with rs = 1 − (6Σd2) / [n(n2−1)], where d is the difference between the ranks of each pair. A value close to +1 indicates strong positive correlation, close to −1 indicates strong negative correlation, and near 0 suggests little to no monotonic relationship.
散点图揭示两个变量之间关系的性质。斯皮尔曼秩相关系数 rs 衡量单调关联的强度，计算公式为 rs = 1 − (6Σd2) / [n(n2−1)]，其中 d 是每对数据的秩次之差。系数接近 +1 表示强正相关，接近 −1 表示强负相关，接近 0 则意味着几乎不存在单调关系。
Common inaccuracies: mis‑ranking when there are tied values – tied scores must be given the mean of the positions they occupy. For example, two scores tied for 3rd and 4th place each receive the rank 3.5. Errors also arise when squaring the rank differences, with students forgetting that d is the rank difference, not the original data difference. Finally, interpreting rs = 0 as no relationship at all is wrong; a perfect U‑shaped curve could give rs ≈ 0 but clearly shows a strong non‑linear relationship.
常见不精确之处：出现相同数值时排序错误——并列得分必须取它们应占位置的平均秩。比如两个分数并列第三和第四名，应各赋予秩次 3.5。学生在平方秩次差时也容易犯错，有时会忘记 d 是秩次差而非原始数据之差。此外，将 rs = 0 解释为完全没有关系是不对的；一个完美的 U 形曲线可能得到 rs ≈ 0，却清晰地展示出强烈的非线性关系。
8. Standardised Scores (z‑scores) | 标准化分数（z 分数）
A standardised score tells you how many standard deviations a raw score lies above or below the mean: z = (x − μ) / σ. It allows fair comparison across different distributions. A positive z‑score means the value is above the mean; a negative z‑score means below.
标准化分数告诉你一个原始分数距离平均值有多少个标准差：z = (x − μ) / σ。它使得在不同分布之间进行公平比较成为可能。正 z 分数表示数值高于均值，负 z 分数则表示低于均值。
Frequent slip‑ups: reversing the formula to z = (μ − x) / σ; forgetting to use brackets, which can give a negative sign in the wrong place; and misinterpreting a z‑score of, say, 1.8 as “the score is 1.8 times the mean” rather than “1.8 standard deviations above the mean”. Another subtle error is dividing by the standard deviation when it equals zero – a standardised score is undefined in that case.
常见的粗心错误：把公式记反写成 z = (μ − x) / σ；漏掉括号，导致负号位置错误；将 1.8 的 z 分数误解为“得分是平均值的 1.8 倍”而不是“高于平均值 1.8 个标准差”。另一个隐蔽错误是当标准差为零时仍然除以它——此时标准化分数是未定义的。
9. Time Series and Moving Averages | 时间序列与移动平均
A time series plots data recorded at regular time intervals. It often includes a trend, seasonal variation, and random fluctuations. Moving averages are used to smooth the data and reveal the trend. A 4‑point moving average requires centring: the average of the first four values is placed opposite the mid‑point of those time periods, often by averaging two consecutive moving averages.
时间序列绘制出按固定时间间隔记录的数据，通常包含趋势、季节变动和随机波动。移动平均用于平滑数据并揭示趋势。4 点移动平均需要取中：先把前四个值的平均值放在对应时间段的中间，通常要再对两个连续的移动平均值取平均来实现居中对齐。
Predicting future values involves projecting the trend line and then adding the average seasonal variation. A hallmark error is extrapolating the trend without seasonal adjustment, or applying a seasonal effect to the wrong quarter. Also, when students calculate a moving average, they frequently forget to align it properly – for example, writing a 4‑point moving average next to the first data point rather than between the second and third points.
预测未来数值时需要推展趋势线并加上平均季节变动。典型的错误是不经季节调整就进行趋势外推，或者将季节效应应用到错误的季度上。此外，学生在计算移动平均时经常忘记正确对齐——比如把一个 4 点移动平均值写在第一个数据点旁边，而不是对齐到第二个和第三个时间点之间。
10. Index Numbers | 指数
An index number expresses the change in a variable compared with a base period. The simple price relative is (current price ÷ base price) × 100. Weighted index numbers account for the importance of items: weighted index = Σ(price relative × weight) ÷ Σweights. Chain base indices link successive periods and are useful when the basket of goods changes over time.
指数用数值表达变量相对于基期的变化。简单的价比是（现价 ÷ 基价）× 100。加权指数计入了项目的相对重要程度：加权指数 = Σ(价比 × 权重) ÷ Σ权重。链基指数则将连续时期链接起来，在商品篮子随时间变动时尤其有用。
Examiners’ favourite traps: forgetting to multiply by 100, so an index is given as
Published by TutorHao | Year 11 统计 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