📚 Year 11 OCR Statistics: Core Knowledge Points Revision | OCR 统计学核心知识点梳理
This article provides a comprehensive revision of the essential topics in the Year 11 OCR GCSE Statistics course. From data collection and sampling methods to probability distributions and hypothesis testing, each section summarises the key concepts you need to master. All explanations are paired bilingually to support both English and Chinese learners, ensuring clarity and depth for exam preparation.
本文全面梳理了 Year 11 OCR GCSE 统计课程的核心知识点，涵盖数据收集、抽样方法、概率分布和假设检验等关键内容。每一部分均以中英双语对照讲解，帮助中英双语学习者深入理解并有效备考。
1. Types of Data and Data Collection | 数据类型与数据收集
In statistics, data are classified into categorical (qualitative) data, such as favourite colours or types of vehicle, and numerical (quantitative) data. Numerical data can be further divided into discrete data, which take only specific values (e.g. number of students), and continuous data, which can take any value within a range (e.g. height, time).
在统计学中，数据分为定性（类别）数据，如喜爱的颜色或车辆类型，以及定量（数值）数据。数值数据可进一步分为离散数据（只能取特定值，如学生人数）和连续数据（可在某范围内取任意值，如身高、时间）。
Data collection methods distinguish between primary data, gathered directly by the researcher through experiments, surveys, or observations, and secondary data, obtained from existing sources like government reports or past studies. Primary data allow control over accuracy and relevance, while secondary data are cheaper and faster to obtain but may be less specific to the research question.
数据收集方法分为一手数据（研究者通过实验、调查或观察直接收集）和二手数据（从政府报告或过往研究等现有来源获取）。一手数据能更好地控制准确性和相关性，二手数据则成本更低、获取更快，但可能与研究问题的契合度稍差。
A well-designed data collection sheet or questionnaire is vital for reliable results. Questions must be clear, unbiased, and appropriate to the target population. Pilot surveys help identify problems before the full-scale data collection begins.
一份设计良好的数据收集表或问卷对于结果的可靠性至关重要。问题必须清晰、无偏见且适合目标人群。全面收集数据前进行试点调查有助于发现问题。
2. Sampling Techniques | 抽样方法
Sampling selects a subset of a population to estimate characteristics of the whole group. A random sample ensures every member has an equal chance of being chosen, often using random number generators or drawing lots. This method minimises bias but requires a complete sampling frame.
抽样是从总体中选取子集来估计整体特征的方法。随机抽样保证每个成员被选中的机会相等，通常使用随机数生成器或抽签。这种方法能最大限度减少偏差，但需要一个完整的抽样框架。
Stratified sampling divides the population into distinct strata (e.g. by age or gender) and takes random samples from each stratum in proportion to its size. It improves representativeness when the population is heterogeneous. Systematic sampling selects every k-th individual from a list, which is simple to implement but can introduce periodicity bias.
分层抽样先将总体按年龄或性别等特征分成不同层，再从每层中按比例随机抽取样本，特别适用于异质性较强的总体。系统抽样从名单中每隔 k 个抽取一个个体，操作简单，但可能引入周期性偏差。
Cluster sampling splits the population into clusters and randomly selects entire clusters to sample. Quota sampling is non-random; interviewers are given quotas for certain characteristics. Convenience sampling involves choosing readily available individuals, but it is highly prone to bias and should be avoided in rigorous statistical work.
整群抽样将总体分成群组并随机选取若干整群；配额抽样是非随机抽样，访问员按特定特征定额选择样本。便利抽样选取最容易接触的个体，虽然省事，但极易产生偏差，在严谨的统计工作中应避免。
Recognising the strengths and limitations of each method is critical for interpreting survey results and evaluating the reliability of conclusions.
识别每种方法的优缺点对于解读调查结果和评估结论的可靠性至关重要。
3. Graphical Representations of Data | 数据的图形展示
Choosing the right chart depends on the data type. Bar charts display categorical data with rectangular bars, while pie charts show proportions of a whole. Histograms are used for continuous data, where the area of each bar is proportional to frequency – note that bar widths can vary when class intervals are unequal, and frequency density is plotted on the vertical axis.
选择正确的图表取决于数据类型。条形图用于展示类别数据，饼图展示各部分占整体的比例。直方图用于连续数据，其中每个直条的面积与频数成正比——注意，当组距不等时直条宽度可以不同，纵轴为频率密度。
Cumulative frequency graphs (ogives) allow estimation of medians and quartiles. Box plots (box-and-whisker diagrams) provide a five-number summary: minimum, lower quartile, median, upper quartile, and maximum, making it easy to compare distributions and identify outliers.
累积频率图（肩形图）可用于估算中位数和四分位数。箱线图通过最小值、下四分位数、中位数、上四分位数和最大值这一五数概括，便于比较分布和识别异常值。
Stem-and-leaf diagrams retain original data values while displaying distribution shape, and scatter graphs reveal relationships between two variables. Understanding how to construct and interpret each chart is essential for exam questions that ask for comparisons, trends, or calculations of statistics like the interquartile range.
茎叶图在展示分布形态的同时保留了原始数据，散点图则揭示两个变量之间的关系。掌握每种图表的绘制与解读方法，对于解答比较、趋势分析或计算四分位距等统计量的试题至关重要。
4. Measures of Central Tendency and Dispersion | 集中趋势与离散趋势的度量
Central tendency is described by the mean, median, and mode. The mean is the arithmetic average, calculated as the sum of all values divided by the number of values. The median is the middle value when data are ordered; it is less affected by outliers. The mode is the most frequent value and is the only measure suitable for categorical data.
集中趋势由平均数、中位数和众数描述。平均数是所有数值之和除以个数得到的算术平均值。中位数是排序后位于中间的值，受异常值影响较小。众数是出现频率最高的值，也是唯一适用于类别数据的集中趋势度量。
Mean: x̄ = Σx / n
Dispersion measures include range, interquartile range (IQR), variance, and standard deviation. The range (max – min) is simple but sensitive to outliers. The IQR (upper quartile – lower quartile) covers the middle 50% of data and is robust against outliers.
离散趋势的度量包括极差、四分位距（IQR）、方差和标准差。极差（最大值–最小值）计算简单，但易受异常值影响。四分位距（上四分位数–下四分位数）涵盖中间50%的数据，对异常值具有稳健性。
IQR = Q₃ – Q₁
Variance and standard deviation give a more precise picture of spread around the mean. For a sample, variance is the average of the squared deviations from the mean, and standard deviation is its square root. They are fundamental when comparing the consistency of datasets.
方差和标准差能更精确地反映数据围绕平均值的分散程度。样本方差是各数据与均值之差的平方的平均数，标准差是其平方根。在比较数据集的稳定性时，这两个量尤为重要。
Variance: s² = Σ(x – x̄)² / (n – 1) Standard deviation: s = √[Σ(x – x̄)² / (n – 1)]
Worked examples using frequency tables or grouped data require careful application of midpoints and cumulative columns.
处理频数表或分组数据时，需要仔细运用组中值并设置累积列进行计算。
5. Probability Basics | 概率基础
er of favourable outcomes / total number of outcomes. The complement rule states P(not A) = 1 – P(A).
概率用来量化事件发生的可能性，范围从0（不可能）到1（必然）。对于等可能的结果，P(事件) = 有利结果数 / 总结果数。互补规则为 P(非A) = 1 – P(A)。
other’s probabilities; for two independent events, P(A and B) = P(A) × P(B). Conditional probability, P(A| ability when we know B has happened, and it is linked to tree diagrams and two-way tables.
互斥事件不能同时发生，其“或”概率为 P(A 或 B) = P(A) + P(B)。独立事件互不影响概率，对两个独立事件，P(A 且 B) = P(A) × P(B)。条件概率 P(A|B) 在已知 B 发生时对概率进行细化，并在树形图和双向表中体现。
Conditional probability: P(A|B) = P(A ∩ B) / P(B)
Tree diagrams systematically show all possible outcomes and are especially useful for successive events. Labels on branches are probabilities that multiply along paths; summing relevant endpoint probabilities gives overall event probabilities.
树形图系统地展示所有可能的结果，尤其适用于相继发生的事件。各分支上标以概率，沿路径相乘；将相关终点概率相加即得到整体事件的概率。
6. The Binomial Distribution | 二项分布
The binomial distribution models the number of successes in a fixed number of independent trials, each with the same probability of success, p. The number of trials, n, and p are the parameters, and the random variable X represents the number of successes.
二项分布描述在固定次数独立试验中成功的次数，每次成功的概率 p 相同。参数为试验次数 n 和 p，随机变量 X 表示成功次数。
X ~ B(n, p)
ing cumulative probabilities like P(X ≤ r) can be done using statistical tables or by summing individual probabilities.
恰好获得 r 次成功的概率由二项公式给出，它利用组合数计算可能的序列。累积概率 P(X ≤ r) 可以通过统计表或逐个概率相加获得。
P(X = r) = nCr × pr × (1 – p)n – r
Where nCr = n! / (r!(n – r)!). The mean of a binomial distribution is μ = np, and the variance is σ² = np(1 – p). Recognising binomial conditions – fixed n, independence, constant p, only two outcomes – is crucial for correct application.
其中 nCr = n! / (r!(n – r)!). 二项分布的均值 μ = np，方差 σ² = np(1 – p)。识别二项分布的条件（固定 n、独立、恒定 p、只有两种结果）对于正确应用至关重要。
7. The Normal Distribution | 正态分布
The normal distribution is a continuous probability distribution with a symmetric bell-shaped curve defined by its mean μ and standard deviation σ. The total area under the curve equals 1, and probabilities correspond to areas under the curve between given values.
正态分布是一种连续型概率分布，由均值 μ 和标准差 σ 决定，呈对称的钟形曲线。曲线下的总面积为 1，概率对应于给定数值之间曲线下的面积。
The empirical rule (68–95–99.7 rule) states that approximately 68% of data lie within 1 standard deviation of the mean, 95% within 2, and 99.7% within 3. This rule helps estimate probabilities without a table, although precise calculations require standardisation.
经验法则（68–95–99.7 法则）指出，约 68% 的数据落在均值±1个标准差的范围内，95% 落在±2个标准差内，99.7% 落在±3个标准差内。该法则有助于估算概率，但精确计算需要进行标准化。
z = (x – μ) / σ
The z-score transforms any normal distribution to the standard normal distribution N(0,1). Using z-tables, one can find probabilities for any normal variable. In Year 11, students learn to interpret problems, sketch curves, and use simple standardised values.
z 分数将任意正态分布转换为标准正态分布 N(0,1)。利用 z 表可以求出任何正态变量的概率。在 Year 11 阶段，学生需学会理解问题、绘制曲线草图并运用简单的标准化值。
8. Scatter Graphs and Correlation | 散点图与相关性
Scatter graphs display the relationship between two numerical variables. Correlation describes the direction and strength of a linear relationship. Positive correlation means that as one variable increases, the other tends to increase; negative correlation means one decreases as the other increases. No correlation means there is no discernible pattern.
散点图展示两个数值变量之间的关系。相关性描述线性关系的方向和强度。正相关意味着一个变量增加，另一个也趋于增加；负相关意味着一个增加而另一个减少；无相关则表示没有明显的模式。
A line of best fit drawn through the data can be used to make predictions. Interpolation estimates values within the range of the original data, while extrapolation extends beyond the data range and is less reliable.
通过数据点画出的最佳拟合线可用于预测。内插法估算原始数据范围内的值，而外插法超出数据范围，可靠性较低。
Spearman’s rank correlation coefficient (rₛ) measures monotonic relationships without assuming linearity. It uses ranked data and is robust to outliers. The formula involves the sum of squared differences in ranks.
斯皮尔曼等级相关系数 (rₛ) 用于测量单调关系，不要求线性。它基于排序数据，对异常值具有稳健性。该公式涉及秩差平方和。
rₛ = 1 – (6Σd²) / [n(n² – 1)]
An rₛ close to +1 indicates strong positive rank correlation, while values near –1 indicate strong negative correlation. Understanding correlation does not imply causation is a fundamental principle reinforced throughout the course.
rₛ 接近 +1 表示强正等级相关，接近 –1 表示强负相关。理解相关关系并不意味着因果关系，这是课程始终强调的基本原则。
9. Time Series Analysis | 时间序列分析
A time series is a sequence of data points recorded over time, common in economics, sales, and meteorology. Components often include a long-term trend, seasonal variation, and random fluctuations. Trend lines can be identified using moving averages, which smooth out short-term irregularities.
时间序列是按时间顺序记录的一系列数据点，常见于经济、销售和气象领域。其组成通常包括长期趋势、季节变动和随机波动。趋势线可通过移动平均法识别，该方法能平滑短期不规则波动。
A moving average for a point in time is the mean of a fixed number of surrounding values. Plotting moving averages reveals the underlying trend more clearly. Seasonal variation is then isolated by subtracting the trend from the actual values, enabling forecasting.
某时间点的移动平均值是周围固定数量数值的平均数。绘制移动平均线可更清晰地揭示潜在趋势。然后通过用实际值减去趋势值分离出季节变动，从而进行预测。
Forecasting future values involves extending the trend and adding the relevant seasonal component. However, forecasts assume past patterns continue, so longer-term predictions carry greater uncertainty.
预测未来值需要延伸趋势并加上相应的季节分量。但预测假设过去的模式会持续，因此长期预测的不确定性更大。
10. Index Numbers | 指数
An index number measures the relative change in a variable, usually price or quantity, compared to a base value. The base period is typically assigned an index of 100, and subsequent values are expressed as percentages of the base.
指数用于衡量某一变量（通常是价格或数量）相对于基期值的变化。基期通常被赋予指数 100，后续数值则表示为基期的百分数。
Simple index = (Current value / Base value) × 100
Weighted index numbers, such as the Consumer Price Index (CPI), give greater importance to items that represent a larger share of spending. The aggregate weighted index is calculated by multiplying each price relative by its weight, summing, and dividing by total weight.
加权指数，如消费者价格指数（CPI），对占支出较大份额的项目赋予更高权重。综合加权指数通过将每个价格比乘以对应权重、求和后除以总权重来计算。
Understanding how indices are constructed helps in evaluating real-world economic data and making comparisons across time. Chain base indices relate each value to the immediate previous period, allowing the pattern of period-to-period change to be studied.
理解指数的构造方式有助于评估现实经济数据并进行跨期对比。链基指数将每个值与前一期相联系，便于研究逐期变化模式。
11. Hypothesis Testing and the Chi-Squared Test | 假设检验与卡方检验
Statistical hypothesis testing provides a framework for making decisions based on sample data. The null hypothesis (H₀) is a statement of no effect or no difference, while the alternative hypothesis (H₁) challenges it. A significance level, usually 5%, sets the threshold for rejecting H₀.
统计假设检验提供了一个基于样本数据做出决策的框架。原假设（H₀）陈述无效应或无差异，备择假设（H₁）则对其提出质疑。显著性水平（通常为 5%）设定了拒绝 H₀ 的阈值。
The chi-squared (χ²) test for goodness of fit checks whether observed frequencies differ significantly from expected frequencies under a hypothesised distribution. The test statistic compares observed (O) and expected (E) counts. For a contingency table, the test for independence checks whether two categorical variables are associated.
卡方（χ²）拟合优度检验用于检查观测频数是否与假设分布下的期望频数存在显著差异。检验统计量比较观测值（O）与期望值（E）。对于列联表，独立性检验则检查两个类别变量是否有关联。
χ² = Σ (O – E)² / E
e degrees of freedom depend on the context: for goodness of fit, df = number of categories – 1 – H₀ is rejected. Students must be able to state conclusions in context and acknowledge that a hypothesis test never ‘proves’ H₀, it only assesses evidence against it.
自由度视具体情形而定：拟合优度检验中 df = 类别数 – 1 – 估计参数个数。将计算出的 χ² 与查表所得的临界值比较，如果检验统计量大于临界值，则拒绝 H₀。学生必须能结合情境陈述结论，并承认假设检验永不会“证明”H₀，仅评估反对 H₀ 的证据。
A proper conclusion should explicitly refer to the significance level, e.g., “At the 5% significance level there is sufficient evidence to reject the null hypothesis.”
恰当的结论应明确指出显著性水平，如“在 5% 的显著性水平下，有充分证据拒绝原假设”。
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