Core Knowledge Review for Year 12 SQA Statistics | SQA 统计核心知识点梳理

📚 Core Knowledge Review for Year 12 SQA Statistics | SQA 统计核心知识点梳理

Welcome to your comprehensive revision guide for the Year 12 SQA Statistics course. This article distils the essential knowledge areas into a clear, bilingual format, helping you master data analysis, probability models, and inferential techniques required for success in your assessments. Each section pairs an English explanation with its Chinese counterpart, reinforcing your understanding from both linguistic perspectives.

欢迎阅读这份面向 Year 12 SQA 统计课程的综合复习指南。本文以清晰的双语形式提炼了核心知识领域，帮助你掌握数据分析、概率模型和推断技术，为考试成功奠定基础。每个小节都将英文阐释与中文对照结合，从双语角度强化你的理解。

1. Data Types and Sampling Methods | 数据类型与抽样方法

Understanding data begins with recognising the difference between qualitative (categorical) and quantitative (numerical) variables. Quantitative data can be further split into discrete counts, such as the number of defects per batch, and continuous measurements, like the mass of a chemical sample. Correct classification influences every subsequent choice of statistical tool.

理解数据始于识别定性（分类）变量与定量（数值）变量的区别。定量数据可进一步划分为离散型计数，如每批产品的缺陷数，以及连续型测量值，如化学样本的质量。正确的分类影响着后续对统计工具的选择。

Reliable conclusions depend on sound sampling. Simple random sampling gives every member of the population an equal chance of selection, while stratified sampling ensures key subgroups are represented proportionally. In SQA problems you may also encounter systematic, cluster, and quota methods; always comment on potential bias and the suitability of the design for the given context.

可靠的结论取决于合理的抽样方法。简单随机抽样使总体中每一个体都有均等的被选机会，而分层抽样则确保关键子群体按比例被代表。在 SQA 考题中你可能还会遇到系统抽样、整群抽样和配额抽样；始终要讨论潜在的偏差以及该设计在给定情境下的适用性。

2. Descriptive Statistics: Measures of Central Tendency and Spread | 描述性统计：集中趋势与离散程度

The mean, median, and mode summarise the centre of a data set. The mean, x̄ = Σx / n, uses every value but is sensitive to outliers. The median is robust for skewed distributions, and the mode identifies the most frequent category or value. Choosing the most representative measure requires examining the shape of the data.

均值、中位数和众数概括了数据集的中心。均值 x̄ = Σx / n 使用了所有数值，但对异常值敏感。中位数在偏态分布中更为稳健，而众数则用于识别最常见的类别或数值。选择最具代表性的度量需要观察数据的分布形态。

Spread is quantified by the range, interquartile range (IQR = Q₃ – Q₁), and standard deviation. For a sample, s = √[Σ(x – x̄)²/(n – 1)] uses n – 1 to provide an unbiased estimate of the population standard deviation. The variance is simply s², and together these statistics determine how concentrated or dispersed the observations are around the centre.

离散程度通过极差、四分位距 (IQR = Q₃ – Q₁) 和标准差来量化。对于样本，s = √[Σ(x – x̄)²/(n – 1)] 采用 n – 1 以给出总体标准差的无偏估计。方差即 s²，这些统计量共同决定了观测值在中心周围的集中或分散程度。

3. Graphical Representations | 图形表示

Box plots provide a five‑number summary (minimum, Q₁, median, Q₃, maximum) and reveal skewness and potential outliers. Side‑by‑side box plots are excellent for comparing two or more groups visually. A box plot with a long upper whisker suggests a right‑skewed distribution, whereas a symmetric box indicates the data are roughly symmetric.

箱线图提供了五数概括（最小值、Q₁、中位数、Q₃、最大值），并能揭示偏度和潜在的异常值。并排箱线图非常适合对两个或多个组进行可视化比较。上须较长的箱线图表明右偏分布，而对称的箱形则表明数据大致对称。

Histograms display the frequency of data within continuous intervals; the area of each bar is proportional to frequency. When constructing a histogram, choose equal class widths where possible, and ensure that boundary values are handled consistently. Stem‑and‑leaf diagrams keep individual data values visible while showing shape, and scatter graphs illustrate the relationship between two numerical variables.

直方图展示数据在连续区间内的频率；每个条形的面积与频率成比例。绘制直方图时应尽可能选择等宽的组距，并确保边界值处理一致。茎叶图既能保持各个数据值可见，又能显示分布形状，而散点图则用于呈现两个数值变量之间的关系。

4. Probability Rules and Conditional Probability | 概率法则与条件概率

The addition rule, P(A ∪ B) = P(A) + P(B) − P(A ∩ B), prevents double counting when events overlap. Multiplication for independent events simplifies to P(A ∩ B) = P(A) × P(B). Always verify whether events are mutually exclusive (cannot happen simultaneously) or independent before applying shortcuts.

加法法则 P(A ∪ B) = P(A) + P(B) − P(A ∩ B) 避免了事件重叠时的重复计算。对于独立事件，乘法简化为 P(A ∩ B) = P(A) × P(B)。在应用简捷公式之前，始终要验证事件是否互斥（不能同时发生）或独立。

Conditional probability is central to SQA exam questions: P(A|B) = P(A ∩ B) / P(B). Rearranging gives the multiplication rule in its general form, P(A ∩ B) = P(A|B) × P(B). Bayes’ theorem, P(A|B) = [P(B|A) × P(A)] / P(B), updates prior probabilities when new evidence is obtained, and is commonly tested using tree diagrams or two‑way tables.

条件概率是 SQA 考题的核心：P(A|B) = P(A ∩ B) / P(B)。整理后可得乘法法则的一般形式 P(A ∩ B) = P(A|B) × P(B)。贝叶斯定理 P(A|B) = [P(B|A) × P(A)] / P(B) 在获得新证据时更新先验概率，通常借助树形图或双向表格进行考查。

5. Discrete Probability Distributions: Binomial and Poisson | 离散概率分布：二项分布与泊松分布

A binomial distribution, X ~ B(n, p), counts the number of successes in n independent trials, each with constant probability p. The probability mass function is P(X = r) = ⁿCᵣ pʳ (1−p)ⁿ⁻ʳ. Its mean is μ = np and variance σ² = np(1−p). Check that the number of trials is fixed, trials are independent, and the outcome is binary.

二项分布 X ~ B(n, p) 用于计算在 n 次独立试验中成功的次数，每次试验的成功概率 p 不变。其概率质量函数为 P(X = r) = ⁿCᵣ pʳ (1−p)ⁿ⁻ʳ。均值为 μ = np，方差为 σ² = np(1−p)。须检验试验次数固定、试验间独立以及结果为二值。

The Poisson distribution, X ~ Po(λ), models the number of events occurring in a fixed interval of time or space when events happen independently at a constant average rate λ. The formula is P(X = r) = e⁻λ λʳ / r!. The mean and variance both equal λ. Poisson can also approximate the binomial when n is large and p is small, using λ = np.

泊松分布 X ~ Po(λ) 用于对固定时间或空间区间内事件发生的次数建模，要求事件独立且以恒定平均率 λ 出现。公式为 P(X = r) = e⁻λ λʳ / r!。均值与方差都等于 λ。当 n 很大且 p 很小时，泊松分布也可用于近似二项分布，此时取 λ = np。

6. Continuous Probability Distributions: Normal Distribution | 连续概率分布：正态分布

The normal distribution, denoted X ~ N(μ, σ²), is defined by its bell‑shaped curve symmetric about the mean μ. The standard deviation σ determines the spread. In SQA statistics you will use z‑scores to standardise values: z = (x − μ) / σ. The standard normal variable Z ~ N(0, 1²) then allows probability calculations from statistical tables.

正态分布记为 X ~ N(μ, σ²)，以其关于均值 μ 对称的钟形曲线为特征。标准差 σ 决定曲线的宽度。在 SQA 统计中，你将使用 z 分数进行标准化：z = (x − μ) / σ。标准正态变量 Z ~ N(0, 1²) 进而可以通过统计用表计算概率。

When a sample mean x̄ is considered, the sampling distribution is also normal with mean μ and standard error σ/√n, provided the population is normal or n ≥ 30 (Central Limit Theorem). You must frequently find probabilities like P(X < a) or P(a < X < b), and identify inverse problems, such as finding the value x for a given upper‑tail probability.

当考虑样本均值 x̄ 时，只要总体服从正态分布或 n ≥ 30（中心极限定理），其抽样分布也是正态的，均值为 μ，标准误为 σ/√n。你需要频繁地求解诸如 P(X < a) 或 P(a < X < b) 的概率，并处理逆问题，如根据给定的上尾概率反求 x 值。

7. Confidence Intervals | 置信区间

A confidence interval provides a range of plausible values for a population parameter. For a population mean μ with known σ, the 95% confidence interval is x̄ ± 1.96 × (σ/√n). When σ is unknown, replace 1.96 with the t‑value from t(n−1) and estimate σ with the sample standard deviation s.

置信区间给出了总体参数的可信范围。对于已知 σ 的总体均值 μ，95% 置信区间为 x̄ ± 1.96 × (σ/√n)。当 σ 未知时，将 1.96 替换为来自 t(n−1) 分布的 t 值，并用样本标准差 s 估计 σ。

For a population proportion p, the large‑sample confidence interval uses the sample proportion p̂: p̂ ± z* × √[p̂(1 – p̂)/n]. The margin of error halves require quadrupling sample size. Interpreting a 95% interval correctly means that if we repeated the sampling process many times, about 95% of the constructed intervals would capture the true parameter.

对于总体比例 p，大样本置信区间使用样本比例 p̂：p̂ ± z* × √[p̂(1 – p̂)/n]。要使误差范围减半，样本量须增至原来的四倍。正确解读 95% 区间意味着：若多次重复抽样过程，大约 95% 构造出的区间会包含真值。

8. Hypothesis Testing: One‑sample and Two‑sample Tests | 假设检验：单样本与双样本检验

A hypothesis test begins with a null hypothesis H₀ and an alternative H₁. The test statistic, such as z = (x̄ − μ₀)/(σ/√n), measures how far the sample result deviates from what H₀ predicts. The p‑value is the probability of obtaining a result at least as extreme as the observed one, assuming H₀ is true; a p‑value below the significance level α leads to rejecting H₀.

假设检验始于原假设 H₀ 与备择假设 H₁。检验统计量，如 z = (x̄ − μ₀)/(σ/√n)，衡量样本结果偏离 H₀ 预测的程度。p 值是在 H₀ 成立的条件下，获得至少与观测结果同样极端的结果的概率；当 p 值低于显著性水平 α 时，拒绝 H₀。

Two‑sample tests compare means from independent groups. For unknown but assumed equal variances, the pooled t‑test is used: the test statistic is t = (x̄₁ − x̄₂) / [sₚ √(1/n₁ + 1/n₂)] with degrees of freedom n₁ + n₂ − 2. Always check assumptions: normality of each group, independence within and between samples, and homogeneity of variance if pooling.

双样本检验用于比较来自独立组的均值。在方差未知但假定相等的情况下，使用合并 t 检验：检验统计量为 t = (x̄₁ − x̄₂) / [sₚ √(1/n₁ + 1/n₂)]，自由度为 n₁ + n₂ − 2。务必检验假定：各组数据服从正态分布、样本内及样本间独立，以及方差齐性（若进行合并）。

9. Chi‑squared Tests: Goodness of Fit and Independence | 卡方检验：拟合优度与独立性检验

The chi‑squared goodness‑of‑fit test evaluates whether observed frequencies match an expected distribution. The test statistic is χ² = Σ [(O − E)² / E], where O and E are observed and expected frequencies. Degrees of freedom are (number of categories − 1) for a simple fit, or (categories − 1 − number of estimated parameters) if parameters are estimated from the data.

卡方拟合优度检验用于评估观测频数是否与期望分布吻合。检验统计量为 χ² = Σ [(O − E)² / E]，其中 O 与 E 分别为观测和期望频数。简单拟合的自由度为（类别数 − 1），若参数由数据估计得出，则为（类别数 − 1 − 估计参数个数）。

The chi‑squared test for independence examines whether two categorical variables are associated in a contingency table. Expected frequencies are calculated as (row total × column total) / grand total. Degrees of freedom equal (r − 1)(c − 1). A small p‑value suggests association, but the test is valid only when all expected frequencies are at least 5.

独立性卡方检验用于考察列联表中两个类别变量是否有关联。期望频数通过（行合计 × 列合计）/ 总计计算。自由度等于 (r − 1)(c − 1)。较小的 p 值表明存在关联，但只有当所有期望频数至少为 5 时，该检验才有效。

10. Correlation and Linear Regression | 相关与线性回归

Pearson’s correlation coefficient r measures the strength and direction of a linear relationship between two quantitative variables. The formula involves standardised deviations: r = Σ[(x − x̄)(y − ȳ)] / {√[Σ(x − x̄)²] √[Σ(y − ȳ)²]}. r always lies between −1 and 1; values close to ±1 indicate strong linear association, while r = 0 indicates no linear correlation.

皮尔逊相关系数 r 用来衡量两个定量变量之间线性关系的强度与方向。其公式涉及标准化偏差：r = Σ[(x − x̄)(y − ȳ)] / {√[Σ(x − x̄)²] √[Σ(y − ȳ)²]}。r 始终介于 −1 与 1 之间；接近 ±1 的值表示强线性关联，而 r = 0 则表示无线性相关。

The least‑squares regression line of y on x is ŷ = a + bx, where b = Sₓy / Sₓₓ and a = ȳ − b x̄. This line minimises the sum of squared vertical residuals. The coefficient of determination, r², tells us the proportion of variability in y explained by x. Always plot residuals to check for curvature or non‑constant variance before trusting the model.

y 对 x 的最小二乘回归直线为 ŷ = a + bx，其中 b = Sₓy / Sₓₓ，a = ȳ − b x̄。该直线使垂直残差的平方和最小。决定系数 r² 反映了由 x 解释的 y 的变异比例。在采信模型之前，始终应绘制残差图以检查是否存在弯曲或非常数方差。

Published by TutorHao | Statistics Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）

Core Knowledge Review for Year 12 SQA Statistics | SQA 统计核心知识点梳理