📚 Core Concepts in SQA Statistics | SQA 统计核心知识点梳理
The SQA Advanced Higher Statistics course equips Year 13 students with the tools to collect, analyse, and interpret data in a rigorous and critical manner. It builds on earlier statistical ideas and introduces formal probability models, inferential techniques, and regression methods that are essential for higher education and research. Mastering these core concepts not only prepares students for examinations but also lays a strong foundation for any data-driven discipline.
SQA Advanced Higher 统计课程为 Year 13 学生提供了严谨而批判性地收集、分析和解释数据的工具。它建立在早期统计思想的基础上，引入了正规的概率模型、推断方法以及回归技术，这些对于高等教育和研究至关重要。掌握这些核心概念不仅能为考试做好准备，还能为任何数据驱动的学科打下坚实基础。
1. Types of Data and Sampling Methods | 数据类型与抽样方法
In any statistical investigation the first step is to identify the type of data being collected. Data can be categorical (nominal or ordinal) or numerical (discrete or continuous). Quantitative variables such as height or mass yield continuous data, whereas counts like number of accidents produce discrete data. Understanding this distinction influences the choice of graphical displays and summary statistics.
在任何统计调查中，第一步是确定所收集数据的类型。数据可以是分类数据（名义或有序）或数值数据（离散或连续）。诸如身高或体重这类定量变量产生连续数据，而事故次数这类计数则产生离散数据。理解这种区别会影响图表展示和汇总统计量的选择。
A sample must be selected using a sound sampling technique to avoid bias and ensure that results can be generalised. Common methods include simple random sampling, stratified sampling, systematic sampling, and cluster sampling. In SQA problems students often need to justify why a particular method is appropriate for a given context, considering both practical constraints and the need for representativeness.
必须采用合理的抽样技术选取样本，以避免偏差并确保结果具有可推广性。常见的方法包括简单随机抽样、分层抽样、系统抽样和整群抽样。在 SQA 试题中，学生常常需要论证为什么在特定情境下某种方法更为合适，既要考虑实际条件，又要确保样本的代表性。
2. Descriptive Statistics: Central Tendency and Spread | 描述统计：集中趋势与离散程度
Once data are collected, they are summarised through measures of centre and spread. The mean, median, and mode each describe central tendency, but they are affected differently by skewness and outliers. For symmetric distributions the mean and median coincide, whereas in skewed data the median is often more representative of a typical value.
收集数据后，可以通过中心度量和离散度量来汇总数据。均值、中位数和众数各自描述集中趋势，但它们受偏度和异常值的影响不同。对于对称分布，均值和中位数重合；而在偏斜数据中，中位数往往更具代表性。
Measures of dispersion include the range, interquartile range (IQR), variance, and standard deviation. The standard deviation is particularly important because it is expressed in the same units as the original data and forms the basis of many inferential procedures. SQA candidates are expected to calculate these statistics for small data sets and interpret their meaning in context.
离散度量包括极差、四分位距（IQR）、方差和标准差。标准差尤为重要，因为它与原始数据具有相同的单位，并且是许多推断程序的基础。SQA 考生需要能够针对小型数据集计算这些统计量，并结合情境解释其含义。
3. Probability Rules and Conditional Probability | 概率规则与条件概率
Probability provides the language for quantifying uncertainty. The basic rules include the addition rule P(A ∪ B) = P(A) + P(B) − P(A ∩ B) and, for independent events, P(A ∩ B) = P(A) × P(B). Students must be comfortable applying these rules in both structured and unstructured problems, including those involving tree diagrams and Venn diagrams.
概率为量化不确定性提供了数学语言。基本规则包括加法法则 P(A ∪ B) = P(A) + P(B) − P(A ∩ B)，以及对于独立事件 P(A ∩ B) = P(A) × P(B)。学生必须能熟练地在结构化和非结构化问题中应用这些规则，包括涉及树形图和维恩图的情景。
Conditional probability, expressed as P(A|B) = P(A ∩ B) / P(B), is central to updating probabilities in light of new information. Many SQA exam questions test the ability to distinguish between P(A|B) and P(B|A) and to use the law of total probability when events partition the sample space.
条件概率 P(A|B) = P(A ∩ B) / P(B) 是根据新信息更新概率的核心工具。许多 SQA 考题会考查学生区分 P(A|B) 和 P(B|A) 的能力，以及当事件划分了样本空间时使用全概率公式的能力。
4. Discrete Random Variables and Expected Value | 离散随机变量与期望值
A discrete random variable X takes a countable set of values with associated probabilities. The probability mass function P(X = x) must satisfy two conditions: each probability is between 0 and 1, and the sum of all probabilities equals 1. From this distribution we can compute expected value E(X) = Σ x·P(X = x) and variance Var(X) = E(X²) − [E(X)]².
离散随机变量 X 取可数个值，每个值对应一个概率。概率质量函数 P(X = x) 必须满足两个条件：每个概率介于 0 和 1 之间，并且所有概率之和等于 1。基于该分布，我们可以计算期望值 E(X) = Σ x·P(X = x) 和方差 Var(X) = E(X²) − [E(X)]²。
Expectation is a form of long-run average and is used widely in decision-making. The SQA syllabus also covers transformations of random variables, such as E(aX + b) = aE(X) + b and Var(aX + b) = a²Var(X). These linear transformation results are essential for later work with normal distributions and confidence intervals.
期望值是一种长期平均值，广泛应用于决策问题。SQA 课程大纲也包括随机变量的线性变换，例如 E(aX + b) = aE(X) + b 和 Var(aX + b) = a²Var(X)。这些线性变换的结果对于后续处理正态分布和置信区间至关重要。
5. The Binomial Distribution | 二项分布
When a fixed number n of independent trials is performed and each trial has the same probability p of success, the number of successes X follows a binomial distribution X ~ B(n, p). The probability of exactly k successes is given by the formula:
当进行固定次数 n 次独立试验，且每次试验都有相同的成功概率 p 时，成功次数 X 服从二项分布 X ~ B(n, p)。恰好得到 k 次成功的概率由下式给出：
P(X = k) = ⁿCₖ pᵏ (1 − p)ⁿ⁻ᵏ
The binomial distribution is characterised by mean μ = np and variance σ² = np(1 − p). Students need to be able to recognise binomial situations from a description, check the necessary assumptions (independence, constant probability, fixed number of trials), and use the formula or statistical tables appropriately.
二项分布的特征是均值 μ = np，方差 σ² = np(1 − p)。学生需要能够从文字描述中识别二项情境，检查必要的假设条件（独立性、恒定概率、固定试验次数），并正确使用公式或统计表。
6. The Poisson Distribution | 泊松分布
The Poisson distribution models the number of events that occur in a fixed interval of time or space when events happen independently at a constant average rate λ. The probability mass function is:
泊松分布用于建模在固定时间或空间间隔内，事件以恒定平均速率 λ 独立发生时的发生次数。其概率质量函数为：
P(X = k) = (λᵏ e⁻λ) / k!
Both the mean and variance of a Poisson distribution equal λ. This distribution is often applied to rare events, such as the number of phone calls to a switchboard per minute or the number of defects per metre of cloth. Students must also know the conditions under which a binomial distribution B(n, p) can be approximated by Poisson(λ) with λ = np, when n is large and p is small.
泊松分布的均值和方差都等于 λ。该分布常常用于稀有事件，例如每分钟电话交换台的呼叫次数或每米布料的缺陷数。学生还需掌握当 n 很大而 p 很小时，二项分布 B(n, p) 可用泊松分布 Poisson(λ) 近似，其中 λ = np。
7. The Normal Distribution | 正态分布
The normal distribution is one of the most important continuous probability distributions. It is defined by its bell-shaped curve, symmetric about the mean μ, with spread determined by the standard deviation σ. We write X ~ N(μ, σ²). Because the normal distribution is continuous, probabilities are found as areas under the density curve, and P(X = x) = 0 for any single value.
正态分布是最重要的连续概率分布之一。它由对称于均值 μ 的钟形曲线定义，散布程度由标准差 σ 决定，记作 X ~ N(μ, σ²)。由于正态分布是连续的，概率由密度曲线下的面积得到，对于任何单个值有 P(X = x) = 0。
To calculate probabilities, we standardise a normal random variable using the Z-score:
为了计算概率，我们通过 Z 分数对正态随机变量进行标准化：
z = (x − μ) / σ
The resulting standard normal distribution Z ~ N(0, 1) can be used with statistical tables to find probabilities. SQA questions frequently involve inverse normal calculations where a probability is given and the corresponding value of x must be found.
由此得到的标准正态分布 Z ~ N(0, 1) 可配合统计表查找概率。SQA 试题经常涉及逆正态计算，即给定概率，要求找到对应的 x 值。
8. Sampling Distributions and the Central Limit Theorem | 抽样分布与中心极限定理
When we draw repeated samples from a population, the sample mean x̄ varies. This variability is described by the sampling distribution of the mean. For a population with mean μ and standard deviation σ, the sampling distribution of x̄ has mean μ and standard error σ/√n. If the population is normally distributed, x̄ is also normal exact.
当我们从总体中重复抽样时，样本均值 x̄ 会发生变化。这种变异性由均值的抽样分布来描述。对于均值为 μ、标准差为 σ 的总体，x̄ 的抽样分布的均值为 μ，标准误为 σ/√n。如果总体服从正态分布，则 x̄ 的精确分布也是正态的。
If the population is not normal, the Central Limit Theorem (CLT) states that for sufficiently large sample sizes (typically n ≥ 30), the sampling distribution of x̄ is approximately normal. This powerful result justifies the use of normal-based inference even when the underlying data are not normally distributed.
如果总体不是正态的，中心极限定理（CLT）指出：当样本量足够大时（通常 n ≥ 30），x̄ 的抽样分布近似正态。这一强大结论使得即便原始数据不服从正态分布，我们依然可以使用基于正态的推断方法。
9. Confidence Intervals for Means and Proportions | 均值和比例的置信区间
A confidence interval provides a range of plausible values for an unknown population parameter. For the population mean μ when σ is known, a 95% confidence interval is:
置信区间为未知总体参数提供了一个合理的取值范围。当 σ 已知时，总体均值 μ 的 95% 置信区间为：
x̄ ± 1.96 × (σ/√n)
When σ is unknown, it is replaced by the sample standard deviation s, and the t-distribution with n − 1 degrees of freedom is used. For proportions, the interval for the population proportion p is constructed using the sample proportion p̂:
当 σ 未知时，用样本标准差 s 替代，并使用自由度为 n − 1 的 t 分布。对于比例，总体比例 p 的置信区间通过样本比例 p̂ 构建：
p̂ ± z* × √[p̂(1 − p̂)/n]
Interpreting a confidence interval correctly – i.e., “we are 95% confident that the true parameter lies within this interval” – is a key skill assessed in SQA examinations.
正确解读置信区间——“我们有 95% 的置信度认为真实参数位于此区间内”——是 SQA 考试中评估的关键技能之一。
10. Hypothesis Testing: Z-Tests for Means and Proportions | 假设检验：均值和比例的 Z 检验
Hypothesis testing is a formal decision-making procedure. The null hypothesis H₀ typically states that there is no effect or no difference, while the alternative H₁ represents what we suspect. For a Z-test on a single mean (σ known), the test statistic is:
假设检验是一种正式的决策程序。零假设 H₀ 通常表述为无效应或无差异，而备择假设 H₁ 则代表我们的怀疑。对于单个均值的 Z 检验（σ 已知），检验统计量为：
z = (x̄ − μ₀) / (σ/√n)
For a single proportion, we use:
对于单个比例，使用：
z = (p̂ − p₀) / √[p₀(1 − p₀)/n]
After computing the test statistic, we compare it to critical values from the standard normal distribution or find the p-value. If the p-value is less than the significance level α (commonly 0.05), we reject H₀. Students must also correctly state conclusions in context without overstating the outcome.
计算出检验统计量后，将其与标准正态分布的临界值进行比较，或算出 p 值。若 p 值小于显著性水平 α（通常取 0.05），则拒绝 H₀。学生还需结合上下文正确陈述结论，避免夸大结果。
11. t-Tests and Chi-Squared Tests | t 检验与卡方检验
When the population standard deviation is unknown, a one-sample t-test is used. The test statistic is t = (x̄ − μ₀) / (s/√n), and it is compared to the t-distribution with n − 1 degrees of freedom. SQA problems also include the paired t-test for matched-pair data, where the differences are analysed as a single sample.
当总体标准差未知时，使用单样本 t 检验。检验统计量为 t = (x̄ − μ₀) / (s/√n)，与自由度为 n − 1 的 t 分布进行比较。SQA 题目还包括配对 t 检验，用于配对数据，将差值作为单样本进行分析。
Chi-squared (χ²) tests are used for categorical data. A χ² goodness-of-fit test assesses whether observed frequencies differ significantly from a hypothesised distribution. A χ² test for association or independence examines whether two categorical variables are related. The test statistic is given by:
卡方（χ²）检验用于分类数据。χ² 适合度检验评估观测频数是否与假设分布存在显著差异。χ² 关联性或独立性检验考察两个分类变量是否相关。检验统计量如下：
χ² = Σ[(O − E)² / E]
where O are observed frequencies and E are expected frequencies under H₀. Knowing the correct degrees of freedom for each test and checking expected cell frequencies are essential for valid application.
其中 O 为观测频数，E 为零假设下的期望频数。掌握每种检验的正确自由度并检查期望格值是否足够大，是正确应用这些检验的关键。
12. Correlation and Linear Regression | 相关性与线性回归
Correlation measures the strength and direction of a linear relationship between two numerical variables. The Pearson product-moment correlation coefficient r ranges from −1 to 1, with values close to ±1 indicating strong linear association. SQA candidates need to compute r using the formula and interpret its meaning, noting that correlation does not imply causation.
相关性衡量两个数值变量之间线性关系的强度和方向。皮尔逊积矩相关系数 r 的取值范围在 −1 到 1 之间，接近 ±1 的值表示存在很强的线性关系。SQA 考生需要运用公式计算 r 并解释其含义，同时注意相关性并不意味着因果关系。
Linear regression takes this further by modelling the relationship with a line of best fit. The least squares regression line ŷ = a + bx minimises the sum of squared vertical distances. Once fitted, the line can be used to make predictions within the range of the data. Residual plots help assess whether the linear model is appropriate.
线性回归在此基础上进一步建模，用最佳拟合直线描述变量间的关系。最小二乘回归线 ŷ = a + bx 最小化了垂直距离的平方和。拟合后，该直线可用于在数据范围内进行预测。残差图有助于评估线性模型是否合适。
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