Year 13 AQA Statistics: Core Knowledge Overview | Year 13 AQA 统计：核心知识点梳理

📚 Year 13 AQA Statistics: Core Knowledge Overview | Year 13 AQA 统计：核心知识点梳理

The Year 13 AQA Statistics syllabus builds on the foundations of probability and data analysis from the first year, introducing more advanced distributions, inference techniques, and the underpinning theory that supports statistical modelling. This revision guide summarises the essential topics you must master, including discrete and continuous distributions, sampling theory, confidence intervals, hypothesis tests for one and two samples, chi-squared tests, correlation and regression, and probability generating functions. Each section highlights key definitions, formulas, conditions, and common exam-style applications.

Year 13 AQA 统计课程在一年级的基础上深入拓展，涵盖更高级的分布、推断方法以及支撑统计建模的理论。这份复习指南梳理了所有核心考点，包括离散与连续分布、抽样理论、置信区间、单双样本假设检验、卡方检验、相关与回归以及概率生成函数。每一节都突出关键定义、公式、适用条件和典型的考试应用方式。

1. Poisson Distribution | 泊松分布

The Poisson distribution models the number of events that occur in a fixed interval of time or space, provided events happen independently at a constant average rate λ. It is often used for rare events such as typographical errors per page or calls arriving at a switchboard per minute. The necessary conditions are: events occur singly, randomly, independently, and at a constant mean rate.

泊松分布用于建模固定时间或空间间隔内事件发生的次数，前提是事件独立发生且平均发生率 λ 恒定。常见应用包括每页打印错误数、每分钟交换机呼叫数等。适用条件为：事件单一、随机、独立出现，且平均速率恒定。

The probability mass function is given by P(X = k) = e^-λ λ^k / k! for k = 0,1,2,… . Both the mean and variance of X are equal to λ. When n is large and p is small, the binomial distribution B(n,p) can be approximated by Poisson with λ = np. This approximation is typically acceptable when n > 50 and np < 5.

概率质量函数为 P(X = k) = e^-λ λ^k / k!，k = 0,1,2,…。X 的均值和方差都等于 λ。当 n 大且 p 小时，二项分布 B(n,p) 可用泊松分布近似，取 λ = np。一般当 n > 50 且 np < 5 时近似效果较好。

In hypothesis testing, we use the Poisson distribution to test whether an observed count is consistent with a given rate, or to perform a goodness-of-fit test against an expected Poisson model. The sum of independent Poisson variables is also Poisson, which is useful when combining counts.

在假设检验中，我们利用泊松分布来检验观测计数是否与给定速率一致，或进行拟合优度检验。独立泊松变量之和仍服从泊松分布，这在合并计数时非常有用。

2. Geometric & Negative Binomial Distributions | 几何分布与负二项分布

The geometric distribution models the number of trials needed to achieve the first success in a sequence of independent Bernoulli trials, each with success probability p. The probability function is P(X = k) = p(1-p)^k-1, for k = 1,2,… . Its mean is 1/p and variance is (1-p)/p².

几何分布描述在一系列独立伯努利试验中，首次成功所需的试验次数，每次成功概率为 p。概率函数为 P(X = k) = p(1-p)^k-1，k = 1,2,…。均值为 1/p，方差为 (1-p)/p²。

The negative binomial distribution extends this to the number of trials needed to obtain r successes, with the same trial structure. Its probability mass function is P(X = k) = C(k-1, r-1) p^r (1-p)^k-r, for k = r, r+1,… . The mean is r/p and variance is r(1-p)/p². Both distributions are discrete and are applied in quality control, waiting-time scenarios, and ecological studies.

负二项分布进一步描述获得 r 次成功所需的试验次数，条件不变。其概率质量函数为 P(X = k) = C(k-1, r-1) p^r (1-p)^k-r，k = r, r+1,…。均值为 r/p，方差为 r(1-p)/p²。这两个离散分布常用于质量控制、等待时间问题以及生态研究。

When r is large enough, the negative binomial can be approximated by a normal distribution; certain hypothesis tests for proportions can be constructed using these distributions as alternatives to the binomial model.

当 r 足够大时，负二项分布可用正态分布近似；有些比例检验可以用这些分布替代二项模型来构建。

Distribution	Mean	Variance	P(X=k)
Poisson(λ)	λ	λ	e^-λ λ^k / k!
Geometric(p)	1/p	(1-p)/p²	p(1-p)^k-1
Neg.Bin(r,p)	r/p	r(1-p)/p²	C(k-1, r-1)p^r(1-p)^k-r

3. Exponential Distribution | 指数分布

The exponential distribution is a continuous probability distribution often used to model the time between events in a Poisson process. If events occur at rate λ, the waiting time T has probability density function f(t) = λe^-λt for t ≥ 0. The mean is 1/λ and the variance is 1/λ².

指数分布是一种连续概率分布，常用于建模泊松过程中事件之间的时间间隔。如果事件发生率为 λ，则等待时间 T 的概率密度函数为 f(t) = λe^-λt，t ≥ 0。均值为 1/λ，方差为 1/λ²。

The cumulative distribution function is F(t) = 1 – e^-λt. A crucial property is the memoryless property: P(T > s+t | T > s) = P(T > t). This makes the exponential distribution suitable for modelling lifetimes of components that do not ‘age’, such as certain electronic parts.

累积分布函数为 F(t) = 1 – e^-λt。指数分布有关键的无记忆性：P(T > s+t | T > s) = P(T > t)。因此指数分布适用于模型化不随时间老化的元件寿命，比如某些电子元件。

In exam contexts, you often need to calculate probabilities directly from the density or CDF, estimate the rate parameter from data, and understand its link to the Poisson process: the number of events in a fixed interval is Poisson, while the gaps between them are exponential.

考试中常要求从密度函数或累积分布函数直接计算概率、通过数据估计速率参数，并理解其与泊松过程的联系：固定区间内的事件数服从泊松分布，事件间的间隔服从指数分布。

4. Continuous Random Variables & PDFs | 连续随机变量与概率密度函数

For a continuous random variable X, the probability density function f(x) satisfies f(x) ≥ 0 and the total area under the curve is ∫ f(x) dx = 1. Probabilities are found by integrating: P(a < X < b) = ∫_a^b f(x) dx. The cumulative distribution function is F(x) = P(X ≤ x) = ∫_-∞^x f(t) dt.

对于连续随机变量 X，概率密度函数 f(x) 满足 f(x) ≥ 0，且曲线下总面积为 ∫ f(x) dx = 1。概率通过积分求得：P(a < X < b) = ∫_a^b f(x) dx。累积分布函数为 F(x) = P(X ≤ x) = ∫_-∞^x f(t) dt。

The median m is found by solving F(m) = 0.5; the mode is the x that maximises f(x). The expected value or mean is E(X) = ∫ x f(x) dx, and the variance is Var(X) = E(X²) – [E(X)]², with E(X²) = ∫ x² f(x) dx. Familiarity with integration of polynomials, exponentials, and piecewise functions is essential.

中位数 m 通过解 F(m)=0.5 求得；众数是使 f(x) 最大化的 x。期望值或均值为 E(X) = ∫ x f(x) dx，方差 Var(X) = E(X²) – [E(X)]²，其中 E(X²) = ∫ x² f(x) dx。熟练掌握多项式、指数函数和分段函数的积分十分必要。

You may also need to find percentiles, interquartile range, and use transformations of continuous variables. Identifying a valid PDF often involves finding an unknown constant by setting the total area to 1.

考试可能还涉及百分位数、四分位距以及连续变量的变换。识别有效的概率密度函数通常需要利用总面积为1来求未知常数。

5. Normal Distribution & Central Limit Theorem | 正态分布与中心极限定理

The normal distribution N(μ, σ²) is the most important continuous distribution in statistics. Its probability density function is symmetric and bell-shaped. Standardising to Z = (X – μ) / σ produces the standard normal N(0,1), which allows use of tables to find probabilities and critical values.

正态分布 N(μ, σ²) 是统计学中最重要的连续分布。其概率密度函数对称且呈钟形。标准化变换 Z = (X-μ)/σ 得到标准正态 N(0,1)，方便利用表格查找概率和临界值。

The Central Limit Theorem (CLT) states that for a random sample of size n from any distribution with mean μ and variance σ², the sample mean X̄ is approximately normally distributed as N(μ, σ²/n) when n is large (typically n ≥ 30). This underpins most parametric inference.

中心极限定理指出，对于来自任意均值为 μ、方差为 σ² 的总体的样本量为 n 的随机样本，当 n 较大时（通常 n ≥ 30），样本均值 X̄ 近似服从 N(μ, σ²/n)。这是多数参数推断的理论基础。

The normal distribution can also be used as an approximation to the Poisson (for large λ) and the binomial (np>5, nq>5). A continuity correction is applied when approximating discrete distributions.

正态分布也可用于近似泊松分布（λ 较大时）和二项分布（np>5, nq>5）。近似离散分布时应使用连续性校正。

6. t-Distribution & Its Uses | t分布及其应用

When the population standard deviation σ is unknown and estimated by the sample standard deviation s, the statistic (X̄ – μ) / (s/√n) follows a t-distribution with n-1 degrees of freedom. The t-curve is symmetric like the normal but has heavier tails, which becomes closer to the normal as the degrees of freedom increase.

当总体标准差 σ 未知而用样本标准差 s 估计时，统计量 (X̄ – μ) / (s/√n) 服从自由度为 n-1 的 t 分布。t 曲线与正态分布一样对称，但尾部更厚；随着自由度增大，越来越接近正态分布。

The t-distribution is essential for small-sample inference and for constructing confidence intervals and hypothesis tests for a single mean, difference between two means, and for regression coefficients. It is used together with t-tables that provide critical values for given significance levels and degrees of freedom.

t 分布对小样本推断至关重要，用于构建单均值、两均值差异以及回归系数的置信区间和假设检验。使用时需查 t 表获取给定显著性水平和自由度下的临界值。

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 ± z_0.025 × σ/√n. When σ is unknown, replace z with the t-value: X̄ ± t_ν,α/2 × s/√n, ν = n-1.

置信区间给出了总体参数的合理取值范围。当已知 σ，总体均值 μ 的95%置信区间为 X̄ ± z_0.025 × σ/√n。当 σ 未知时，用 t 值代替：X̄ ± t_ν,α/2 × s/√n，ν = n-1。

For a population proportion p, the large-sample confidence interval is p̂ ± z×√(p̂(1-p̂)/n). For the Poisson mean λ, an approximate interval uses λ̂ ± z×√(λ̂/n). Interpretation is key: we say we are 95% confident that the interval contains the true parameter, not that there is a 95% probability the parameter lies in a particular interval.

对于总体比例 p，大样本置信区间为 p̂ ± z×√(p̂(1-p̂)/n)。对于泊松均值 λ，近似区间为 λ̂ ± z×√(λ̂/n)。解读方式很关键：我们说“有 95% 的置信度该区间包含真值”，而不是“真值有 95% 的概率落入该特定区间”。

8. One-Sample Hypothesis Tests | 单样本假设检验

Hypothesis testing starts with a null hypothesis H₀ and an alternative H₁. For a population mean with known variance, a z-test is used. The test statistic is z = (X̄ – μ₀) / (σ/√n). For unknown variance, we use the t-test: t = (X̄ – μ₀) / (s/√n) with n-1 degrees of freedom.

假设检验从零假设 H₀ 和备择假设 H₁ 开始。方差已知时用 z 检验，检验统计量为 z = (X̄ – μ₀) / (σ/√n)。方差未知时用 t 检验：t = (X̄ – μ₀) / (s/√n)，自由度 n-1。

For a Poisson mean, we can perform an exact test using the Poisson distribution or an approximate z-test when the count is large. The p-value is the probability of observing a result as extreme as, or more extreme than, the sample, assuming H₀ is true. If p-value < α, we reject H₀.

对于泊松均值，可使用泊松分布进行精确检验，或在计数较大时使用近似 z 检验。p 值是在 H₀ 为真的前提下，观察到当前样本及更极端结果的概率。若 p 值 < α，则拒绝 H₀。

9. Two-Sample & Paired t-Tests | 双样本与配对t检验

To compare the means of two independent populations with unknown but assumed equal variances, we use the two-sample pooled t-test. The pooled variance s_p² = [(n₁-1)s₁² + (n₂-1)s₂²] / (n₁+n₂-2) and the test statistic is t = (X̄₁ – X̄₂) / (s_p√(1/n₁+1/n₂)), df = n₁+n₂-2.

比较两个独立总体均值且方差未知但假设相等时，使用两样本合并 t 检验。合并方差 s_p² = [(n₁-1)s₁² + (n₂-1)s₂²] / (n₁+n₂-2)，检验统计量 t = (X̄₁ – X̄₂) / (s_p√(1/n₁+1/n₂))，自由度 n₁+n₂-2。

When the same subjects are measured twice (paired data), we analyse the differences d_i = X_1i – X_2i. The test becomes a one-sample t-test on the differences: t = d̄ / (s_d/√n), with n-1 degrees of freedom. This pairing removes between-subject variability and can be more powerful.

当同一受试者被测量两次（配对数据），我们分析差值 d_i = X_1i – X_2i。此时转化为对差值的单样本 t 检验：t = d̄ / (s_d/√n)，自由度 n-1。配对能消除受试者间变异，提高检验效能。

10. Chi-Squared Tests | 卡方检验

The chi-squared (χ²) distribution is used to test frequencies. For goodness-of-fit, the test statistic is χ² = Σ (O_i – E_i)² / E_i, where O_i are observed and E_i expected frequencies under H₀. The degrees of freedom are (number of categories – 1 – number of estimated parameters).

卡方分布用于频数检验。对拟合优度而言，检验统计量为 χ² = Σ (O_{Published by TutorHao | Year 13 统计 Revision Series | aleveler.com}

更多咨询请联系16621398022（同微信）

Year 13 AQA Statistics: Core Knowledge Overview | Year 13 AQA 统计：核心知识点梳理