OxfordAQA International AS Further Mathematics 9665 Statistics Topic Test

📚 OxfordAQA International AS Further Mathematics 9665 Statistics Topic Test | 知识点精讲

The OxfordAQA International AS Further Mathematics 9665 specification includes a dedicated Statistics component that builds on core probability concepts and extends into advanced modeling, hypothesis testing, and data analysis. This article provides a focused revision of all essential topics, equipping you with the definitions, formulas, and exam techniques needed to excel in the topic test.

牛津AQA国际AS进阶数学9665的统计学部分在核心概率概念基础上延伸至高级建模、假设检验和数据分析。本文针对所有必考知识点进行精讲，帮助你在单元测试中掌握定义、公式和考试技巧。

1. Discrete Random Variables and Expectation | 离散随机变量与期望

A discrete random variable X takes values x₁, x₂, … with probabilities P(X = xᵢ). The probability distribution must satisfy 0 ≤ P(X = xᵢ) ≤ 1 and Σ P(X = xᵢ) = 1.

离散随机变量X取值为x₁, x₂,…，其概率满足0 ≤ P(X = xᵢ) ≤ 1且所有概率之和Σ P(X = xᵢ) = 1。

The expected value (mean) of X is E(X) = Σ xᵢ P(X = xᵢ), often denoted by µ. Expectation is linear: E(aX + b) = aE(X) + b for constants a, b.

X的期望值（均值）为E(X) = Σ xᵢ P(X = xᵢ)，常记作µ。期望具有线性性：对于常数a, b，有E(aX + b) = aE(X) + b。

2. Variance and Standard Deviation | 方差与标准差

Variance measures the spread of a distribution: Var(X) = E[(X − µ)²] = E(X²) − [E(X)]². The standard deviation is σ = √Var(X).

方差衡量分布的离散程度：Var(X) = E[(X − µ)²] = E(X²) − [E(X)]²。标准差为σ = √Var(X)。

For a linear transformation, Var(aX + b) = a² Var(X). Note that adding a constant does not affect variance.

对于线性变换，Var(aX + b) = a² Var(X)。注意加上常数不影响方差。

3. The Binomial Distribution | 二项分布

A binomial distribution models the number of successes in n independent trials, each with probability p of success. We write X ~ B(n, p). The probability mass function is:

P(X = k) = ⁿCₖ pᵏ (1−p)ⁿ⁻ᵏ, k = 0,1,2,…,n

二项分布用于描述n次独立试验中成功的次数，每次成功概率为p。记作X ~ B(n, p)。概率质量函数如上式。

The mean is E(X) = np and variance is Var(X) = np(1−p). Use binomial tables or a calculator to compute probabilities if n is large.

均值为E(X) = np，方差为Var(X) = np(1−p)。若n较大，可查二项分布表或使用计算器求概率。

4. The Poisson Distribution | 泊松分布

The Poisson distribution models the number of events occurring in a fixed interval of time or space under a constant mean rate λ. X ~ Po(λ) and

P(X = x) = (e⁻ᵡ λˣ) / x!, x = 0,1,2,…

泊松分布用于描述在固定时间或空间间隔内，以恒定平均速率λ发生的事件数。X ~ Po(λ)，概率如上式。

For Poisson, E(X) = λ and Var(X) = λ. The binomial distribution B(n, p) can be approximated by Poisson with λ = np when n is large and p is small (np < 10).

泊松分布中E(X) = λ，Var(X) = λ。当n很大且p很小（np < 10）时，二项分布B(n, p)可用泊松分布（λ = np）近似。

5. The Geometric Distribution | 几何分布

The geometric distribution gives the probability that the first success occurs on the x-th trial in a sequence of independent Bernoulli trials with success probability p. For X ~ Geo(p) defined on x = 1,2,3,…:

P(X = x) = p(1−p)ˣ⁻¹

几何分布给出在一系列独立伯努利试验中，首次成功发生在第x次的概率。X ~ Geo(p) 定义在x = 1,2,3,…，概率如上式。

The mean is E(X) = 1/p and variance Var(X) = (1−p)/p². The geometric distribution is memoryless: P(X > s + t | X > s) = P(X > t).

均值E(X) = 1/p，方差Var(X) = (1−p)/p²。几何分布具有无记忆性：P(X > s + t | X > s) = P(X > t)。

6. Hypothesis Testing – Binomial | 二项假设检验

Hypothesis testing on a binomial proportion p: state null hypothesis H₀: p = p₀ and alternative H₁: p ≠ p₀ (two-tailed) or p < p₀ / p > p₀ (one-tailed).

对二项比例p的假设检验：提出原假设H₀: p = p₀，备择假设H₁: p ≠ p₀（双尾）或p < p₀ / p > p₀（单尾）。

Test statistic is the observed number of successes X. Under H₀, X ~ B(n, p₀). Find the critical region at significance level α, or calculate the p-value = P(X ≤ observed) [or ≥] depending on H₁. Reject H₀ if p-value < α or if test statistic falls in the critical region.

检验统计量为观测成功次数X。在H₀下X ~ B(n, p₀)。找出显著性水平α下的临界区域，或计算p值（根据H₁取P(X ≤ 观测值)或P(X ≥ 观测值)）。若p值<α或统计量落入临界域，则拒绝H₀。

7. Hypothesis Testing – Poisson | 泊松假设检验

For a Poisson mean λ, test H₀: λ = λ₀ against H₁: λ < λ₀, λ > λ₀ or λ ≠ λ₀. Under H₀, X ~ Po(λ₀).

对于泊松均值λ，检验H₀: λ = λ₀，根据H₁选择单尾或双尾。在H₀下X ~ Po(λ₀)。

Calculate the p-value directly from Poisson tables or formula, or determine critical values c such that P(X ≤ c) ≤ α (lower tail) etc. Interpret results in context.

利用泊松表或公式直接计算p值，或确定临界值c使得P(X ≤ c) ≤ α（下尾）等。结合实际问题解释结论。

8. Chi-Squared Tests – Goodness of Fit | 卡方拟合优度检验

This test assesses whether observed frequencies fit a specified distribution. The test statistic is:

χ² = Σ (O − E)² / E

该检验评估观测频数是否拟合指定分布。检验统计量如上式。

Degrees of freedom ν = number of classes − 1 − number of estimated parameters. Use χ² distribution tables. Reject H₀ if χ² > critical value at significance level α.

自由度ν = 类别数 − 1 − 估计的参数个数。使用χ²分布表。若χ²大于显著性水平α下的临界值，则拒绝H₀。

9. Chi-Squared Tests – Independence | 卡方独立性检验

For contingency tables, H₀: two variables are independent. Expected frequency for cell (i, j):

Eᵢⱼ = (Row Totalᵢ × Column Totalⱼ) / Grand Total

对于列联表，H₀: 两变量独立。单元格(i, j)的期望频数如上式。

Compute χ² = Σ (O − E)² / E with ν = (rows − 1) × (columns − 1). Compare with critical value. Ensure all expected frequencies ≥ 5 for validity.

计算χ² = Σ (O − E)² / E，自由度ν = (行数−1)×(列数−1)，与临界值比较。为确保有效，所有期望频数应≥5。

10. Product Moment Correlation | 积矩相关系数

The product moment correlation coefficient (PMCC) r measures linear correlation between two variables x and y:

r = S_xy / √(S_xx S_yy)

其中 S_xx = Σ(x − x̄)² = Σx² − (Σx)²/n，S_yy类似，S_xy = Σ(x − x̄)(y − ȳ) = Σxy − (Σx)(Σy)/n。

r takes values between −1 and 1. Test H₀: ρ = 0 against H₁: ρ ≠ 0 using t-test: t = r √(n − 2) / √(1 − r²) with ν = n − 2, or compare r with critical values from tables.

r的取值范围在−1到1之间。检验H₀: ρ = 0可使用t检验：t = r √(n − 2) / √(1 − r²)，自由度ν = n − 2，或直接比较r与临界值表中的值。

11. Regression Lines | 回归线

The least squares regression line of y on x is y = a + bx, where:

b = S_xy / S_xx, a = ȳ − b x̄

y关于x的最小二乘回归线为y = a + bx，斜率b和截距a如上式。

This line is used to predict y for a given x. Avoid extrapolation beyond the data range. The explanatory variable is x, response is y.

该回归线用于根据x预测y。避免在数据范围之外进行外推。x为解释变量，y为响应变量。

12. Summary and Exam Tips | 总结与考试技巧

Review key formulas: E(X), Var(X) for special distributions, PMF of Binomial, Poisson, Geometric, and the χ² statistic. Practice choosing the correct test and stating hypotheses clearly.

复习关键公式：特殊分布的E(X)和Var(X)、二项、泊松、几何的概率质量函数以及χ²统计量。练习选择正确的检验并清晰地陈述假设。

Check conditions: independence, fixed n, constant p for binomial; randomness and average rate for Poisson; large expected frequencies for χ². In exams, show all steps, state significance level, and give conclusions in context. Use calculator functions wisely but always write down the distribution and parameters.

检查条件：二项分布的独立性、固定n、恒定p；泊松分布的随机性和恒定平均速率；χ²检验的期望频数足够大。在考试中，写出所有步骤，标明显著性水平，并结合实际给出结论。合理使用计算器功能，但务必写出所涉及的分布及其参数。

Published by TutorHao | Mathematics Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）

OxfordAQA International AS Further Mathematics 9665 Statistics Topic Test | 知识点精讲