📚 GCSE AQA Maths: Hypothesis Testing | GCSE AQA 数学：假设检验考点精讲
Hypothesis testing is a fundamental statistical tool that allows you to make decisions about a population based on sample data. At GCSE AQA Mathematics level, you are expected to understand the logic behind testing a claim, use binomial probabilities to assess evidence, and draw valid conclusions in context. This article breaks down every key concept so you can tackle exam questions with confidence.
假设检验是一种基本的统计工具，能让你基于样本数据对总体做出判断。在 GCSE AQA 数学阶段，你需要理解检验某个主张的逻辑，运用二项分布概率评估证据，并结合实际背景得出有效结论。本文拆解每个关键概念，助你自信应对考试题目。
1. Introduction to Hypothesis Testing | 假设检验简介
A hypothesis test starts with a claim about a population parameter. You gather sample data and check whether the observed result is so unusual that it casts doubt on the initial claim. The process is built on the idea of assuming the claim is true, then seeing if the data contradict it strongly.
假设检验从关于总体参数的某个主张开始。你收集样本数据，检查观察结果是否异常到足以对初始主张产生怀疑。这个过程基于这样的思想：先假定主张为真，再看数据是否与之强烈矛盾。
In GCSE AQA Maths, all hypothesis tests use the binomial distribution, meaning you will be dealing with success/failure scenarios such as ‘does a coin land heads more often than expected?’ or ‘is a new manufacturing process producing fewer defective items?’.
在 GCSE AQA 数学中，所有假设检验都使用二项分布，这意味着你将处理成功/失败场景，例如 ‘硬币正面朝上的次数是否比预期的多？’ 或 ‘新工艺是否生产出更少的次品？’
The four essential ingredients of a hypothesis test are: a null hypothesis (H₀), an alternative hypothesis (H₁), a significance level (α), and a decision rule based on probability.
假设检验的四个基本要素是：零假设 (H₀)、备择假设 (H₁)、显著性水平 (α) 以及基于概率的决策规则。
2. Stating the Hypotheses | 陈述假设
The null hypothesis H₀ is the statement being tested; it usually represents ‘no effect’ or ‘no difference’. For a binomial test, H₀ is expressed as p = a specific value, where p is the probability of success in the population.
零假设 H₀ 是被检验的陈述；它通常表示 ‘无效果’ 或 ‘无差异’。对于二项检验，H₀ 表达为 p = 某个特定值，其中 p 是总体中成功的概率。
The alternative hypothesis H₁ says what we suspect might be true. It can take three forms: p > [value] (right-tailed), p < [value] (left-tailed), or p ≠ [value] (two-tailed). The wording of the question tells you which form to use.
备择假设 H₁ 说明我们怀疑可能成立的状况。它可以有三种形式：p > [值] (右尾)，p < [值] (左尾)，或 p ≠ [值] (双尾)。题目的措辞会告诉你该用哪种形式。
Always write both hypotheses clearly using correct notation. For example, if testing whether a coin is biased towards heads, you would write H₀ : p = 0.5 and H₁ : p > 0.5.
务必使用正确符号清楚写出两个假设。例如，检验一枚硬币是否偏向正面，你应写出 H₀ : p = 0.5 和 H₁ : p > 0.5。
3. Significance Level and Critical Region | 显著性水平与临界区域
The significance level, denoted by α, is the probability of rejecting H₀ when it is actually true – a type I error. In GCSE questions, α is often given as 5% (0.05) but can also be 1% or 10%.
显著性水平用 α 表示，它是当 H₀ 实际为真时拒绝 H₀ 的概率——第一类错误。在 GCSE 题目中，α 通常给定为 5% (0.05)，但也可能是 1% 或 10%。
The critical region (or rejection region) is the set of outcomes from the binomial distribution that are so extreme that, if H₀ is true, the probability of falling in this region is ≤ α. The boundary value is called the critical value.
临界区域（或拒绝域）是二项分布中那样极端的一组结果，以致于如果 H₀ 为真，落入该区域的概率 ≤ α。边界值称为临界值。
For a right-tailed test H₁ : p > … , the critical region is X ≥ c, where X is the test statistic (number of successes) and c is the smallest integer satisfying P(X ≥ c) ≤ α.
对于右尾检验 H₁ : p > … ，临界区域为 X ≥ c，其中 X 是检验统计量（成功次数），c 是满足 P(X ≥ c) ≤ α 的最小整数。
4. One-Tailed vs Two-Tailed Tests | 单尾与双尾检验
A one-tailed test is used when the alternative hypothesis specifies a direction: either the parameter is greater than, or less than, the value in H₀. The whole of α is placed in one tail of the distribution.
当备择假设指明方向时使用单尾检验：参数大于或小于 H₀ 中的值。整个 α 放在分布的一个尾部。
A two-tailed test is used for H₁ : p ≠ value. Here, the significance level is split equally between the two tails, so each tail has probability α/2. You need to find two critical values, c₁ and c₂, such that P(X ≤ c₁) ≤ α/2 and P(X ≥ c₂) ≤ α/2.
双尾检验用于 H₁ : p ≠ 值的情况。此时显著性水平在两端均分，因此每个尾部的概率为 α/2。你需要找到两个临界值 c₁ 和 c₂，使得 P(X ≤ c₁) ≤ α/2 且 P(X ≥ c₂) ≤ α/2。
GCSE exam questions often guide you to check just one tail, but you must always read carefully. If the word ‘different’ or ‘changed’ appears without specifying increase or decrease, it is likely a two-tailed test.
GCSE 考试题常引导你只检验一个尾部，但你必须仔细阅读。若出现 ‘不同’ 或 ‘改变’ 而未说明增大或减小，很可能是双尾检验。
5. The Test Statistic and p-value | 检验统计量与 p 值
The test statistic is the observed number of successes in the sample, often denoted by X. For example, if you toss a coin 20 times and get 15 heads, X = 15.
检验统计量是样本中观察到的成功次数，常记为 X。例如，抛硬币 20 次得到 15 次正面，则 X = 15。
The p-value is the probability of obtaining a test statistic at least as extreme as the one observed, assuming H₀ is true. For a right-tailed test, p-value = P(X ≥ observed value). For a left-tailed test, p-value = P(X ≤ observed value). For two-tailed tests, you find one tail probability and double it (provided the distribution is roughly symmetric; for binomial, compare both tails).
p 值是在假设 H₀ 为真的条件下，获得一个至少像观察值这样极端的检验统计量的概率。对于右尾检验，p 值 = P(X ≥ 观察值)。对于左尾检验，p 值 = P(X ≤ 观察值)。对于双尾检验，找出单尾概率并加倍（前提分布大致对称；二项分布则需比较两端）。
If the p-value ≤ α, the result is statistically significant and you reject H₀. If p-value > α, you do not have enough evidence to reject H₀.
若 p 值 ≤ α，则结果统计显著，你拒绝 H₀。若 p 值 > α，则没有足够证据拒绝 H₀。
6. Using the Binomial Distribution | 使用二项分布
All GCSE AQA hypothesis tests rely on the binomial distribution X ~ B(n, p). Here n is the number of trials (sample size) and p is the assumed probability of success under H₀.
所有 GCSE AQA 假设检验都基于二项分布 X ~ B(n, p)。这里 n 是试验次数（样本量），p 是 H₀ 中所假定的成功概率。
To calculate probabilities, you can use your calculator’s binomial CD function, or sometimes exam papers provide cumulative binomial tables. Always show the probability calculation, e.g. P(X ≥ 7) = 1 – P(X ≤ 6).
要计算概率，你可以使用计算器的二项累积分布功能，或者有时试卷提供累积二项分布表。务必展示概率计算过程，如 P(X ≥ 7) = 1 – P(X ≤ 6)。
Remember that binomial probabilities depend on n and p. If the question does not state these, deduce them from the context. For instance, ‘a sample of 10 items is selected’ means n = 10.
记住二项概率取决于 n 和 p。如果题目未给出，从上下文中推导。例如 ‘选取 10 件作为样本’ 表示 n = 10。
7. Finding Critical Values | 求临界值
Finding the critical value c means finding the boundary of the critical region. For a right-tailed test with significance level α, find the smallest c such that P(X ≥ c) ≤ α.
求临界值 c 意味着找出临界区域的边界。对于显著性水平为 α 的右尾检验，找出使 P(X ≥ c) ≤ α 的最小 c。
For example, if X ~ B(20, 0.5) and α = 0.05, check P(X ≥ 14) maybe > 0.05, P(X ≥ 15) maybe < 0.05, so c = 15. Then the critical region is X ≥ 15.
例如，若 X ~ B(20, 0.5) 且 α = 0.05，检验 P(X ≥ 14) 可能 > 0.05, P(X ≥ 15) 可能 < 0.05, 所以 c = 15。那么临界区域为 X ≥ 15。
In a two-tailed test, find c₁ such that P(X ≤ c₁) ≤ α/2 and c₂ such that P(X ≥ c₂) ≤ α/2. Then critical regions are X ≤ c₁ and X ≥ c₂.
在双尾检验中，找出使 P(X ≤ c₁) ≤ α/2 的 c₁，以及使 P(X ≥ c₂) ≤ α/2 的 c₂。于是临界区域为 X ≤ c₁ 和 X ≥ c₂。
8. Making a Decision and Conclusion | 做出决策与结论
Compare the test statistic to the critical region: if the observed X lies in the critical region, reject H₀. Otherwise, do not reject H₀.
将检验统计量与临界区域比较：若观察值 X 落在临界区域内，则拒绝 H₀；否则，不拒绝 H₀。
Alternatively, compare the p-value with α. Reject H₀ if p-value ≤ α.
另一种方式是比较 p 值与 α。若 p 值 ≤ α 则拒绝 H₀。
Your conclusion must be written in the context of the original problem, never just ‘reject H₀’. For example, ‘There is sufficient evidence at the 5% level to suggest the coin is biased towards heads.’
你的结论必须写在原始问题的背景中，决不能只写 ‘拒绝 H₀’。例如 ‘在 5% 水平上有充分证据表明这枚硬币偏向正面。’
If you do not reject H₀, say: ‘There is insufficient evidence to reject the null hypothesis that …’ or ‘There is no significant evidence that …’.
如果不拒绝 H₀，可以说：’没有充分证据拒绝…的零假设’ 或 ‘没有显著证据表明…’。
9. Worked Example: Coin Fairness | 示例：硬币公平性
A student suspects a coin is biased towards heads. She tosses it 20 times and gets 16 heads. Test at the 5% level whether the coin is biased.
一名学生怀疑一枚硬币偏向正面。她抛掷 20 次得到 16 次正面。在 5% 水平上检验该硬币是否有偏。
Step 1: Hypotheses. H₀ : p = 0.5, H₁ : p > 0.5 (one-tailed test).
步骤1：假设。H₀ : p = 0.5, H₁ : p > 0.5（单尾检验）。
Step 2: Distribution. Under H₀, X ~ B(20, 0.5).
步骤2：分布。在 H₀ 下，X ~ B(20, 0.5)。
Step 3: Find critical value. We need smallest c such that P(X ≥ c) ≤ 0.05. Using calculator, P(X ≥ 15) = 0.0207, P(X ≥ 14) = 0.0577, so c = 15. Critical region: X ≥ 15.
步骤3：求临界值。需要使 P(X ≥ c) ≤ 0.05 的最小 c。使用计算器，P(X ≥ 15) = 0.0207, P(X ≥ 14) = 0.0577，故 c = 15。临界区域：X ≥ 15。
Step 4: Decision. Observed X = 16 lies in critical region, so reject H₀.
步骤4：决策。观察值 X = 16 落在临界区域，故拒绝 H₀。
Step 5: Conclusion. There is sufficient evidence at the 5% significance level to suggest that the coin is biased towards heads.
步骤5：结论。在 5% 显著性水平上有充分证据表明该硬币偏向正面。
10. Common Mistakes to Avoid | 常见错误避免
Forgetting to define the test statistic and clearly state the binomial distribution under H₀. Always write ‘Let X be the number of… Under H₀, X ~ B(n, p)’.
忘记定义检验统计量并清楚表述 H₀ 下的二项分布。务必写出 ‘设 X 为…的次数。在 H₀ 下，X ~ B(n, p)’。
Confusing one-tailed and two-tailed tests. Look for words like ‘increase’, ‘decrease’, ‘more than’ (one-tailed) versus ‘different’, ‘changed’, ‘not equal’ (two-tailed).
混淆单尾与双尾检验。留意 ‘增加’、’减少’、’多于’（单尾）与 ‘不同’、’改变’、’不等于’（双尾）等词汇。
Using the wrong tail probability in two-tailed tests. Remember that significance level is halved for each tail. Check both ends carefully.
双尾检验中使用了错误的尾部概率。记住每个尾部的显著性水平减半。仔细检查两端。
Drawing conclusions without context. ‘Reject H₀’ alone earns no marks; you must say what the rejection means in terms of the original problem.
结论脱离背景。单独写 ‘拒绝 H₀’ 不得分；你必须说明拒绝在原问题中意味着什么。
11. Exam Tips | 考试技巧
Always write the hypotheses in symbolic form: H₀: p = … , H₁: p … . Include both sides of the equation.
始终用符号形式写假设：H₀: p = … , H₁: p … 。等式两边都包含。
Show all probability calculations. Even if using a calculator, write the expression like P(X ≥ 7) = 1 – P(X ≤ 6) and give the final probability.
展示所有概率计算。即使使用计算器，也要写出表达式如 P(X ≥ 7) = 1 – P(X ≤ 6) 并给出最终概率。
If the question asks for a conclusion at a given significance level, make sure your conclusion references that level. ‘At the 5% level, there is evidence…’
如果题目要求在某显著性水平下得出结论，确保结论提到该水平。’在 5% 水平下，有证据…’
Check whether the test statistic exactly equals the critical value. If it does, it is still in the critical region.
检查检验统计量是否恰好等于临界值。若相等，仍算落在临界区域内。
12. Summary | 总结
Hypothesis testing on the GCSE AQA Maths syllabus uses the binomial distribution to test claims about a population probability p. You must set up H₀ and H₁, choose the correct tail(s), work with a significance level α, find critical values or p-values, and make a contextual conclusion.
GCSE AQA 数学大纲中的假设检验使用二项分布来检验关于总体概率 p 的主张。你必须建立 H₀ 与 H₁，选择正确的尾部，运用显著性水平 α，求出临界值或 p 值，并做出符合背景的结论。
Practice past papers to become fluent in writing hypotheses, calculating binomial probabilities, and interpreting results. With clear structure and careful language, full marks are well within reach.
通过练习历年真题来熟练书写假设、计算二项概率和解读结果。有了清晰的结构和严谨的语言，满分唾手可得。
Published by TutorHao | Mathematics 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