Hypothesis Testing: Key Points for IB & CIE Mathematics | 假设检验考点精讲

📚 Hypothesis Testing: Key Points for IB & CIE Mathematics | 假设检验考点精讲

Hypothesis testing is a statistical method used to make inferences about population parameters based on sample data. It is a core topic in both IB Mathematics (Analysis & Approaches/Applications & Interpretation) and CIE Mathematics (9709). Understanding its logic, steps, and potential errors is essential for exams.

假设检验是一种基于样本数据对总体参数进行推断的统计方法。这是IB数学（分析与方法/应用与解释）和CIE数学（9709）的核心主题。理解其逻辑、步骤和潜在错误对于考试至关重要。

---

1. Introduction to Hypothesis Testing | 假设检验简介

Hypothesis testing is a formal procedure for investigating ideas about the world using statistics. It is widely used in science, business, and social sciences to decide whether a claim about a population parameter is supported by the data.

假设检验是一种利用统计学研究现实世界观点的正式程序。它广泛应用于科学、商业和社会科学，以决定关于总体参数的说法是否得到数据支持。

In the context of IB and CIE Mathematics, you will typically test a population proportion (using the binomial distribution) or a population mean (using the normal distribution). The core concepts remain consistent across examination boards.

在IB和CIE数学的背景下，你通常会检验总体比例（使用二项分布）或总体均值（使用正态分布）。不同考试局的核心概念是一致的。

Hypothesis testing does not prove a hypothesis to be true; it merely assesses whether there is sufficient evidence against the null hypothesis.

假设检验并不能证明一个假设为真；它只是评估是否有足够的证据来反驳原假设。

---

2. Null and Alternative Hypotheses | 原假设与备择假设

ypothesis, H₁, represents what we suspect might be true instead, such as H₁: p > 0.5, H₁: p < 0.5, or H₁: p ≠ 0.5.

原假设，记作H₀，是一个无效应、无差异或维持现状的说法。例如，H₀: p = 0.5 或 H₀: μ = 100。备择假设H₁表示我们怀疑可能为真的情况，例如 H₁: p > 0.5、H₁: p < 0.5 或 H₁: p ≠ 0.5。

The hypotheses must be mutually exclusive and exhaustive. In exam questions, you are often asked to write down the null and alternative hypotheses clearly, marking the parameter of interest.

这两个假设必须是互斥且穷尽的。在考试题目中，你经常需要清晰地写下原假设和备择假设，并标注感兴趣的参数。

( = ), while H₁ contains a strict inequality ( >, <, or ≠ ). The burden of proof is on H₁.

注意H₀总是包含等号 ( = )，而H₁包含严格的不等号 ( >、< 或 ≠ )。举证责任在于H₁。

---

3. Significance Level and Critical Regions | 显著性水平与拒绝域

The significance level, α (alpha), is the probability of rejecting H₀ when it is actually true. Common values are 5% (0.05), 1% (0.01), and 10% (0.10). The critical region (rejection region) consists of all values of the test statistic that would lead to rejection of H₀.

显著性水平 α (alpha) 是当H₀为真时拒绝H₀的概率。常用值为5% (0.05)、1% (0.01)和10% (0.10)。拒绝域（临界域）由所有会导致拒绝H₀的检验统计量的值组成。

For a one-tailed test, the critical region lies entirely in one tail of the sampling distribution; for a two-tailed test, it is split between both tails, each with area α/2.

对于单尾检验，拒绝域完全位于抽样分布的一侧尾部；对于双尾检验，则平均分配在两个尾部，各占α/2。

The boundary of the critical region is called the critical value. In binomial tests, you find the smallest number of successes that would lead to rejection.

拒绝域的边界称为临界值。在二项检验中，你要找到会导致拒绝的最小成功次数。

---

广告 / Sponsored

4. Test Statistic and P-value | 检验统计量与P值

ample proportion. For a normal mean test with known variance, the test statistic is z = (x̄ - μ₀) / (σ/√n).

检验统计量由样本数据计算得出，用于决定是否拒绝H₀。对于二项比例检验，检验统计量是观察到的成功次数 X 或样本比例。对于已知方差的正态均值检验，检验统计量为 z = (x̄ - μ₀) / (σ/√n)。

true. If p-value ≤ α, we reject H₀. IB and CIE both emphasize interpretation of p-values.

P值是假设H₀为真时，获得至少与观察值一样极端的检验统计量的概率。如果 p值 ≤ α，我们拒绝H₀。IB和CIE都强调对p值的解释。

In binomial tests, the p-value is often found by summing probabilities from the tail(s) using the binomial distribution formula or tables. A smaller p-value indicates stronger evidence against H₀.

在二项检验中，p值通常通过使用二项分布公式或表格，对尾部概率求和得到。p值越小，表明反对H₀的证据越强。

---

5. One-tailed and Two-tailed Tests | 单尾与双尾检验

If the alternative hypothesis specifies a direction (e.g., H₁: p > 0.3), we use a one-tailed (upper-tail) test. If it is H₁: p < 0.3, we use a lower-tail one-tailed test. For H₁: p ≠ 0.3, we use a two-tailed test.

如果备择假设指定了方向（例如 H₁: p > 0.3），我们使用单尾（上尾）检验。如果是 H₁: p < 0.3，则使用下尾单尾检验。若是 H₁: p ≠ 0.3，则使用双尾检验。

The decision rule depends on the test direction: in a two-tailed test, we reject H₀ if the test statistic falls in either the upper or lower tail critical region, or if the p-value (two-tailed) is less than α.

决策规则取决于检验方向：在双尾检验中，如果检验统计量落在上尾或下尾的拒绝域内，或者双尾p值小于α，则拒绝H₀。

Always determine the number of tails from the wording of the problem. Words like 'change', 'different', 'differs' typically indicate a two-tailed test, while 'increase', 'decrease', 'more than' indicate a one-tailed test.

始终根据问题的措辞确定尾数。诸如“改变”、“不同”、“有差异”等词语通常表示双尾检验，而“增加”、“减少”、“多于”等表示单尾检验。

---

6. Steps in Hypothesis Testing | 假设检验的步骤

A systematic approach is crucial for exams. The typical steps are: 1) State the null and alternative hypotheses. 2) Determine the significance level α. 3) Identify the appropriate test and calculate the test statistic. 4) Find the critical value(s) or p-value. 5) Make a decision: reject H₀ or do not reject H₀. 6) Write a conclusion in context.

系统的解题方法对考试至关重要。典型步骤：1) 陈述原假设和备择假设。2) 确定显著性水平α。3) 选择适当的检验并计算检验统计量。4) 求临界值或p值。5) 做出决策：拒绝H₀或不拒绝H₀。6) 在题目背景下写出结论。

CIE and IB mark schemes often require the conclusion to be written in non-technical language and clearly linked to the context, e.g., 'There is sufficient evidence at the 5% significance level to suggest that the proportion has increased.'

CIE和IB的评分标准通常要求结论用非技术性语言书写，并明确联系背景，例如：“在5%的显著性水平下，有充分证据表明比例有所增加。”

Never use 'accept H₀'. You either reject H₀ or

Published by TutorHao | IB Mathematics Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）