📚 Common Misconceptions in WJEC Year 13 Statistics and How to Fix Them | WJEC Year 13 统计常见误区及纠正方法
In Year 13 WJEC Statistics, students often encounter subtle yet critical misconceptions that can cost marks and obscure deeper understanding. This article highlights common pitfalls – from misreading p‑values to misapplying probability distributions – and provides clear corrections with exam‑focused advice. By addressing these errors head‑on, you'll build confidence for AS/A2 assessments.
在 WJEC 的 Year 13 统计课程中，学生常在一些细微但关键的概念上出错，不仅丢分，还影响深层理解。本文总结常见误区——从误读 p 值到错误使用概率分布——并给出清晰纠正和应试建议。直面这些错误，你能在测验中更有信心。
1. Confusing Binomial and Poisson Conditions | 混淆二项分布与泊松分布的条件
Many students treat binomial and Poisson distributions as interchangeable, forgetting that the Poisson models rare events in a continuous interval while the binomial counts successes in a fixed number of independent trials. A common error is using the Poisson approximation without checking that n is large and p is small (typically n > 50 and np < 5), or using the binomial when events are not independent.
许多学生把二项分布和泊松分布混用，忘了泊松分布在连续区间内建模稀有事件，而二项分布计算固定次数独立试验的成功次数。常见错误是在没有检查 n 很大、p 很小（通常 n > 50 且 np < 5）的情况下使用泊松近似，或者在事件不独立时仍用二项分布。
Correction: Always check the model assumptions. For binomial X ~ B(n, p), the mean is np and variance npq. For Poisson X ~ Po(λ), both mean and variance equal λ. When approximating, ensure conditions are met and state the approximation clearly. Use binomial when you have fixed trials and constant probability; use Poisson for random occurrences in time/space with a known average rate.
纠正：始终检查模型假设。对于二项分布 X ~ B(n, p)，均值为 np，方差为 npq。对于泊松分布 X ~ Po(λ)，均值和方差都等于 λ。近似时要确保条件满足，并明确写出近似形式。有固定试验次数和不变概率时用二项分布；有已知平均发生率的时间/空间随机事件用泊松分布。
2. Misinterpreting p‑values and Error Types | 误读 p 值和两类错误
Many students believe that a p‑value tells them the probability that the null hypothesis H₀ is true, or that 'failing to reject H₀' means H₀ is true. They also confuse the significance level α with the p‑value, thinking α is the probability of making a Type I error on this specific test. Correctly, α is the long‑run probability of rejecting a true H₀. The risk of a Type II error (β) and the power of a test are often ignored.
很多学生以为 p 值表示原假设 H₀ 为真的概率，或以为“不能拒绝 H₀”就意味着 H₀ 为真。他们还把显著性水平 α 与 p 值混淆，以为 α 是本次检验犯第一类错误的概率。正确的理解是，α 是长期中拒绝一个真实 H₀ 的概率。第二类错误 (β) 的风险和检验的功效也常被忽视。
Correction: A p‑value is the probability, assuming H₀ is true, of obtaining a test statistic at least as extreme as the one observed. If p < α, we reject H₀, but this does not prove H₀ false – it merely indicates the result is unlikely under H₀. A Type I error (rejecting a true H₀) occurs with probability α. A Type II error (failing to reject a false H₀) occurs with probability β, and the power of the test is 1−β. Avoid saying 'accept H₀'; use 'do not reject H₀'.
纠正：p 值是在 H₀ 为真的前提下，得到与观测值同等极端或更极端的检验统计量的概率。若 p < α，我们拒绝 H₀，但这并不能证明 H₀ 为假，只表明在 H₀ 下该结果不太可能出现。第一类错误（拒真）发生的概率为 α。第二类错误（取伪）概率为 β，检验功效为 1−β。避免说“接受 H₀”，要用“不拒绝 H₀”。
3. Wrong Probability Interpretation of Confidence Intervals | 置信区间的错误概率解释
It is tempting to say that a 95% confidence interval for the mean μ has a 95% chance of containing μ. This is incorrect because once a specific interval is calculated from a sample, it is fixed; μ either lies inside it or not. The 95% confidence level refers to the long‑run proportion of such intervals that capture the true parameter in repeated sampling.
很容易说均值 μ 的 95% 置信区间有 95% 的概率包含 μ。这是错的，因为根据样本算出的某个具体区间是固定的，μ 要么在里面，要么不在。95% 的置信度指的是在重复抽样下，这样构造的区间中有 95% 包含真参数的比例。
Correct interpretation: 'If we were to take many random samples and construct a 95% confidence interval from each, we would expect about 95% of those intervals to contain the true population mean.' For a specific interval, we cannot assign a probability. Use phrasing such as 'We are 95% confident that the interval … captures the population mean.' This confidence refers to the method, not the particular numeric interval.
正确解读：“如果我们多次随机抽样，并从每个样本构造一个 95% 置信区间，那么大约 95% 的这些区间会包含真实的总体均值。”对于一个具体的区间，我们不能赋予概率。应使用“我们有 95% 的信心认为该区间……包含了总体均值”的表述。这里的信心指向方法，
Published by TutorHao | Year 13 统计 Revision Series | aleveler.com
更多咨询请联系16621398022（同微信）
或截图后用「扫一扫 → 相册」选择本图