📚 Year 11 CCEA Statistics: Case Study Practice | CCEA 11年级统计：案例分析实战演练
Case studies are a cornerstone of GCSE Statistics, requiring you to plan, collect, analyse and interpret data in a real-world context. This walkthrough demonstrates a full investigation into whether study hours relate to test scores, modelling the process examiners expect from Year 11 CCEA candidates.
案例分析是 GCSE 统计的基石，要求你在真实情境中规划、收集、分析和解释数据。本文通过演示“学习时间是否与考试成绩相关”的完整调查，模拟了 CCEA 11 年级考生应掌握的统计过程。
1. Defining the Problem | 定义问题
Start with a precise research question. A strong example is: ‘Is there a relationship between the number of hours Year 11 students study per week and their score on a standardised mathematics test?’
从一个精确的研究问题开始。一个有力的例子是：“11 年级学生每周学习的小时数与标准化数学测验分数之间是否存在关系？”
Justify the investigation. Understanding this link can help teachers give better study advice and support students aiming to improve performance. The variables are clearly identified: the independent variable is study hours (x), and the dependent variable is test score (y).
说明调查的理由。了解这一关联可以帮助教师提供更好的学习建议，并支持想提高成绩的学生。变量已明确界定：自变量是学习时间 (x)，因变量是测验分数 (y)。
State the statistical population – all Year 11 students in your school. This ensures you know exactly who the findings might apply to.
表明统计总体——你所在学校的所有 11 年级学生。这能确保你确知研究结果可能适用于哪些人。
2. Planning and Hypotheses | 规划与假设
Write a null hypothesis (H₀) and an alternative hypothesis (H₁). For correlation, H₀ states there is no correlation (ρ = 0), while H₁ suggests a correlation exists (ρ ≠ 0). You might predict a positive direction: ‘Students who study more tend to score higher.’
写出原假设 (H₀) 和备择假设 (H₁)。针对相关性，H₀ 表述为没有相关性 (ρ = 0)，而 H₁ 则表明存在相关性 (ρ ≠ 0)。你可以预测正向关系：“学习时间越长的学生往往分数越高。”
Decide on data collection methods. A closed questionnaire can capture study hours reliably, and accessing anonymous test scores from the maths department ensures accurate, ethical data. Plan for a pilot study with two or three students to spot confusing questions.
确定数据收集方法。一份封闭式问卷可以可靠地获取学习时间信息，而从数学教研组获取匿名测验成绩则能保证数据的准确性与合乎伦理。安排两三名学生进行试点调查，以发现令人困惑的问题。
Consider ethical approval and confidentiality. Use student ID codes, not names, and obtain consent. Document everything to meet CCEA coursework or controlled assessment standards.
考虑伦理批准与保密性。使用学生编号代替姓名，并获得知情同意。记录所有细节，以满足 CCEA 课程作业或控制评估标准。
3. Sampling Strategy | 抽样策略
A simple random sample of 30 students is ideal for this bivariate study. Assign each Year 11 student a number and use a random number generator to select participants. This reduces selection bias and supports generalisation.
对于这项双变量研究，30 名学生的简单随机样本是理想的。为每位 11 年级学生分配一个编号，并使用随机数生成器选择参与者。这能减少选择偏倚并支持推广性。
If a full list is unavailable, stratified sampling by gender or class can ensure representation. Explain why your chosen method suits the context: random sampling gives each student an equal chance, making the sample fair.
如果无法获得完整名单，按性别或班级进行分层抽样可以确保代表性。解释为何所选方法适合情境：随机抽样使每位学生有相等的机会，让样本公平。
Discuss sample size. A sample of 30 is manageable and meets the rule of thumb for detecting a moderate correlation. Acknowledge that larger samples would increase reliability but also the time needed for data collection.
讨论样本量。30 个样本便于实施，且符合检测中等相关性的经验法则。承认更大的样本能提高可靠性，但也会增加数据收集所需的时间。
4. Data Collection | 数据收集
Administer the questionnaire during tutor time to maximise response rate. Students report their average weekly study hours outside lessons, to the nearest half hour. Use a clear instruction: ‘Include all independent revision and homework for maths.’
在辅导课时间发放问卷，以最大化回复率。学生报告他们在课外平均每周的学习小时数，精确到半小时。给出明确说明：“包括所有数学的自主复习和家庭作业。”
Collect the corresponding test scores from the recent mock exam, masked by student ID. Record the data in a structured table to avoid transcription errors. Double-check entries against original records.
从最近的模拟考试中收集与学号对应的测验分数，以掩盖身份。将数据记录在结构化表格中，避免转录错误。对照原始记录再次核对各项内容。
Handle missing data carefully. If a student is absent, either exclude the case or, if appropriate, use the class mean – but explain and justify your choice. The final paired dataset must be complete for correlation analysis.
谨慎处理缺失数据。如果学生缺席，则剔除该案例，或者在适当时使用班级均值——但要解释并证明你的选择。最终配对数据集必须完整，以便进行相关分析。
5. Organising and Displaying Data | 数据整理与展示
Present the raw data in a well-labelled table. Below is a simplified example for ten students (the full study used 30). The columns show Study Hours (x) and Test Score (y).
在一张标记清晰的表中呈现原始数据。下面是一个简化示例，包含 10 名学生（完整研究使用了 30 名）。各列分别显示学习时间 (x) 和测验分数 (y)。
| Student (ID) | Study Hours, x | Test Score, y |
|---|---|---|
| 01 | 4.5 | 38 |
| 02 | 6.0 | 52 |
| 03 | 3.0 | 29 |
| 04 | 7.5 | 61 |
| 05 | 5.0 | 44 |
| 06 | 2.5 | 25 |
| 07 | 8.0 | 65 |
| 08 | 4.0 | 35 |
| 09 | 6.5 | 54 |
| 10 | 5.5 | 48 |
Check the data visually with a stem-and-leaf plot for study hours, identifying any outliers. For test scores, a simple box plot can show the median, quartiles and range at a glance.
用茎叶图直观检查学习时间数据，识别离群值。对于测验分数，简单的箱线图可以一目了然地呈现中位数、四分位数和全距。
Always label axes on graphs: ‘Study Hours per Week’ on the x-axis and ‘Test Score (out of 80)’ on the y-axis. Give each display a figure number and a descriptive title.
务必给图形轴加上标签：x 轴为“每周学习小时数”，y 轴为“测验分数（满分 80 分）”。为每张图表加上图号及描述性标题。
6. Summary Statistics: Averages and Spread | 汇总统计量：平均数与离散程度
Calculate the mean and median of both variables. For the sample above, the mean study time x̄ = 5.25 hours and the mean test score ȳ = 45.1. The medians are 5.25 and 46 respectively, suggesting roughly symmetric distributions.
计算两个变量的均值和中位数。对于上述样本，平均学习时间 x̄ = 5.25 小时，平均测验分数 ȳ = 45.1。中位数分别为 5.25 和 46，表明分布大致对称。
Measure spread using standard deviation (s) or interquartile range (IQR). Here the standard deviation for study hours is about 1.8 hours and for test scores about 12.4 marks. The IQR for test scores is 17, indicating moderate variation.
用标准差 (s) 或四分位距 (IQR) 衡量离散程度。这里学习时间的标准差约为 1.8 小时，测验分数的标准差约为 12.4 分。测验分数的 IQR 为 17，表明中等变异程度。
These statistics set the scene. They help you assess whether the data are reasonably spread and whether any values lie far from the centre before moving to bivariate analysis.
这些统计量为后续分析奠定基础。它们帮助你评估数据是否合理分布，以及在进入双变量分析之前是否存在远离中心的值。
7. Scatter Diagrams and Initial Interpretation | 散点图与初步解读
Plot each (x, y) pair on a scatter diagram. For our ten-point sample, points rise from bottom-left to top-right, suggesting a positive correlation. Label the graph clearly and use evenly spaced scales.
在散点图中绘出每对 (x, y) 数据。对于我们的 10 点样本，点从左下到右上攀升，表明存在正相关。清晰标注图表，并使用等距刻度。
Describe the pattern: direction (positive), form (roughly linear) and strength (moderate to strong). Point out any outliers, such as a student with very high study hours but a low score, which might indicate inefficient revision or an external factor.
描述模式：方向（正向）、形状（近似线性）和强度（中等到强）。指出任何离群点，例如某个学习时间很长但分数很低的学生，这可能表明复习效率低或存在外部因素。
A scatter diagram is worth a thousand summary statistics. It can reveal non-linear trends or clusters that correlation coefficients alone might miss. Never skip this step.
一张散点图胜过千言万语的汇总统计。它可以揭示非线性趋势或聚类，而单靠相关系数可能会遗漏这些信息。绝不要跳过这一步。
8. Correlation Analysis | 相关分析
Calculate the product-moment correlation coefficient (PMCC), r, to quantify the linear relationship. For our sample data, r ≈ 0.89. This value is close to +1, indicating a strong positive linear correlation.
计算积矩相关系数 (PMCC) r，以量化线性关系。对于我们的样本数据，r ≈ 0.89。这个值接近 +1，表明存在强正线性相关。
Interpret r² (the coefficient of determination). Here r² = 0.79, meaning about 79% of the variation in test scores can be explained by study hours. The remaining 21% is due to other factors, such as prior knowledge or exam anxiety.
解释 r²（决定系数）。这里 r² = 0.79，意味着测验分数中约 79% 的变异可由学习时间解释。剩下的 21% 归因于其他因素，如先前知识或考试焦虑。
Test the significance of r using a critical value table for Spearman’s rank or Pearson’s r, depending on your syllabus. With n = 30, a calculated r of 0.89 is highly significant at the 5% level, so we reject H₀ and accept a positive correlation.
根据教学大纲，使用斯皮尔曼秩或皮尔逊 r 的临界值表检验 r 的显著性。当 n = 30 时，计算所得 r = 0.89 在 5% 水平上高度显著，因此我们拒绝 H₀，接受存在正相关。
9. Regression and Prediction | 回归与预测
If the correlation is linear and significant, fit a least-squares regression line of the form y = a + bx. For our data, the equation is approximately y = 12.4 + 6.4x. The slope (6.4) means each extra study hour is associated with a 6.4-mark increase in the test score, on average.
如果相关性呈线性且显著，则拟合一条最小二乘回归线，形式为 y = a + bx。对于我们的数据，方程约为 y = 12.4 + 6.4x。斜率 (6.4) 意味着平均而言，每增加一小时学习时间，测验分数增加约 6.4 分。
Use the equation to make predictions within the range of the data (interpolation). For a student studying 5.5 hours, the predicted score is y = 12.4 + 6.4 × 5.5 ≈ 47.6 marks. Avoid extrapolation beyond 8 hours since the relationship may change outside the observed interval.
使用方程在数据范围内进行预测（内插）。对于学习 5.5 小时的学生，预测分数为 y = 12.4 + 6.4 × 5.5 ≈ 47.6 分。避免外推到 8 小时以外，因为在观察区间之外关系可能会改变。
Always state that the regression line is a model, not an exact rule. Check residuals (actual minus predicted) to spot any student whose score is markedly different from the prediction; this can lead to deeper insights.
始终说明回归线是一个模型，而非精确规则。检查残差（实际值减预测值），找出任何分数与预测值显著不同的学生；这可以带来更深层次的洞见。
10. Conclusions, Limitations and Communication | 结论、局限与沟通
Write a clear conclusion: ‘There is strong evidence of a positive linear correlation between weekly study hours and mathematics test scores in Year 11. For every additional hour studied, the score improved on average by 6.4 marks within the observed range.’
写出清晰的结论：“有强有力的证据表明，11 年级学生每周学习小时数与数学测验分数之间存在正线性相关。在观察范围内，每多学习一小时，分数平均提高 6.4 分。”
Discuss limitations honestly. The sample came from one school, so results may not generalise. Correlation does not imply causation: other variables like motivation or prior attainment could influence both study hours and scores. Measurement of study hours relied on self-reporting, which may be inaccurate.
诚实地讨论局限性。样本来自一所学校，因此结果可能无法推广。相关性并不暗示因果关系：动机或先前成绩等其他变量可能同时影响学习时间和分数。学习时间的测量依赖自我报告，可能不准确。
Propose improvements: a larger stratified sample across multiple schools, a diary method to track study time, and controlling for other variables through a multiple regression. Explain how these changes would increase the reliability and validity of the investigation.
提出改进建议：从多所学校抽取更大的分层样本，使用日记方法追踪学习时间，并通过多元回归控制其他变量。说明这些改变如何提高调查的可靠性和有效性。
Communicate findings appropriately for the audience. A written report with annotated scatter plot, regression equation and plain-language summary is suitable for teachers. Use technical vocabulary – correlation coefficient, significance, residual – as expected at GCSE level.
为受众选择合适的沟通方式。一份包含带标注的散点图、回归方程和通俗语言摘要的书面报告适用于教师。在 GCSE 层级中，应使用相关系数、显著性、残差等专业词汇。
Reflect on the whole process. A statistical case study is more than calculation; it is a cycle of planning, doing, reviewing and improving. This reflective skill is highly valued by CCEA examiners.
反思整个流程。统计案例分析不仅仅是计算；它是一个计划、执行、回顾和改进的循环。这种反思性技能极受 CCEA 考官重视。
Published by TutorHao | Statistics 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