📚 Statistical Report Writing Framework for WJEC Year 11 | Year 11 WJEC 统计论文写作框架与范文
Writing a statistical report for WJEC Year 11 can feel daunting, but with a clear framework and understanding of the assessment criteria, you can produce a well-structured, evidence-based analysis. This article provides a step-by-step guide to constructing a high-scoring statistical report, covering the PPDAC cycle, descriptive and inferential techniques, and common pitfalls. A sample report on mobile phone usage and sleep quality is included to illustrate best practice.
为 WJEC Year 11 撰写统计论文可能令人生畏，但有了清晰的框架和对评分标准的理解，你就能写出一份结构严谨、基于证据的分析报告。本文逐步指导如何构建高分的统计报告，涵盖 PPDAC 循环、描述性和推断性统计技巧以及常见误区，并附上一篇关于手机使用与睡眠质量的范文，以展示最佳做法。
1. Understanding the PPDAC Cycle | 理解 PPDAC 循环
The backbone of any WJEC statistical report is the PPDAC cycle: Problem, Plan, Data, Analysis, Conclusion. This structured approach ensures your investigation is logical, thorough, and meets the syllabus requirements. Start by defining a clear problem or question, then plan your data collection carefully before gathering data. Analyse the data using appropriate techniques, and finally draw a well-supported conclusion.
任何 WJEC 统计报告的核心都是 PPDAC 循环：问题、计划、数据、分析、结论。这种结构化的方法能确保你的调查逻辑清晰、全面详尽，并符合课程大纲的要求。首先应明确问题或研究问题，然后仔细规划数据收集方案，再收集数据。随后使用适当的技术分析数据，最后得出有数据支撑的结论。
Following this cycle will help you stay focused and ensure that every section of your report addresses the three assessment objectives: AO1 (recalling and selecting statistical methods), AO2 (applying techniques accurately), and AO3 (interpreting results and evaluating the process). Examiners look for evidence that you have moved through each stage deliberately, not just presented a series of disconnected calculations.
遵循这个循环有助于你保持专注，并确保报告的每个部分都能对应三个评估目标：AO1（回忆与选择统计方法）、AO2（准确应用技术）和 AO3（解释结果与评价过程）。考官寻找的证据是你能有意识地经历每个阶段，而不仅仅是呈现一系列互不关联的计算。
2. Defining the Problem and Hypothesis | 确定问题与假设
Your report must begin with a precise research question, such as ‘Is there a relationship between the number of hours Year 11 students spend on their phones per day and their self-reported sleep quality?’ Then state a null hypothesis (e.g., ‘There is no correlation between phone usage and sleep quality’) and an alternative hypothesis (e.g., ‘There is a negative correlation between phone usage and sleep quality’). This sets the statistical foundation for your test.
你的报告必须以一个精确的研究问题开头，例如：“Year 11 学生每天使用手机的时长与自报睡眠质量之间是否存在关系？”然后提出零假设（如“手机使用时间与睡眠质量之间无相关性”）和备择假设（如“手机使用时间与睡眠质量之间存在负相关”）。这为你的统计检验奠定了理论基础。
The hypothesis must be clearly directional if you are using a one-tailed test, or non-directional for a two-tailed test. Avoid vague phrases like ‘there may be a link’ – go for a statement that can be tested. For instance, write ‘The more hours students spend on their phones, the lower their sleep quality score’ as your alternative hypothesis when appropriate.
如果使用单尾检验，假设必须明确方向；如果使用双尾检验，则假设应是无方向的。避免使用“可能存在某种联系”等模糊措辞——要给出一个可检验的陈述。例如，适当时可将备择假设写为“学生在手机上花费的时间越多，其睡眠质量得分越低”。
3. Planning and Data Collection | 计划与数据收集
Describe your sampling method, such as stratified sampling by gender or simple random sampling from the Year 11 cohort. Justify your choice to minimise bias. Specify your variables: the independent variable (e.g., daily hours of phone use) and the dependent variable (e.g., sleep quality score on a scale of 1-10). Detail your data collection tool, like a questionnaire, and discuss ethical considerations, including anonymity and consent.
描述你的抽样方法，例如按性别分层抽样或从 Year 11 群体中简单随机抽样，并说明选择的理由以尽量减少偏差。明确你的变量：自变量（如每日手机使用时长）和因变量（如睡眠质量评分，1-10 分）。详细说明数据收集工具，如问卷，并讨论伦理考量，包括匿名和知情同意。
Aim for a sample size of at least 30 to enable reliable conclusions; smaller samples increase the margin of error and make it harder to detect genuine effects. If using a questionnaire, pilot it with a few classmates to check for ambiguous wording. Always keep a record of how many people were invited and how many actually responded, as non-response bias can weaken your findings.
样本量应至少为 30，以便得出可靠的结论；较小的样本会增加误差幅度，更难发现真实效应。如果使用问卷，先找几位同学试填，以检查措辞是否有歧义。同时要记录邀请了多少人以及实际回应了多少人，因为无回应偏差会削弱研究结论。
4. Data Cleaning and Organisation | 数据清理与整理
Before analysis, clean your data by checking for errors, outliers, or missing values. Present the raw data in a well-labelled table, ensuring all units are clear. If using a spreadsheet, explain how you handled anomalies. For example, an entry of 24 hours of phone use might be excluded as a data entry error. Organise the cleaned data into a frequency table or a grouped frequency table if the data range is large.
在分析之前，需清理数据：检查错误、异常值或缺失值。将原始数据呈现在标注清晰的表格中，确保所有单位明确。如果使用电子表格，解释你如何处理异常情况。例如，一个 24 小时的手机使用记录可能作为数据录入错误被剔除。将清理后的数据整理成频数表，如果数据范围较大，则整理成分组频数表。
When grouping continuous data, choose class intervals of equal width and avoid open-ended classes like ’10 or more’. State the boundaries clearly, e.g., 2 ≤ x < 4. This clarity is vital if you later need to calculate estimates of the mean or plot a histogram. Also explain any data transformations, such as converting text responses into numerical scores.
在对连续数据分组时，应选择等宽的组距，并避免使用诸如“10 及以上”的开放组。要清楚地标明边界，如 2 ≤ x < 4。若之后需估算均值或绘制直方图，这种清晰度至关重要。同时，要解释任何数据转换，例如将文字回答转化为数值评分的过程。
5. Descriptive Statistics and Visualisation | 描述性统计与可视化
Calculate measures of central tendency (mean, median, mode) and dispersion (range, interquartile range, standard deviation) for each variable. Use appropriate charts: a scatter graph to show the relationship between phone use and sleep quality, box plots to compare distributions by gender, and histograms for the distribution of hours. Label axes clearly and include a title for every graph.
计算每个变量的集中趋势度量（平均值、中位数、众数）和离散度量（全距、四分位距、标准差）。使用适当的图表：散点图展示手机使用与睡眠质量的关系，箱线图比较不同性别的分布，直方图展示使用时长的分布。坐标轴应标注清晰，每个图表都应包含标题。
When presenting a box plot, always label the five-number summary: minimum, lower quartile, median, upper quartile, and maximum. Use it to identify outliers, which are typically plotted as individual points beyond 1.5 × IQR from the quartiles. Comment on the shape, spread, and any clustering of data, as this prepares you for deeper analysis later.
在展示箱线图时，一定要标注五数概括：最小值、下四分位数、中位数、上四分位数和最大值。用箱线图来识别异常值，异常值通常以单独的点标出，位于四分位数外 1.5 倍 IQR 的位置。对数据的形状、散布和聚集情况加以评论，这能为你随后的深入分析做好准备。
6. Choosing the Right Graph and Table | 选择正确的图表与表格
Selecting the correct graphical representation is essential. Use bar charts for discrete categories, histograms for continuous data, frequency polygons for overlapping distributions, and pie charts only for simple percentage breakdowns with few categories. Scatter diagrams are for bivariate numerical data. A poorly chosen graph can mislead the reader and lose you marks in AO1.
选择正确的图形表示至关重要。离散分类数据用条形图，连续数据用直方图，重叠分布用频数折线图，饼图只用于类别较少时的简单百分比展示。散点图则适用于双变量数值型数据。选择不当的图形会误导读者，并在 AO1 中失分。
Tables should be neat and self-explanatory with headings and units in the top row. Where possible, present summary statistics like mean and standard deviation alongside the graph. Never rely on a graph alone to convey the numerical story; always support it with a sentence or two of interpretation.
表格应整洁、一目了然，标题和单位应放在首行。尽可能在图形旁同时呈现均值、标准差等汇总统计量。切勿仅靠图形来传达数值信息，始终用一两句解读加以辅助。
7. In-depth Analysis: Correlation and Regression | 深入分析：相关与回归
If investigating a relationship, calculate Spearman’s rank correlation coefficient (rₛ) or Pearson’s product-moment correlation coefficient (r), depending on the data type. For ranked or non-linear monotonic data, use Spearman’s; for normally distributed, linear data, use Pearson’s. Then perform a hypothesis test for correlation, comparing your test statistic to the critical value at the 5% significance level. You may also fit a regression line to make predictions, but discuss its limitations.
如果研究的是关系，根据数据类型计算斯皮尔曼秩相关系数（rₛ）或皮尔逊积矩相关系数（r）。对于等级数据或非线性单调关系，使用斯皮尔曼系数；对于正态分布的线性数据，使用皮尔逊系数。然后进行相关性假设检验，将检验统计量与 5% 显著性水平下的临界值进行比较。你也可以拟合回归直线进行预测，但要讨论其局限性。
When interpreting r, remember that a strong correlation does not imply causation. Also mention the coefficient of determination, R², which tells you the percentage of variation in the response variable explained by the explanatory variable. If R² is very low, your model has weak predictive power. Always check the residuals for patterns, as a curved pattern suggests a non-linear relationship that may require a different approach.
解读 r 值时，请记住强相关性并不意味着因果关系。还要提及决定系数 R²，它告诉你响应变量的变异中有多少百分比可由解释变量解释。如果 R² 非常低，说明模型的预测力很弱。务必检查残差中的规律性，若出现曲线规律则暗示可能存在非线性关系，需要采用不同的方法。
8. Interpreting p-values and Significance | 解读 P 值与显著性
The p-value is the probability of obtaining your observed result, or one more extreme, if the null hypothesis were true. A common threshold is 0.05 (5%). If p < 0.05, you reject the null hypothesis and call the result 'statistically significant'. In WJEC exams, you may be asked to find the critical value from tables rather than calculate the exact p-value, but the logic is the same: compare your test statistic to the critical value.
P 值是在零假设为真的情况下，获得当前观测结果或更极端结果的概率。常用的阈值为 0.05（5%）。若 P < 0.05，则拒绝零假设，并称结果“具有统计学显著性”。在 WJEC 考试中，你可能需要从表中查找临界值，而不是计算精确的 P 值，但逻辑是相同的：将检验统计量与临界值进行比较。
Avoid the common mistake of saying ‘the alternative hypothesis is proven’. Significance testing provides evidence against the null, not proof of an alternative. Also, never state that a non-significant result ‘proves no effect’; it simply means you did not have enough evidence to reject H₀, which could be due to a small sample size.
避免常见错误，如说“备择假设得到了证实”。显著性检验提供的是反对零假设的证据，而不是对备择假设的证明。同样，永远不要说“不显著的结果证明了没有效应”，它只是意味着你没有足够的证据拒绝 H₀，这可能是因为样本量太小。
9. Conclusion and Evaluation | 结论与评估
State clearly whether you reject or fail to reject the null hypothesis, in the context of the original problem. Summarise key findings and their real-world implications. Then critically evaluate your investigation: discuss sources of bias (sampling, measurement, response), the reliability of your data, and any improvements you could make, such as increasing sample size or using more objective sleep trackers.
明确说明你是否拒绝零假设，并结合原始问题加以解释。总结主要发现及其现实意义。然后批判性地评估你的调查：讨论偏差来源（抽样、测量、应答偏差）、数据的可靠性，以及你可以做出的改进，例如增加样本量或使用更客观的睡眠追踪器。
A strong evaluation also acknowledges what went well and whether the sample was representative. If you found an unusual outlier, discuss its possible cause and how you decided to treat it. Finally, suggest a related question that could be investigated next, showing that you understand the investigation cycle continues.
一份有力的评估还应承认做得好的地方以及样本是否具有代表性。如果你发现了异常值，要讨论其可能的成因以及你是如何处理它的。最后，提出一个可以继续研究的相关问题，以表明你明白调查循环是可延续的。
10. Sample Report: Mobile Usage and Sleep | 范文展示：手机使用与睡眠
Problem: This investigation aims to determine if there is a negative correlation between daily mobile phone screen time (hours) and self-rated sleep quality (1–10, 10 being excellent) among Year 11 students at a Welsh secondary school. Null hypothesis: ρ = 0; Alternative hypothesis: ρ < 0 (one-tailed test).
问题：本调查旨在研究威尔士一所中学的 Year 11 学生每日手机屏幕使用时间（小时）与自评睡眠质量（1–10，10 为极好）之间是否存在负相关。零假设：ρ = 0；备择假设：ρ < 0（单尾检验）。
Plan: Stratified random sampling was used to select 30 students (15 male, 15 female) from the Year 11 cohort. A questionnaire collected data on average daily phone screen time and sleep quality over the past week. All participants gave informed consent.
计划：采用分层随机抽样，从 Year 11 群体中选取 30 名学生（15 男，15 女）。问卷收集了过去一周的日均手机屏幕使用时间和睡眠质量数据。所有参与者均知情同意。
Data: The cleaned data ranged from 1.5 to 9.2 hours of phone use, and sleep quality scores from 2 to 9. A negative pattern was visible in the scatter graph. Spearman’s rank correlation coefficient was calculated as rₛ = -0.68 (n=28 after removing two incomplete responses).
数据：清理后的数据中，手机使用时间从 1.5 到 9.2 小时，睡眠质量评分从 2 到 9 分。散点图中可见负向模式。斯皮尔曼秩相关系数计算得 rₛ = -0.68（剔除 2 份无效回答后 n=28）。
Analysis: The critical value for a one-tailed test at the 5% level with 26 degrees of freedom is approximately 0.331. Since | -0.68 | > 0.331, we reject the null hypothesis. The probability of obtaining this result by chance is less than 5%. The regression equation Sleep Quality = 11.2 – 1.1 × Phone Hours explains 46% of the variation (R² = 0.46).
分析：单尾 5% 显著性水平下自由度为 26 的临界值约为 0.331。由于 | -0.68 | > 0.331，我们拒绝零假设。获得这一结果由偶然造成的概率小于 5%。回归方程 睡眠质量 = 11.2 – 1.1 × 手机使用时间 解释了 46% 的变异（R² = 0.46）。
Conclusion: There is significant evidence of a moderate negative correlation between phone screen time and sleep quality. However, causation cannot be inferred; other variables like stress may also play a role. The sample was limited to one school, so generalisability is restricted. Future studies could use sleep tracking devices for more accurate data.
结论：有显著证据表明手机屏幕时间与睡眠质量之间存在中等程度的负相关。然而，不能推断因果关系；压力等其他变量也可能起作用。样本仅限于一所学校，因此推广性受限。未来研究可使用睡眠追踪设备获取更准确的数据。
Published by TutorHao | Year 11 统计 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Cancel reply