📚 IGCSE OCR Statistics: Experimental/Practical Assessment Key Points | IGCSE OCR 统计：实验/实践考核要点
In IGCSE OCR Statistics, practical or experimental assessment focuses on your ability to apply statistical thinking to real-world problems. This involves planning an investigation, collecting and processing data, and drawing meaningful conclusions. While the final examination is written, questions are often rooted in practical scenarios, testing your understanding of how a statistician works from start to finish. Mastering these practical skills is essential for tackling questions about survey design, sampling, and data analysis.
在 IGCSE OCR 统计课程中，实践或实验考核侧重于你将统计思维应用于实际问题的能力。这包括规划一项调查、收集和处理数据，以及得出有意义的结论。虽然最终的考试是笔试，但题目往往基于实践场景，考察你从始至终像一位统计学家那样工作的理解。掌握这些实践技能对于应对问卷设计、抽样和数据分析等题型至关重要。
1. Understanding the Practical Assessment | 理解实践考核
The practical assessment in IGCSE OCR Statistics is not a separate laboratory exam but rather the application of statistical enquiry skills throughout the syllabus. You are expected to demonstrate the ability to formulate a hypothesis or a question, design a data collection plan, collect or interpret provided data, and evaluate the whole process. Many exam questions present a mini-investigation and ask you to critique the method or suggest improvements, mirroring real practical work.
IGCSE OCR 统计中的实践考核并非单独的实验室考试，而是统计探究技能在全部课程内容中的应用。你需要展现出制定假设或提出问题、设计数据收集方案、收集或解读给定数据以及评估整个过程的能力。很多考题会呈现一个小型调查，要求你评论其方法或提出改进建议，这就模拟了真实的实践工作。
The key stages of a statistical investigation form the backbone of the practical assessment: planning, collecting, processing, presenting, and interpreting. You need to know how to move logically through each stage and be able to justify decisions about sample size, sampling method, and data collection tool.
统计调查的关键阶段构成了实践考核的骨架：规划、收集、处理、展示和解读。你需要懂得如何合乎逻辑地推进每个阶段，并能为关于样本大小、抽样方法和数据收集工具的选择提供理由。
2. Planning a Statistical Investigation | 规划统计调查
Every successful practical investigation starts with a clear research question or hypothesis. A good hypothesis is specific, measurable, and clearly states what you expect to find. For example, ‘Pupils in Year 11 spend more hours per week on homework than pupils in Year 9’ is a testable statement. Avoid vague questions that cannot be answered with data.
每一项成功的实践调查都始于清晰的研究问题或假设。好的假设是具体的、可测量的，并清楚说明你预期会发现什么。例如，“十一年级学生每周花在家庭作业上的时间多于九年级学生”就是一个可验证的陈述。要避免那些无法用数据回答的含糊问题。
Next, identify your population and decide on the variables to be measured. The population is the entire group you want to draw conclusions about, such as all students in a school. Variables can be categorical (e.g., eye colour) or numerical (e.g., height). Define each variable clearly and decide whether it will be discrete or continuous data.
接下来，确定你的总体并决定要测量的变量。总体是你希望得出与之相关结论的整个群体，例如一所学校的所有学生。变量可以是分类的（如眼睛颜色）或数值的（如身高）。要清楚地定义每个变量，并判断它是离散数据还是连续数据。
3. Sampling Techniques | 抽样方法
It is usually impractical to collect data from every member of a population, so you need to select a sample. The choice of sampling method directly affects the reliability and validity of your conclusions. You must be able to justify why a particular method is suitable for a given investigation.
通常收集总体中每个成员的数据是不切实际的，因此你需要选择一个样本。抽样方法的选择直接影响到结论的可靠性和有效性。你必须能够说明为什么某种方法适用于某个特定的调查。
The main sampling techniques you should know for practical work are:
在实践工作中你需要了解的主要抽样方法有：
- Simple random sampling — every member has an equal chance of selection, often using random number generators. / 简单随机抽样 — 每个成员被选中的机会均等，通常使用随机数生成器。
- Stratified sampling — the population is divided into groups (strata) based on a relevant characteristic, and a random sample is taken from each group in proportion to its size. / 分层抽样 — 根据相关特征将总体划分为若干组（层），然后按各层大小比例从中随机抽取样本。
- Systematic sampling — select every kth member from a list, starting from a random point. / 系统抽样 — 从一个随机起点开始，在名单上每隔 k 个成员选取一个。
- Cluster sampling — split the population into clusters, randomly select some clusters, and collect data from all members within those clusters. / 整群抽样 — 将总体分成群，随机选取若干群，然后收集这些群内所有成员的数据。
- Quota sampling — divide the population into groups and set a quota for each group, then select participants non-randomly until the quotas are filled. / 配额抽样 — 将总体分成组并为每组设定配额，然后非随机地选取参与者直至配额填满。
In an experimental or practical context, you must also consider sample size. A larger sample generally gives more precise estimates, but you need to balance practical constraints such as time and cost.
在实验或实践背景下，你还必须考虑样本大小。较大的样本通常能给出更精确的估计，但你需要权衡时间和成本等实际限制因素。
4. Designing Data Collection Tools | 设计数据收集工具
Once the sampling plan is ready, you need a reliable tool to collect data. In many IGCSE statistics tasks, this takes the form of a questionnaire, an observation sheet, or an experimental record. The design of your tool must minimise bias and collect exactly the information required to answer your research question.
抽样方案就绪后，你需要一个可靠的工具来收集数据。在许多 IGCSE 统计任务中，这一工具表现为问卷、观察记录表或实验记录。工具的设计必须最大限度地减少偏差，并准确收集回答研究问题所需的信息。
When designing a questionnaire, questions should be short, unambiguous, and neutral. Avoid leading questions like ‘Don’t you agree that homework is boring?’ Instead, ask ‘How many hours per week do you spend on homework?’ Use closed questions (multiple choice, tick boxes) for easier analysis, but occasionally open questions can capture richer detail.
设计问卷时，问题应简短、无歧义且中立。避免引导性问题，如“你难道不觉得家庭作业很无聊吗？”。应改为“你每周花多少小时做家庭作业？”。为便于分析，可使用封闭式问题（选择题、复选框），但偶尔开放式问题可以捕捉更丰富的细节。
Pre-test your data collection tool with a small pilot group. This helps identify confusing wording or missing response categories before you commit to the full-scale data collection. In the IGCSE course, you are often asked to suggest improvements to a given questionnaire, so understanding piloting is crucial.
先在一小群人中预测试你的数据收集工具。这有助于在全面开展数据收集之前发现令人困惑的措辞或缺失的答案类别。在 IGCSE 课程中，你常常需要为给定的问卷提出改进建议，因此理解试点测试至关重要。
5. Collecting Data Ethically and Accurately | 合乎道德且准确地收集数据
Practical data collection must follow ethical guidelines. Always obtain informed consent from participants, explaining how their data will be used. Anonymise the data so that individuals cannot be identified. If you are conducting an experiment, ensure no harm comes to participants. In school-based projects, these principles are often tested through scenario-style questions.
实践数据收集必须遵循道德准则。始终要取得参与者的知情同意，说明他们的数据将如何使用。将数据匿名化，使个体无法被识别。如果你在进行实验，要确保参与者不会受到伤害。在学校项目中，这些原则常通过情景式题目来考查。
Accuracy is equally important. Data should be recorded immediately and clearly. When measuring, use appropriate tools and repeat measurements if possible to reduce random error. For example, if measuring pulse rate after exercise, do it quickly and consistently. Recording data in a well-organised table directly on the spot prevents mistakes later.
准确性同样重要。数据应立即并清晰地记录下来。测量时应使用适当的工具，如有可能应重复测量以减少随机误差。例如，测量运动后的心率，要快速且一致地进行。当场将数据记录在条理清晰的表格中可以避免事后出错。
In exam problems, you may be presented with a poorly recorded dataset and asked to identify anomalies or potential sources of error. Always check for impossible values, such as a height of 500 cm or a negative age.
在考试中，你可能会遇到记录不佳的数据集，并被要求找出异常值或潜在的误差来源。一定要检查是否有不可能的值，比如身高 500 cm 或负的年龄。
6. Organising and Cleaning Data | 整理与清洗数据
Raw data is rarely ready for analysis. You need to organise it into frequency tables or spreadsheets. For categorical data, tally tables help count occurrences. For numerical data, grouping into class intervals makes patterns easier to spot. Decide on appropriate interval widths: too wide and you lose detail, too narrow and the data remains cluttered.
原始数据很少能直接用于分析。你需要将其整理成频数表或电子表格。对于分类数据，用划记表帮助统计出现次数。对于数值数据，分组到组距区间会使模式更易于识别。要选择合适的组距宽度：太宽会丢失细节，太窄则数据仍然杂乱。
Data cleaning involves checking for outliers and missing values. An outlier is a value that lies far away from the rest of the data. You need to decide whether to keep it, remove it, or investigate further. In practical assessments, you must be able to explain how an outlier could affect your summary statistics and conclusions.
数据清洗包括检查异常值和缺失值。异常值是远离其他数据的值。你需要决定是保留、剔除还是进一步调查它。在实践考核中，你必须能够解释异常值会如何影响你的汇总统计量和结论。
When faced with a missing response, never just ignore the whole entry. If it is reasonable, you may impute a value, such as using the mean of the remaining data, but always note this assumption. In IGCSE questions, simpler tasks often require you to identify that missing data reduces sample size and may introduce bias.
遇到缺失的回答时，切勿直接忽略整条记录。如果合理，你可以估算一个值，例如使用剩余数据的平均值，但要务必注明这一假设。在 IGCSE 题目中，较简单的任务通常要求你认识到缺失数据会减少样本量并可能引入偏差。
7. Representing Data Appropriately | 恰当地展示数据
Data visualisation is a core practical skill. The choice of chart or graph depends on the type of data and what you want to show. Bar charts are for categorical data, pie charts show proportions of a whole, and line graphs display trends over time. Histograms (with frequency density) are for continuous data grouped into unequal intervals.
数据可视化是一项核心实践技能。图表的选择取决于数据类型和你想要展示的内容。条形图用于分类数据，饼图显示整体中各部分的比例，折线图展示随时间变化的趋势。直方图（使用频数密度）用于分组间距不等时的连续数据。
In practical work, always label axes clearly, give the graph a title, and use an appropriate scale. Avoid distorting the scale to exaggerate differences. For scatter diagrams, plot points accurately and draw a line of best fit if there is a clear correlation. Do not force a straight line through a curved pattern.
在实践工作中，务必清楚地标注坐标轴，给图表加标题，并使用合适的刻度。避免扭曲刻度以夸大差异。对于散点图，要精确描点，如果相关关系明显则画出最佳拟合线。不要强行在曲线模式中画出直线。
When constructing a cumulative frequency curve, plot the upper class boundary against the cumulative frequency and join the points with a smooth curve. The median and quartiles can then be read from the graph. Always show your working for these readings, as examiners check your graph interpretation.
绘制累积频数曲线时，将组距上界与累积频数相交描点，并用平滑曲线连接各点。然后可以从图形中读取中位数和四分位数。在读取时要始终标出操作过程，因为考官会考察你解读图形的能力。
8. Calculating Summary Statistics | 计算汇总统计量
After displaying data, you must calculate measures of central tendency and spread. The mean, median, and mode summarise the centre of the data. For practical assessments, you should be able to select the most appropriate average. The median is often better when there are outliers, as it is not affected by extreme values.
展示数据之后，你必须计算集中趋势和离差的度量。平均数、中位数和众数概括了数据的中心。在实践考核中，你应该能够选择最合适的平均值。当存在异常值时，中位数通常更好，因为它不受极端值的影响。
The three main calculations for a dataset are:
mean = Σx / n
The mean uses all values and is suitable for symmetric distributions. / 平均数使用了所有数值，适用于对称分布。
median position = (n + 1) / 2
The median is the middle value when data is ordered. / 中位数是数据排序后位于中间的值。
range = maximum − minimum
The range shows the spread but is sensitive to outliers. More robust measures are the interquartile range (IQR = Q₃ − Q₁) and standard deviation. / 极差展示了离散程度，但对异常值敏感。更稳健的度量是四分位距 (IQR = Q₃ − Q₁) 和标准差。
For grouped data, use the midpoints of class intervals to estimate the mean. In practical investigations, comparing summary statistics between groups—for instance, comparing the mean hours of homework for Year 9 and Year 11—can help answer your initial hypothesis.
对于分组数据，使用组距区间的中点来估算平均数。在实践调查中，比较不同组别之间的汇总统计量——例如比较九年级和十一年级家庭作业的平均时长——可以帮助回答你最初的假设。
9. Interpreting Results and Drawing Conclusions | 解释结果与得出结论
Once summary statistics and charts are ready, you must interpret them in the context of the original question. Do not just state numbers; explain what they mean. For example, ‘The median of Year 11 homework time is 8 hours, which is 3 hours higher than the median for Year 9, supporting the hypothesis that older students spend more time on homework.’
汇总统计量和图表准备好之后，你必须结合原始问题的背景对其进行解释。不要只罗列数字，而要解释它们的含义。例如，“十一年级家庭作业时间的中位数为 8 小时，比九年级的中位数高出 3 小时，这支持了关于高年级学生花更多时间做作业的假设。”
Consider the strength of any relationship you have found. If you used a scatter diagram, describe the correlation: positive, negative, or none, and note its strength (strong, moderate, weak). You can informally assess correlation strength, but you should also recognise that correlation does not imply causation. An observed pattern might be due to another hidden variable.
考虑你发现的任何关系的强度。如果你使用了散点图，描述相关关系：正相关、负相关或无相关，并注明其强度（强、中、弱）。你可以非正式地评估相关强度，但你也应认识到相关性并不意味着因果关系。观察到的模式可能是由另一个隐藏变量导致的。
When drawing conclusions, be honest. If your data does not clearly support the hypothesis, say so. In practical assessments, credibility comes from recognising limitations rather than forcing a desired outcome.
得出结论时要诚实。如果你的数据没有明确支持假设，就如实说明。在实践考核中，可信度来自于认识到局限性，而不是强行得出期望的结果。
10. Evaluating the Investigation | 评估调查过程
Evaluation is a critical final stage that is frequently tested. You need to reflect on the entire process and identify sources of bias or error. Did the sampling method lead to a representative sample? Were the measuring instruments reliable? In a questionnaire, was there any non-response bias because some people refused to participate?
评估是常被考查的重要收尾阶段。你需要反思整个过程并指出偏差或错误的来源。抽样方法是否得到了代表性样本？测量工具可靠吗？在问卷调查中，是否存在因有人拒绝参与而导致的未响应偏差？
List specific limitations and, for each, propose a realistic improvement. For instance, ‘Only 20 students were surveyed, which may not be sufficient to generalise. In future, increase the sample size to at least 50 and include students from different classes.’ Another common improvement is to extend the measurement period to reduce day-to-day variation.
列出具体的局限性，并针对每一项提出切实可行的改进建议。例如，“仅调查了 20 名学生，可能不足以进行推广。未来应将样本量增加到至少 50 人，并纳入不同班级的学生。”另一种常见的改进是延长测量时长以减少日间波动。
You might also discuss whether any extraneous variables could have influenced the results. In an experiment comparing reaction times, factors such as tiredness or distraction could affect individuals. In the IGCSE exam, you should be ready to suggest controls or a better experimental design, such as a matched pairs design or a controlled environment.
你也可以讨论是否有任何无关变量可能影响了结果。在比较反应时间的实验中，疲劳或分心等因素可能会影响个体。在 IGCSE 考试中，你应准备好提出控制措施或更好的实验设计方案，例如配对设计或受控环境。
11. Working with Probability Experiments | 处理概率实验
Practical statistics often includes simple probability experiments, such as tossing coins, rolling dice, or drawing cards. These experiments help you understand relative frequency and the concept of expected outcomes. In an assessment, you might be asked to conduct a trial and compare experimental probability with theoretical probability.
实践统计常常包含简单的概率实验，如抛硬币、掷骰子或抽扑克牌。这些实验有助于你理解相对频数和期望结果的概念。在考核中，你可能会被要求进行一次试验，并将实验概率与理论概率进行比较。
To obtain reliable experimental probabilities, you need a large number of trials. A common task is to toss two coins 50 times and record the frequency of at least one head. The experimental probability is then (frequency of event) ÷ (total trials). The larger the sample, the closer this relative frequency tends to get to the theoretical value (the Law of Large Numbers).
要获得可靠的实验概率，你需要大量的试验。一项常见任务是抛两枚硬币 50 次，并记录至少出现一个正面的频数。实验概率即为（事件发生频数）÷（总试验次数）。根据大数定律，样本越大，这个相对频数就越趋近于理论值。
When presenting probability experiment results, a two-way table or a tree diagram can be used to list all possible outcomes and verify the theoretical probability. For example, the probability of getting at least one head when flipping two coins is 1 − P(two tails) = 1 − ¼ = ¾. Comparing this with your experimental result allows you to comment on the accuracy of your experiment.
展示概率实验结果时，可以使用双向表或树状图列出所有可能结果，并验证理论概率。例如，抛两枚硬币至少出现一个正面的概率为 1 − P(两个反面) = 1 − ¼ = ¾。将此与你实验得到的结果进行比较，可以让你对实验的准确度做出评价。
12. Common Pitfalls and How to Avoid Them | 常见陷阱及如何避免
Many students lose marks on practical-style questions because of avoidable mistakes. One of the most frequent is confusing discrete and continuous data when choosing a diagram—using a line graph for discrete categories instead of a bar chart. Also, when drawing a histogram with unequal class widths, forgetting to calculate frequency density (frequency ÷ class width) leads to incorrect bar heights.
许多学生在实践类题目中因可以避免的错误而失分。最常见的一个错误是在选择图表时将离散数据和连续数据混淆——用折线图来表示离散类别，而应该使用条形图。同时，在绘制不等组距的直方图时，忘记计算频数密度（频数 ÷ 组距宽度）也是导致柱高绘制不正确的常见原因。
Another pitfall is misinterpreting the purpose of a control group in an experiment. If you are testing a new teaching method, a control group using the standard method is essential for comparison. Without it, you cannot attribute any improvement to the new method. Always ask: what are you comparing against?
另一个陷阱是误解实验中对照组的目的。如果你在测试一种新的教学方法，那么一个使用标准方法的对照组对于比较是必不可少的。没有它，你就无法将任何改进归因于新方法。始终要问：你在拿什么进行比较？
Finally, remember to link your conclusions back to the original hypothesis and the population. A valid interpretation is specific, so avoid over-generalising. For example, a conclusion about ‘students in one school’ should not be presented as a claim about ‘all teenagers’. This demonstrates careful scientific reasoning and is essential for the evaluation stage.
最后，记得将你的结论与最初的假设和总体联系起来。有效的解释是具体的，因此要避免过度推广。例如，关于“某校学生”的结论不应被表述为适用于“所有青少年”的论断。这展示了严谨的科学推理能力，对于评估阶段至关重要。
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