📚 Year 10 CCEA Statistics: Unit Test Mock Paper Analysis | Year 10 CCEA 统计：单元测试模拟卷解析
This article provides a step-by-step analysis of a typical Year 10 CCEA Statistics unit test. We will break down key question types, highlight common pitfalls, and offer clear revision strategies to help you master the subject. Each section corresponds to a question or concept you are likely to encounter, with detailed explanations in both English and Chinese.
本文将对一份典型的 Year 10 CCEA 统计单元测试进行逐步解析。我们将拆解重点题型，指出常见错误，并提供清晰的复习策略，帮助你掌握这门学科。每个部分对应一个你可能遇到的题目或概念，并配有中英双语详细解释。
1. Question 1: Classifying Data Types | 问题1：数据分类
The first question often presents a list of variables and asks you to classify them as qualitative or quantitative, and for quantitative data, further identify whether they are discrete or continuous. Getting this right builds a strong foundation for the rest of your statistical work.
第一道题通常会列出一组变量，要求你将其分类为定性数据或定量数据，并对于定量数据，进一步判断其为离散型还是连续型。正确完成这一步骤将为后续的统计工作打下坚实基础。
Qualitative data describes qualities or categories that cannot be measured with numbers, such as hair colour or car brand. Quantitative data is numerical and can be either discrete (countable, whole numbers like the number of students in a class) or continuous (measurable, any value within a range like height or temperature).
定性数据描述的是无法用数字测量的属性或类别，例如头发颜色或汽车品牌。定量数据则是数值型，可以是离散的（可数的整数，如班级学生人数）或连续的（可测量的、在一定范围内可取任意值的量，如身高或温度）。
A common mistake is confusing discrete and continuous data. Remember: if you can count it precisely and it only takes certain fixed values, it is discrete. If it can be measured more and more finely (theoretically infinite decimal places), it is continuous. For example, the number of goals scored in a football match is discrete; the time taken to run 100 metres is continuous.
一个常见错误是混淆离散数据和连续数据。请记住：如果你能精确地数出它有多少，并且它只取某些固定值，它就是离散的。如果它可以被越来越精细地测量（理论上有无限小数位），它就是连续的。例如，一场足球比赛的进球数是离散的；跑100米所用的时间是连续的。
2. Question 2: Primary and Secondary Data | 问题2：一手数据与二手数据
This section tests your ability to distinguish between data you collect yourself and data that already exists. The examiner may give you a scenario and ask whether the data used is primary or secondary, and to state one advantage of using that type.
这一部分考查你区分自己收集的数据和已有数据的能力。考官可能会给出一个情境，问你所用数据是一手的还是二手的，并要求说明使用该类型数据的一个优点。
Primary data is collected directly by the researcher for a specific purpose, such as conducting a survey or an experiment. Its main advantage is that it is completely relevant and up-to-date, and you control its accuracy. Secondary data is data collected by someone else for a different purpose, such as government statistics, newspapers, or the internet. It is often cheaper and quicker to obtain, and may cover a much larger sample size than you could achieve on your own.
一手数据是由研究者为特定目的直接收集的，例如进行问卷调查或实验。它的主要优点是具有完全的针对性且时效性强，你可以控制其准确性。二手数据是他人为其他目的收集的数据，如政府统计数据、报纸或互联网信息。它通常获取成本更低、速度更快，并且可能涵盖比你独自收集大得多的样本量。
In a typical question, if a student uses a published census report, the data is secondary. If they interview classmates, it is primary. Always link the advantage to the context, e.g., 'using secondary data saved time as the census data was already processed'.
在一道典型题目中，如果学生使用了已发布的人口普查报告，那么数据就是二手的。如果他们对同学进行了面对面采访，则为一手数据。记得要将优点与给定情境关联起来，例如“使用二手数据节省了时间，因为普查数据已经处理好了”。
3. Question 3: Designing a Data Collection Sheet | 问题3：设计数据收集表
You may be shown a partially completed data collection sheet and asked to critique it or fill in the missing parts. This assesses your practical understanding of how to gather clean, usable data.
你可能会看到一个部分完成的数据收集表，被要求进行评价或填写缺失部分。这考查你对如何收集清晰可用数据的实际理解。
A good data collection sheet needs a clear title, labelled rows and columns, and appropriate response boxes (tick boxes for categorical data, numerical spaces for quantitative data). It must avoid overlapping categories — for instance, age groups should not be '0–10, 10–20' because 10 appears in both; use '0–9, 10–19' instead. If the sheet uses tally marks, there must be a frequency column to record the total count.
一个好的数据收集表需要有清晰的标题、标注明确的行列，以及合适的作答框（分类数据用勾选框，定量数据用数字空格）。它必须避免类别重叠——例如，年龄分组不应为“0–10, 10–20”，因为10在两个组中都出现了；应使用“0–9, 10–19”。如果表格使用划记符号，则必须有一个频数列来记录总数。
When you are asked to improve a sheet, check for: insufficient space to write answers, unclear category labels, lack of a frequency column, or bias in the question design. For example, 'Do you agree that our fantastic new menu is great?' is a leading question and should be rewritten neutrally.
当要求你改进一张表格时，请检查：书写答案的空间是否不足、类别标签是否含糊、是否缺失频数列，或问题设计是否有偏见。例如，“你是否同意我们超棒的新菜单太好了？”就是一个诱导性问题，应当改写为中性表述。
4. Question 4: Mean, Median, and Mode | 问题4：平均数、中位数与众数
Calculating the three measures of central tendency from a list or a frequency table is a core skill. The question might present raw data or a grouped frequency distribution.
从列表或频数表中计算三种集中量数是一项核心技能。题目可能会给出原始数据或一个组距式频数分布。
e middle value when data is ordered; for an even number of data points, take the mean of the two middle values. The mode is the most frequent value. In a frequency table, you multiply each value (or midpoint for grouped data) by its frequency, sum the products, and divide by total frequency to estimate the mean.
平均数通过将所有数值相加再除以数值个数来计算：平均数 = (Σx)/n。中位数是将数据排序后位于中间的数；对于偶数个数据点，取中间两个数的平均数。众数是出现频率最高的值。在频数表中，你需要将每个值（或分组数据的中点值）乘以对应频数，加总乘积，再除以总频数来估算平均数。
Consider this frequency table for the number of pets owned by students:
| Number of pets (x) | Frequency (f) | f × x |
|---|---|---|
| 0 | 4 | 0 |
| 1 | 8 | 8 |
| 2 | 5 | 10 |
| 3 | 3 | 9 |
th and 11th values are both 1, so median = 1. Always interpret the answer in context: on average, students have 1.35 pets, but the typical number is 1.
平均数 = Σ(f × x) / Σf = (0+8+10+9) / (4+8+5+3) = 27 / 20 = 1.35 只宠物。众数为1只宠物（频数8）。为求中位数，将20个数据按序排列：第10和第11个值都是1，因此中位数为1。务必结合上下文解释答案：平均每位学生拥有1.35只宠物，但典型的数量是1只。
5. Question 5: Range and Interquartile Range | 问题5：极差与四分位数间距
Measures of spread tell us how consistent or varied the data is. The range is simple, but the interquartile range (IQR) is often preferred because it is not affected by outliers.
离散量数告诉我们数据的稳定或变化程度。极差很简单，但四分位数间距（IQR）通常更受欢迎，因为它不受异常值的影响。
Range = maximum value – minimum value. The IQR = upper quartile (Q3) – he data set has an odd number of values, the median itself is not included in either half.
极差 = 最大值 – 最小值。IQR = 上四分位数 (Q3) – 下四分位数 (Q1)。下四分位数是数据下半部分的中位数，上四分位数是数据上半部分的中位数。如果数据集有奇数个数值，中位数本身不纳入任何一半。
8 → Q1 = (5+7)/2 = 6. The upper half is 13, 15, 18, 21 → Q3 = (15+18)/2 = 16.5. IQR = 16.5 – 6 = 10.5. A larger IQR indicates greater variation in the middle 50% of the data. Students often forget to order the data first, so always check that step.
对于数据集 3, 5, 7, 8, 12, 13, 15, 18, 21（9个值），中位数为12。下半部分为 3, 5, 7, 8 → Q1 = (5+7)/2 = 6。上半部分为 13, 15, 18, 21 → Q3 = (15+18)/2 = 16.5。IQR = 16.5 – 6 = 10.5。IQR 越大表示中间50%的数据变异越大。学生经常忘记先排序，所以务必检查这一步。
6. Question 6: Interpreting Box Plots | 问题6：解读箱线图
A box plot question usually asks you to draw one from a data set or to compare two box plots. It is a visual summary of the five-number summary: minimum, Q1, median, Q3, and maximum.
箱线图题目通常会要求你根据数据集绘制图形，或比较两个箱线图。它是五数概括的直观呈现：最小值、Q1、中位数、Q3 和最大值。
When comparing two box plots, use comparative phrases like 'the median for Group A is higher than for Group B, showing that Group A tends to score more'. Also compare the IQR and the range to discuss spread. For example, 'Group B has a larger IQR, which suggests more variation in the middle 50% of its data'. A longer whisker indicates a wider spread in the top or bottom 25%.
在比较两个箱线图时，应使用比较性短语，如“A组的中位数高于B组，表明A组往往得分更高”。同时比较 IQR 和极差以讨论离散程度。例如，“B组的 IQR 更大，这表明其中间50%的数据变异性更大”。较长的须线表示上下25%的数据分布更广。
To draw an accurate box plot, use a suitable scale on the horizontal axis, mark the five key numbers with short vertical lines, and construct the box from Q1 to Q3 with the median line inside. The whiskers extend to the minimum and maximum values, unless there are outliers, which are marked with crosses. The CCEA exam may ask you to identify the percentage of data above a certain value; from the median, you know 50% of data lies above it.
要绘制准确的箱线图，需在横轴上选择合适的刻度，用短竖线标出五个关键数值，并从 Q1 到 Q3 构建矩形，内部绘制中位线。须线延伸至最小值和最大值，除非有异常值，此时异常值用叉号标出。CCEA 考试可能会要求你找出高于某值的百分比数据；根据中位数，你知道有50%的数据在其上。
7. Question 7: Probability Scales and Basic Events | 问题7：概率尺度与基本事件
Basic probability questions often involve marking probabilities on a scale from 0 (impossible) to 1 (certain), and calculating the probability of a single event.
基础概率题通常会涉及在从0（不可能）到1（必然）的尺度上标记概率，并计算单一事件的概率。
f favourable outcomes / total number of possible outcomes. This can be expressed as a fraction, decimal, or percentage. For example, a fair six-sided die has the probability of rolling a 3 as 1/6. Probabilities must always add up to 1 for all mutually exclusive outcomes in a sample space.
事件概率 = 有利结果数 / 所有可能结果总数。这可以用分数、小数或百分数表示。例如，一个均匀的六面骰子掷出3的概率是 1/6。样本空间中所有互斥结果的概率之和必须为1。
When placing an event on a probability scale, use words like 'even chance' for 0.5, 'unlikely' for values close to 0, and 'likely' for values close to 1. A common CCEA question: ' d, 8 are green, and the rest are yellow. What is the probability of picking a yellow sweet?' Answer: 7/20 = 0.35, which can be described as 'unlikely'.
将事件置于概率尺度上时，0.5 可用“均等机会”描述，接近 0 的值用“不太可能”，接近 1 的值用“很可能”。典型的 CCEA 题目：“一个袋中有20颗糖果，其中5颗红色，8颗绿色，其余为黄色。拿到一颗黄色糖果的概率是多少？”答案：7/20 = 0.35，可描述为“不太可能”。
8. Question 8: Relative Frequency and Expected Frequency | 问题8：相对频数与期望频数
This section links probability with experimental data. You need to calculate relative frequency from an experiment and use it to estimate probability, or use theoretical probability to predict expected frequency.
这一部分将概率与实验数据联系起来。你需要根据实验计算相对频数，并用以估计概率，或使用理论概率预测期望频数。
ds to stabilise around the theoretical probability, demonstrating the law of large numbers. Conversely, expected frequency = probability × number of trials.
相对频数 = （事件发生次数）/（试验总次数）。随着试验次数增加，相对频数会趋于稳定在理论概率附近，这体现了大数定律。反过来，期望频数 = 概率 × 试验次数。
estimate of the probability of heads. If you then flip the coin 500 times, the expected number of heads is 0.55 × 500 = 275. Never round the expected frequency to a whole number unless the context demands it; theoretical answers can remain as decimals.
例如，一枚不均匀的硬币抛掷200次，有110次正面朝上，则正面的相对频数为 110/200 = 0.55。这可作为正面概率的估计值。若再抛掷500次，则正面的期望次数为 0.55 × 500 = 275。切勿将期望频数四舍五入为整数，除非题目情境要求如此；理论答案可以保留小数。
9. Question 9: Scatter Graphs and Correlation | 问题9：散点图与相关性
Scatter graphs are used to investigate the relationship between two variables. You must be able to plot points, describe the correlation, draw a line of best fit, and use it to estimate values.
散点图用于探究两个变量之间的关系。你必须能够绘制数据点、描述相关性、绘制最佳拟合线，并用其估计数值。
Correlation can be positive (as one variable increases, the other tends to increase), negative (one increases, the other decreases), or no correlation. It can be strong, moderate, or weak depending on how close the points are to a straight line. Outliers are points that lie well away from the general pattern and should be identified.
相关性可以是正相关（一个变量增加，另一个也趋于增加）、负相关（一个增加，另一个减少）或无相关。根据数据点接近直线的程度，相关强度可分为强、中等、弱。异常值是明显偏离总体分布模式的数据点，应当予以指出。
When drawing a line of best fit, it should have roughly equal numbers of points on both sides and pass through the mean of the x- and y-values if possible. Interpolation (estimating within the data range) is reliable; extrapolation (estimating beyond the range) is unreliable because the trend may change. Always write your estimate in context: 'A student who studied for 4 hours is estimated to score around 68% on the test'.
绘制最佳拟合线时，应使其两侧数据点数量大致相等，如果可能，使其通过 x 和 y 值的均值点。内插（在数据范围内估计）是可靠的；外推（超出范围估计）则不可靠，因为趋势可能改变。始终结合上下文写出你的估计值：“学习4小时的学生估计考试得分约为68%”。
10. Question 10: Misleading Graphs and Bias | 问题10：误导性图表与偏差
The final question often presents a graph or survey method and asks you to critique it. This tests your ability to spot distortions that can manipulate the reader's interpretation.
最后一道题通常会展示一个图表或调查方法，并让你进行批判。这考查你识别可能操纵读者解读的扭曲手段的能力。
Misleading graphs may use a broken scale on the vertical axis that starts above zero, exaggerating small differences. They might use uneven intervals on the horizontal axis, or 3D effects that make comparisons difficult. The area of bars or sectors might not be proportional to the frequencies they represent.
误导性图表可能在垂直轴上使用不从零开始的截断刻度，从而夸大小差异。它们可能使用不均匀的水平轴区间，或使用难以比较的3D效果。条形或扇区的面积可能与其所代表的频数不成比例。
In terms of survey bias, the question or sampling method may be biased. A sample that is not random may not represent the population. A leading question pushes respondents towards a particular answer. Always suggest an improvement: 'To remove bias, the question should be rephrased neutrally and the sample should be selected randomly from the entire population.'
就调查偏差而言，问题或抽样方法可能存在偏差。非随机样本可能无法代表总体。诱导性问题会推动受访者选择特定答案。一定要提出改进建议：“为消除偏差，问题应重新措辞为中性，并且样本应从整个总体中随机选取。”
For example, a graph showing company profits with a y-axis starting at £900,000 instead of £0 makes a modest growth look dramatic. State that the graph is misleading because the vertical scale is not complete, and correct it by redrawing with the axis starting at 0.
例如，一幅显示公司利润的图表，其 y 轴起点为 £900,000 而非 £0，会使适度的增长显得十分显著。应指出该图表具有误导性，因为垂直刻度不完整，并通过重绘以从0开始的轴来纠正它。
Published by TutorHao | Statistics 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