📚 Year 8 CAIE Statistics: Core Knowledge Review | Year 8 CAIE 统计：核心知识点梳理
Welcome to your complete revision guide for Year 8 CAIE Statistics. This article pulls together all the essential concepts you need to feel confident with data handling, averages, charts and probability. Each section breaks a topic down into clear explanations, worked examples and common exam tips, so you can revise effectively and spot how ideas connect.
欢迎来到你的 Year 8 CAIE 统计完整复习指南。本文汇集了数据处理、平均数、图表与概率等所有核心概念，帮助你建立信心。每个部分都通过清晰的解释、例题和常见考试技巧将主题拆解，让你高效复习并理解知识点之间的联系。
1. Data Types and Collection | 数据类型与收集
Statistics always begins with data. In Year 8 you need to recognise two main types: qualitative data (words or categories, like eye colour or favourite sport) and quantitative data (numbers that can be measured or counted). Quantitative data can be discrete (only certain values, such as number of siblings) or continuous (any value within a range, such as height).
统计始终从数据开始。在 Year 8 阶段你需要识别两种主要类型：定性数据（文字或类别，如眼睛颜色或最喜欢的运动）和定量数据（可测量或计数的数字）。定量数据可以是离散的（只取某些值，例如兄弟姐妹数量）或连续的（一个范围内的任意值，例如身高）。
When collecting data, we often use surveys, questionnaires or experiments. A good question should be unbiased and easy to understand. For example, 'How many hours do you sleep on a school night?' gives clear quantitative data, while 'Do you agree that sleeping early is good?' might lead to opinion-based answers.
收集数据时，我们通常使用调查、问卷或实验。一个好的问题应无偏见且易于理解。例如，“你在上学日的晚上睡几个小时？”能提供清晰的定量数据，而“你是否同意早睡有好处？”可能会导致基于观点的回答。
We also classify data as primary (collected by yourself for a specific purpose) or secondary (data that already exists, such as from the internet or a book). Knowing this helps you judge how reliable your information is.
我们还将数据分为一手数据（自己为特定目的收集的）和二手数据（已经存在的数据，如来自网络或书籍）。了解这一点有助于你判断信息的可靠程度。
2. Frequency Tables | 频率表
A frequency table organises raw data by showing how often each value or category appears. It usually has three columns: the data value or category, a tally column and the frequency. Tally marks are grouped in fives (four vertical lines with a diagonal strike through them) to make counting quick and accurate.
频率表通过显示每个数值或类别出现的次数来整理原始数据。它通常有三列：数据值或类别、划记列和频率。划记以五个为一组（四条竖线加一条斜线）来快速而准确地计数。
If you have a list of 25 students' favourite fruits, you could draw a frequency table with 'Fruit' and 'Frequency' columns. Always total the frequency column to check against the number of data items. Avoid losing marks by forgetting to write the total at the bottom.
如果你有一份 25 名同学最喜欢水果的名单，你可以绘制一个包含“水果”和“频率”列的频率表。一定要对频率列求和，以核对数据项的数量。别忘了在表格底部写上总数，以免失分。
tervals should be the same width if possible. When using inequality signs, remember that ≤ includes the boundary and < does not.
对于分组连续数据，我们使用组距，例如 0 ≤ h < 10，其中 h 代表身高（厘米）。分组不能重叠，且所有间隔可能时应保持相同宽度。使用不等号时，记住 ≤ 包括边界值，< 不包括。
3. Bar Charts and Dual Bar Charts | 条形图与双向条形图
Bar charts display categorical or discrete data with rectangular bars. The height (or length, for horizontal bars) of each bar represents frequency. Bars must be of equal width and spaced evenly apart; labelling both axes and giving a title are essential for full marks.
条形图用矩形条显示类别或离散数据。每个条形的高度（或水平条形的长度）代表频率。条形必须宽度相等且间距均匀；标注两条坐标轴并给出标题是获得满分的关键。
A dual bar chart lets us compare two related sets of data side by side. For instance, you could show boys' and girls' favourite sports on the same chart. Use a key to distinguish the two bars and keep the colours or shading consistent. Always read the scale carefully when interpreting these charts.
双向条形图可以让我们并排比较两组相关数据。例如，你可以在同一张图中展示男孩和女孩最喜欢的运动。使用图例区分两组条形，并保持颜色或阴影一致。解读图表时务必仔细查看刻度。
When drawing, use a ruler and a sharp pencil. Plot the frequencies accurately on the given grid. In exams you are often given a partly completed chart to finish; check the scale on the frequency axis before drawing any bars.
绘图时使用直尺和削尖的铅笔。在给定的网格上准确标出频率。考试中常会给出部分完成的图表让你补全；在绘制任何条形之前，先检查频率轴上的刻度。
4. Pie Charts | 饼图
Pie charts show proportions of a whole. Each sector’s angle is calculated using the formula:
Sector angle = (category frequency ÷ total frequency) × 360°
饼图展示整体的各个部分。每个扇区的角度使用以下公式计算：
扇区角度 = (类别频率 ÷ 总频率) × 360°
Work out each angle carefully and check that they sum to 360°. Use a protractor to measure and draw the sectors. Label each sector with the category name and its frequency or percentage, or provide a clear key. Never rely on guessing the size of a sector by eye.
仔细计算每个角度，并检查它们的总和是否为 360°。使用量角器测量和绘制扇区。为每个扇区标注类别名称及其频率或百分比，或提供清晰的图例。切勿靠目测估计扇区大小。
ut you need the total frequency to work out actual frequencies. If the chart shows 90° for 'walk to school' and the total is 540 students, then the number walking is (90 ÷ 360) × 540 = 135 students.
解读饼图时，记住较大的扇区意味着较大的比例，但你需要总频率才能计算实际频率。如果图表中“步行上学”的扇区为 90°，总人数为 540，那么步行上学人数为 (90 ÷ 360) × 540 = 135 人。
5. Scatter Graphs and Correlation | 散点图与相关性
A scatter graph (or scatter plot) is used to investigate the relationship between two sets of quantitative data. Each point on the graph represents a pair of values. We plot the independent variable on the horizontal axis and the dependent variable on the vertical axis.
散点图用于探究两组定量数据之间的关系。图上每个点代表一对数值。我们将自变量绘制在横轴上，因变量绘制在纵轴上。
Correlation describes the pattern of points. Positive correlation means as one variable increases, the other tends to increase (points slope upwards). Negative correlation means as one increases, the other tends to decrease (points slope downwards). If there is no clear pattern, we say there is no correlation.
相关性描述点的模式。正相关意味着随着一个变量增加，另一个也倾向于增加（点向上倾斜）。负相关意味着随着一个变量增加，另一个倾向于减少（点向下倾斜）。如果没有明显的模式，我们称之为无相关性。
We can also talk about strong or weak correlation. Strong correlation has points close to a straight line; weak correlation has points widely scattered. You do not need to calculate the correlation coefficient at this stage, but you should be able to draw a line of best fit by eye for strong linear relationships.
我们还可以讨论强相关或弱相关。强相关的点靠近一条直线；弱相关的点则分散较宽。现阶段不需要计算相关系数，但你应该能够为强线性关系目测画出最佳拟合线。
The line of best fit should have roughly equal numbers of points above and below it and follow the general trend. Do not force it through the origin unless the data clearly suggests it. Outliers (points far from the trend) should be identified and mentioned separately.
最佳拟合线在线上方和下方的点数应大致相等，并遵循总趋势。除非数据明确表明需要通过原点，否则不要强制线经过原点。异常值（远离趋势的点）应单独识别和提及。
6. Mean, Median and Mode | 平均数、中位数与众数
These three measures of central tendency help us summarise a data set with a typical value. The mode is the most frequent value. A data set can have one mode, more than one mode or no mode at all. It is the only measure that can be used with non-numerical data.
这三种集中趋势的度量帮助我们用一个典型值来概括数据集。众数是出现最频繁的值。一组数据可能有一个众数、多个众数或没有众数。它是唯一可用于非数值数据的测量。
The median is the middle value when data are ordered from smallest to largest. If there are n values, the median position is (n + 1) ÷ 2. For an odd number of values, the median is the single middle number; for an even number, it is the mean of the two middle numbers.
中位数是将数据按从小到大顺序排列后的中间值。如果有 n 个数值，中位数的位置是 (n + 1) ÷ 2。当数值个数为奇数时，中位数就是中间那个数；为偶数时，则是中间两个数的平均数。
f values ÷ number of values. The mean includes every data point, so it can be affected by very large or very small outliers.
平均数的计算是将所有数值相加，然后除以数值的个数。用符号表示为：平均数 = 数值总和 ÷ 数值个数。平均数包含每一个数据点，因此可能受到极大或极小异常值的影响。
Choosing the best measure depends on the situation. If data are skewed by one extreme salary, the median gives a better sense of 'typical' than the mean. The mode is useful for finding the most popular item.
选择最佳度量取决于具体情况。如果数据被一个极端的薪水值扭曲，中位数比平均数更能反映“典型”情况。众数则有助于找到最受欢迎的项目。
7. Range and Spread | 极差与数据分布
rgest value − smallest value. It tells us how spread out the data are, but it only uses two values and can be badly affected by a single outlier.
极差是最简单的离散程度度量。其计算公式为：极差 = 最大值 − 最小值。它告诉我们数据的分布范围，但只用到两个值，且会严重受到单个异常值的影响。
A small range means the data values are quite close together (more consistent), while a large range suggests they are more spread out (less consistent). Always mention the units when writing your answer.
极差小意味着数据值相当接近（更一致），而极差大则表明数据更为分散（一致性较低）。在写答案时务必提及单位。
When comparing two data sets, calculate the mean (or median) and the range for each. A higher mean with a smaller range suggests that set typically scores higher and is more consistent. Pairing a measure of central tendency with a measure of spread gives a fuller summary than either alone.
比较两组数据时，分别计算每组的平均数（或中位数）和极差。较高平均数搭配较小极差表明该组通常得分更高且更稳定。将集中趋势度量和离散程度度量搭配使用，比单独使用任何一个都能给出更全面的总结。
8. Introduction to Probability | 概率入门
Probability is a measure of how likely an event is to happen. It can be written as a fraction, decimal or percentage, always between 0 (impossible) and 1 (certain). The probability scale helps us visualise this: 0 for impossible, 0.5 for even chance, 1 for certain.
概率是对某个事件发生可能性的度量。它可以写成分数、小数或百分比，总是在 0（不可能）和 1（确定）之间。概率尺度可以帮助我们可视化：0 表示不可能，0.5 表示均等机会，1 表示确定。
If all outcomes are equally likely, the theoretical probability of an event A is:
P(A) = number of favourable outcomes ÷ total number of possible outcomes
如果所有结果可能性相等，事件 A 的理论概率为：
P(A) = 有利结果的数量 ÷ 可能结果的总数
fair six-sided die, the probability of rolling an even number is 3/6 = 1/2. Outcomes like 'rolling a 7' have a probability of 0 because there are no sevens on a standard die.
对于一个均匀的六面骰子，掷出偶数的概率是 3/6 = 1/2。像“掷出 7”这样的结果概率为 0，因为标准骰子上没有 7。
obability of rain tomorrow is 0.3, then the probability it does not rain is 1 − 0.3 = 0.7.
某事件不发生的概率是 1 减去它发生的概率。这称为互补规则。例如，如果明天下雨的概率是 0.3，那么不下雨的概率就是 1 − 0.3 = 0.7。
9. Experimental Probability | 实验概率
Experimental probability (or relative frequency) is based on actually carrying out trials or observing events. It is calculated as:
Experimental probability = number of times event occurs ÷ total number of trials
实验概率（或相对频率）基于实际开展试验或观察事件。其计算方法为：
实验概率 = 事件发生的次数 ÷ 总试验次数
ay differ from the theoretical probability of 0.5, especially with a small number of trials. As the number of trials increases, the experimental probability tends to get closer to the theoretical probability. This is called the law of large numbers.
如果你抛一枚硬币 50 次，得到 28 次正面，那么正面的实验概率为 28/50 = 0.56。这可能与 0.5 的理论概率不同，尤其是在试验次数较少时。随着试验次数的增加，实验概率会趋于接近理论概率。这称为大数定律。
s, the estimated probability of red is 15/60 = 1/4. Use these estimates to make predictions about larger numbers of trials.
当给你一个结果频率表时，你可以从中估计概率。例如，如果一个转盘在 60 次旋转中落在红色区域 15 次，那么红色的估计概率为 15/60 = 1/4。使用这些估计来预测更大数量的试验结果。
10. Interpreting Statistics | 解读统计信息
Being able to read and question statistical claims is a vital skill. When you see a chart or an average reported, ask yourself: Who collected the data? Is the sample size large enough? Might the sample be biased? For example, a survey about favourite social media apps conducted only in one Year 8 class may not represent the whole school.
能够阅读并质疑统计主张是一项重要技能。当你看到图表或报告的平均数时，问自己：数据是谁收集的？样本量够大吗？样本是否存在偏差？例如，只在一个 Year 8 班级中进行的关于最喜欢的社交媒体应用的调查可能无法代表整个学校。
Check that graph axes do not mislead. A bar chart with a vertical axis that does not start at zero can make small differences look huge. Pie charts should be checked against total frequencies; a 'largest' slice might still represent a minority if the chart omits a large 'other' category.
检查图表坐标轴是否存在误导。纵轴不从零开始的条形图可能让小差异看起来很大。饼图应与总频率进行核对；如果图表省略了一个大的“其他”类别，即使“最大”的扇区可能仍只代表少数。
Also be aware of averages hiding variation. Two sets of marks could both have a mean of 60%, but one set has a range of 10% (most marks near 60%) while the other has a range of 80% (marks scattered from 20% to 100%). Always ask for the spread as well as the average.
此外，要注意平均数可能掩盖差异。两组分数可能都有 60% 的平均数，但一组的极差为 10%（大多数分数接近 60%），而另一组的极差为 80%（分数从 20% 分散至 100%）。除了平均数，还要问及离散程度。
Finally, correlation does not imply causation. A strong positive correlation between ice cream sales and sunglasses sold does not mean buying ice cream causes people to buy sunglasses; the hidden factor is warm sunny weather. Always think about lurking variables before drawing conclusions.
最后，相关性并不意味着因果关系。冰激凌销量与太阳镜销量之间很强的正相关并不意味着购买冰激凌会导致人们购买太阳镜；隐藏的因素是温暖晴朗的天气。在得出结论之前，一定要考虑潜在的隐藏变量。
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