📚 Scatter Graphs and Correlation | 散点图与相关性
Scatter graphs are one of the most useful tools in data handling. They allow you to see at a glance whether two sets of data are connected. In this tutorial, we will explore how to draw a scatter graph, interpret the pattern of points and use a line of best fit to make predictions. The ideas you learn here appear frequently in KS3 and Cambridge Checkpoint assessments, so it is worth spending time to understand them deeply.
散点图是数据处理中最有用的工具之一。它让你能一眼看出两组数据之间是否有关联。在本教程中，我们将学习如何绘制散点图，解释点的分布模式，并利用最佳拟合线进行预测。这些概念经常出现在 KS3 和剑桥 Checkpoint 考试中，因此值得花时间深入理解。
1. What is a Scatter Graph? | 什么是散点图？
A scatter graph (also called a scatter plot) is a diagram that shows the relationship between two variables. Each point on the graph represents a pair of values – one taken from the horizontal axis (x-axis) and one from the vertical axis (y-axis). Unlike line graphs, the points on a scatter graph are not joined up. Instead, we look at how closely the points follow a general trend, which tells us about the correlation between the two variables.
散点图（又称散点图）是一种展示两个变量之间关系的图形。图上的每个点都代表一对数值——一个取自横轴（x轴），另一个取自纵轴（y轴）。与折线图不同，散点图上的点不会连成线。相反，我们观察这些点是否紧密地遵循某种总体趋势，从而判断两个变量之间的相关性。
2. Plotting Points Accurately | 准确描点
To create a scatter graph, start by labelling your axes clearly. The variable you can control or choose is usually placed along the x-axis (the independent variable), while the variable you measure is placed on the y-axis (the dependent variable). For each pair of data, find the x-value on the horizontal scale and the y-value on the vertical scale, then mark a small cross or dot exactly where they meet. It is very easy to misread the scale, so always check the intervals – especially when one square stands for 2, 5 or 10 units.
绘制散点图时，首先要清楚地标注坐标轴。通常将可以控制或选择的变量放在 x 轴（自变量），而将测量的变量放在 y 轴（因变量）。对于每一对数据，在横轴上找到 x 值，在纵轴上找到 y 值，然后在它们交汇的地方画一个小叉号或圆点。刻度很容易看错，因此一定要检查间隔——尤其当一格代表 2、5 或 10 个单位时更要小心。
3. Types of Correlation | 相关性的类型
Correlation describes the direction and strength of the relationship between two variables. We identify three main types: positive correlation, negative correlation and no correlation. The strength of correlation also matters – strong correlation means the points lie very close to a straight line, while weak correlation means the points are loosely scattered but still show a slight direction.
相关性描述两个变量之间关系的方向和强度。我们主要识别三种类型：正相关、负相关和无相关。相关的强度也很重要——强相关意味着点非常靠近一条直线，而弱相关则意味着点虽然分散，但仍呈现出一定的走向。
| Type of Correlation | Pattern of Points | Example |
|---|---|---|
| Positive correlation | As x increases, y increases | Hours of study and test scores |
| Negative correlation | As x increases, y decreases | Speed of a car and time taken to stop |
| No correlation | No clear pattern | Shoe size and favourite subject |
4. Positive Correlation in Detail | 正相关详解
Positive correlation occurs when both sets of data move in the same direction. In other words, high values of one variable are associated with high values of the other, and low values go with low values. On a scatter graph, this looks like a swarm of points that slopes upwards from left to right. The closer the points are to a rising straight line, the stronger the positive correlation. A classic example is the relationship between temperature and ice cream sales: warmer weather usually leads to more ice creams being sold.
当两组数据朝着相同方向变化时，就出现了正相关。也就是说，一个变量的高值对应另一个变量的高值，低值对应低值。在散点图上，这表现为从左向右上升的一片点。点越靠近一条上升的直线，正相关就越强。一个经典的例子是温度与冰淇淋销量之间的关系：天气越暖和，通常冰淇淋卖得越多。
5. Negative Correlation in Detail | 负相关详解
Negative correlation describes a situation where one variable increases while the other decreases. The points on a scatter graph will slope downwards from left to right. For instance, when a car travels at a higher speed, the time it needs to stop generally decreases – not because stopping becomes quicker, but because the thinking distance and braking distance interact. Strong negative correlation means the points hug a downward straight line very closely, while weak negative correlation shows a more scattered downward drift.
负相关描述的是一个变量增加而另一个变量减少的情况。散点图上的点从左向右呈下降趋势。例如，当汽车以更高的速度行驶时，它停下所需的时间通常会更长？实际上，停止时间增加，但如果你观察的是速度与“到达目的地的时间”之类的，可能会减少。更精确的例子：海拔越高，气温越低 – as altitude increases, temperature decreases. 点越贴近一条下降的直线，负相关就越强；弱负相关则表现为更加散乱的下降趋势。
6. No Correlation: When Variables Act Independently | 无相关：当变量各自独立时
Sometimes there is no relationship at all between two variables. The points on the scatter graph appear randomly spread out, with no obvious upward or downward pattern. This is called no correlation, or zero correlation. For example, a student's height and their score on a spelling test are unlikely to show any connection. Recognising no correlation is just as important as spotting positive or negative correlation because it prevents us from making false assumptions about data.
有时两个变量之间完全没有任何关系。散点图上的点显得随机散布，没有明显的上升或下降模式。这被称为无相关或零相关。例如，一个学生的身高和拼写测试成绩不太可能展现任何关联。识别出无相关和识别正、负相关同样重要，因为它能防止我们对数据做出错误假设。
7. Introducing the Line of Best Fit | 引入最佳拟合线
When the points on a scatter graph follow a fairly clear trend, we can draw a line of best fit. This is a single straight line that goes through the middle of the points, balancing the number of points above and below it. The line does not need to pass through the origin, and it does not have to touch every point – in fact it rarely does. Use a transparent ruler to position the line so that it has roughly equal numbers of points on each side and follows the general slope of the data.
当散点图上的点呈现较清晰的趋势时，我们可以画一条最佳拟合线。这是一条穿过点群中央的直线，能平衡线上方和线下方的点数。这条线不必经过原点，也不必经过每一个点——事实上很少如此。使用一把透明直尺来放置这条线，使其两侧的点数大致相等，并跟随数据的总坡向。
8. How to Draw the Line Accurately | 如何准确画出拟合线
First, look at the overall shape of the points. Ignore any outliers – these are points that sit far away from the rest and can pull the line in the wrong direction. Decide whether the trend is linear (straight) or curved. At KS3 we only use straight lines of best fit. Place your ruler so that it follows the general direction. It can help to find the mean of the x-values and the mean of the y-values; the line of best fit should pass through the point (mean x, mean y). Finally, draw the line long enough to extend a little beyond the data points so you can use it for predictions.
首先，观察点的总体形状。忽略任何异常点——这些是远离其他点的点，会把拟合线拉向错误的方向。判断趋势是线性的（直线的）还是曲线的。在 KS3 阶段我们只使用直线型最佳拟合线。将尺子放在符合总体方向的位置。求出 x 值的平均数和 y 值的平均数会很有帮助；最佳拟合线应经过点（x 均值，y 均值）。最后，把线画得足够长，稍微超出数据点范围，以便用其进行预测。
9. Making Predictions: Interpolation and Extrapolation | 进行预测：内插和外推
Once the line of best fit is drawn, you can use it to estimate unknown values. Interpolation means predicting a value inside the range of the given data. For example, if you have data for 10, 20, 30 and 40 hours of study, predicting the score for 25 hours is interpolation – it is likely to be reliable if the correlation is strong. Extrapolation means predicting a value outside the given range, such as using the line to guess the score for 60 hours of study. Extrapolation is much less reliable because you are extending beyond the known pattern, and other factors might affect the result.
画出最佳拟合线后，你就可以用它来估计未知数值。内插指的是在给定数据范围内的预测。例如，如果你有关于 10、20、30 和 40 个小时学习时间的数据，预测 25 个小时的成绩就属于内插——如果相关性很强，这种预测通常比较可靠。外推则是超出给定范围进行预测，比如用该线去猜测 60 个小时学习时间的成绩。外推的可靠性要低得多，因为你把规律延伸到了已知模式之外，其他因素可能会影响结果。
10. Scatter Graphs in Real-world Contexts | 现实情境中的散点图
Scatter graphs are everywhere in daily life and science. Farmers might plot rainfall against crop yield to see if dry weather reduces harvests. Sports coaches analyse scatter graphs of training hours and sprint times to check if extra practice improves performance. Even mobile phone battery life can be plotted against screen brightness to find the best balance. Learning to read scatter graphs gives you a powerful skill for evaluating claims in the news and in advertisements – for instance, when someone says 'studying longer always improves grades', you can ask: 'is there a scatter graph with a line of best fit to support that?'
散点图在日常生活和科学中无处不在。农民可能会把降雨量与作物产量放在散点图上，观察干旱天气是否减少收成。体育教练会分析训练时长与短跑用时之间的散点图，以检查额外训练是否提升表现。甚至手机电池续航时间也可以与屏幕亮度绘制成散点图，以寻找最佳平衡。学会阅读散点图能让你掌握一项强大技能，用来评价新闻和广告中的论断——例如，当有人说“学习时间越长成绩越好”时，你可以问：“有散点图和最佳拟合线支持这种说法吗？”
11. Common Mistakes and How to Avoid Them | 常见错误及如何避免
Many students join the dots on a scatter graph as if it were a line graph – this is wrong. The points should stand alone so you can judge the correlation. Another mistake is forcing the line of best fit to go through the origin when the data does not suggest that. Remember, the line should simply split the points evenly. Also, not extending the line can mean you cannot use it for estimation, so always draw it slightly beyond the data range. Finally, mislabelling axes or forgetting to include units leads to loss of marks in tests; label every axis with the variable name and its unit in brackets.
许多学生会像画折线图那样把散点图的点连起来——这是错误的。点应保持独立，以便判断相关性。另一个错误是当数据并未暗示图形经过原点时，强行让最佳拟合线经过原点。记住，线应该只是均匀分割点群。此外，如果没有延长拟合线，就无法用它进行估计，所以一定要把线画得稍微超出数据范围。最后，坐标轴标注错误或遗漏单位会导致考试失分；每个轴都要标注变量名并用括号写明单位。
12. Summary and Key Takeaways | 总结与关键要点
A scatter graph shows the relationship between two variables. Correlation can be positive, negative or absent, and its strength tells us how closely the points fit a straight line. The line of best fit is a powerful tool for making predictions, as long as we understand the risks of extrapolation. Always plot points carefully, draw the line by balancing the points on each side, and label everything clearly. Practice these skills with real data sets, and you will soon find scatter graphs one of the most straightforward topics in mathematics.
散点图展示两个变量之间的关系。相关性可以是正相关、负相关或无相关，其强度告诉我们点与直线的贴合程度。最佳拟合线是进行预测的有力工具，但前提是我们要理解外推的风险。一定要仔细描点，通过平衡两侧的点来画出拟合线，并清晰标注所有内容。使用真实数据集多加练习，你很快就会发现散点图是数学中最直接了当的主题之一。
Published by TutorHao | Mathematics 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