统计相关系数r与r2的区别

Correlations are a great tool for learning about how one thing changes with another. After reading this, you should understand what correlation is, how to think about correlations in your own work, and code up a minimal implementation to calculate correlations.

关联是学习一件事如何变化的好工具。 阅读此内容后，您应该了解什么是相关性，如何在自己的工作中考虑相关性，并编写一个最小的实现来计算相关性。

Correlation is an abstract math concept, but you probably already have an idea about what it means. Here are some examples of the three general categories of correlation.

关联是一个抽象的数学概念，但是您可能已经对它的含义有所了解。 以下是相关的三个常规类别的一些示例。

As you eat more food, you will probably end up feeling more full. This is a case of when two things are changing together in the same way. One goes up (eating more food), then the other also goes up (feeling full). This is a positive correlation.

当您吃更多的食物时，您可能最终会感到更饱。 这是两种情况以相同的方式一起改变的情况。 一个上升(吃更多的食物)，然后另一个上升(吃饱)。 这是正相关 。

When you're in a car and it goes faster, you will probably get to your destination faster and your total travel time will be less. This is a case of two things changing in the opposite direction (more speed, but less time). This is a negative correlation.

当您开车时，它行驶得更快，您可能会更快到达目的地，而总的旅行时间会更少。 这是两种情况朝相反方向变化的情况(速度更快，时间却更少)。 这是负相关 。

There is also a third possible way two things can "change". Or rather, not change. For example, if you were to gain weight and looked at how your test scores changed, there probably won't be any general pattern of change in your test scores. This means there's no correlation.

还有第三种可能的方法，即两件事可以“改变”。 或者说，不变。 例如，如果您要增加体重并查看您的考试成绩如何变化，则考试成绩可能不会有任何一般的变化模式。 这意味着没有关联。

Being able to describe what is going on in our previous examples is great and all. But what's the point? The reason is to apply this knowledge in a meaningful way to help predict what will happen next.

能够描述我们前面的示例中发生的事情是非常重要的。 但是有什么意义呢？ 原因是要以有意义的方式应用这些知识，以帮助预测接下来会发生什么。

In our eating example, we may record how much we eat for a whole week and then make a note of how full we feel afterwards. As we found before, the more we eat, the more full we feel.

在我们的饮食示例中，我们可以记录一整周的饮食量，然后记下之后的饱腹感。 正如我们之前所发现的，我们吃的越多，我们的饱腹感就越大。

After collecting all of this information, we can ask more questions about why this happens to better understand this relationship. Here, we may start to ask what kind of foods make us more full, or whether the time of day affects how full we feel as well.

收集了所有这些信息之后，我们可以提出更多有关为什么会发生这种情况的更多问题，以更好地理解这种关系。 在这里，我们可能会开始问哪种食物会让我们更饱，或者一天中的时间是否也会影响我们的饱感。

Similar thinking can be applied to your job or business as well. If you notice sales or other important metrics are going up or down with other measure of your business (in other words, things are positively correlated or negatively correlated), it may be worth exploring and learning more about that relationship to improve your business.

类似的想法也可以应用于您的工作或业务。 如果您发现销售额或其他重要指标随您的业务其他指标而上升或下降(换句话说，事情是正相关或负相关的)，那么可能值得探索和了解更多有关这种关系的知识以改善您的业务。

We've covered some general correlations as either

我们已经涵盖了一些一般的相关性，因为

Although those descriptions are okay, all positive and negative correlations are not all the same.

尽管这些描述还可以，但是所有正相关和负相关都不尽相同。

These descriptions can also be translated to numbers. A correlation value can take on any decimal value between negative one, \(-1\), and positive one, \(+1\).

这些描述也可以翻译成数字。 相关值可以采用负数\(-1 \)和正数\(+ 1 \)之间的任何十进制值。

Decimal values between \(-1\) and \(0\) are negative correlations, like \(-0.32\).

\(-1 \)和\(0 \)之间的小数值为负相关，例如\(-0.32 \)。

Decimal values between \(0\) and \(+1\) are positive correlations, like \(+0.63\).

\(0 \)和\(