Pearson’s Linear Correlation | 皮尔逊线性相关

📚 Pearson’s Linear Correlation | 皮尔逊线性相关

In biology, we frequently collect paired data that may show a relationship—for example, the effect of temperature on enzyme activity or the link between leaf surface area and transpiration rate. Pearson’s linear correlation coefficient, denoted by r, is a powerful tool used to quantify the strength and direction of a linear association between two continuous variables. Mastering this concept is essential for A-Level biologists who must analyse experimental results and draw valid conclusions from scatter plots.

在生物学中，我们经常收集可能显示关系的成对数据——例如，温度对酶活性的影响或叶片表面积与蒸腾速率之间的联系。皮尔逊线性相关系数（用 r 表示）是一个强大的工具，用于量化两个连续变量之间线性关联的强度和方向。掌握这一概念对于需要分析实验结果并从散点图得出有效结论的 A-Level 生物学生至关重要。

1. Introduction to Correlation in Biology | 生物学中的相关性介绍

In many biological investigations, two variables appear to change together in a predictable manner. For instance, as the concentration of a substrate increases, the rate of an enzyme-catalysed reaction may rise until the active sites become saturated. Correlation analysis allows us to move beyond saying “this pattern looks strong” and instead assign a numerical value to that strength. Pearson’s r specifically captures the degree of linear relationship, giving a unit‑free measure between −1 and +1. Negative values indicate an inverse relationship, positive values a direct relationship, and zero suggests no linear pattern.

在许多生物学研究中，两个变量似乎以可预测的方式一起变化。例如，随着底物浓度的增加，酶催化反应的速率可能会上升，直到活性位点饱和。相关性分析使我们不再只是说“这种模式看起来很强”，而是可以为这种强度赋予一个数值。皮尔逊 r 专门捕捉线性关系的程度，给出一个介于 −1 和 +1 之间的无量纲量度。负值表示反向关系，正值表示正向关系，零则表示没有线性模式。

A common pitfall in biology is assuming that a high correlation proves causation. In reality, the link could be caused by a confounding variable—for example, a positive correlation between ice‑cream sales and shark attacks is driven by the warm weather, not by ice‑cream causing sharks to bite. Always combine statistical analysis with biological reasoning.

生物学中一个常见的陷阱是认为高相关性证明了因果关系。实际上，这种联系可能是由混杂变量引起的——例如，冰淇淋销量与鲨鱼袭击之间的正相关是由温暖天气驱动的，而不是冰淇淋导致鲨鱼咬人。务必把统计分析与生物学推理结合起来。

2. What is Pearson’s Linear Correlation Coefficient? | 什么是皮尔逊线性相关系数？

Pearson’s product‑moment correlation coefficient, often simply called Pearson’s r, was developed by Karl Pearson at the turn of the 20th century. It is a parametric statistic, meaning it operates under specific assumptions about the distribution of the data. The coefficient measures the covariance of the two variables divided by the product of their standard deviations, thereby standardising the result. In A‑Level Biology, we always work with the sample correlation coefficient, r, which estimates the population correlation ρ (rho).

皮尔逊积矩相关系数，通常简称为皮尔逊 r，由卡尔·皮尔逊在 20 世纪初提出。它是一种参数统计量，意味着它依赖于关于数据分布的特定假设。该系数测量了两个变量的协方差除以它们标准差的乘积，从而使结果标准化。在 A-Level 生物中，我们始终使用样本相关系数 r，它是对总体相关系数 ρ (rho) 的估计。

Because r is standardised, it is unaffected by the units of measurement. Whether you measure leaf length in millimetres or metres, the r value will be identical as long as the relationship remains linear. This property makes Pearson’s r especially useful when comparing relationships across different studies or variables.

由于 r 是标准化的，它不受测量单位的影响。无论你用毫米还是米测量叶长，只要关系保持线性，r 值都相同。这一特性使得皮尔逊 r 在比较不同研究或变量之间的关系时特别有用。

3. The Mathematical Formula for r | r 的数学公式

The formula for Pearson’s r uses the means of the two variables, x̄ and ȳ. It is constructed from the sum of the products of deviations divided by the square root of the product of the sums of squares:

皮尔逊 r 的公式使用了两个变量的平均值，x̄ 和 ȳ。它由偏差乘积之和除以平方和乘积的平方根构成：

r = Σ((x − x̄)(y − ȳ)) / √( Σ(x − x̄)² × Σ(y − ȳ)² )

In this equation, the numerator Σ((x − x̄)(y − ȳ)) is the covariance of x and y. The denominator √(Σ(x − x̄)² × Σ(y − ȳ)²) is the product of the standard deviations of x and y multiplied by (n − 1), which cancels out with the same factor in the numerator when using sample statistics. The result always lies between −1 and +1 inclusive.

在这个等式中，分子 Σ((x − x̄)(y − ȳ)) 是 x 和 y 的协方差。分母 √(Σ(x − x̄)² × Σ(y − ȳ)²) 是 x 和 y 的标准差的乘积乘以 (n − 1)，当使用样本统计量时，这与分子中的相同因子抵消。结果始终在 −1 到 +1 之间（含）。

4. Assumptions Underlying Pearson’s Correlation | 皮尔逊相关的基本假设

To apply Pearson’s r and make valid inferences, several conditions should be met: (1) Both variables must be measured on a continuous scale. (2) The data pairs must be independent of one another. (3) The relationship between the two variables should be linear—a scatter plot should not show a strong curve. (4) The variables should be approximately bivariate normally distributed, especially when performing hypothesis tests. (5) There should be no extreme outliers, as a single unusual point can greatly distort r.

要应用皮尔逊 r 并作出有效推断，应满足几个条件：(1) 两个变量都必须用连续尺度测量。(2) 数据对必须相互独立。(3) 两个变量之间的关系应为线性——散点图不应显示出明显的曲线。(4) 变量应近似服从二元正态分布，特别是在进行假设检验时。(5) 应该没有极端异常值，因为单个异常点可能极大地扭曲 r。

If a dataset has a curved, U‑shaped, or exponential trend, Pearson’s r may be close to zero even when a strong deterministic relationship exists. In such cases, a visual inspection of the scatter plot is crucial, and a non‑parametric alternative such as Spearman’s rank correlation may be more suitable.

如果数据集有曲线、U 形或指数趋势，即使存在很强的确定性关系，皮尔逊 r 也可能接近零。在这种情况下，目视检查散点图至关重要，斯皮尔曼秩相关等非参数替代方法可能更合适。

5. Step‑by‑Step Calculation of r | r 的逐步计算

Although A‑Level exam questions often provide a pre‑calculated r value, knowing the steps deepens your understanding. The calculation proceeds as follows: (1) Calculate the mean of all x values, x̄, and the mean of all y values, ȳ. (2) For each data pair, subtract the mean from each value to obtain (x − x̄) and (y − ȳ). (3) Multiply these differences for each pair and sum them to get Σ(x − x̄)(y − ȳ). (4) Square the differences, then sum to obtain Σ(x − x̄)² and Σ(y − ȳ)². (5) Substitute into the formula. The sign of the sum in step 3 determines the sign of r.

尽管 A-Level 考试题常常提供预先算好的 r 值，了解计算步骤可以加深理解。计算过程如下：(1) 计算所有 x 值的平均值 x̄，以及所有 y 值的平均值 ȳ。(2) 对每个数据对，从每个值中减去均值，得到 (x − x̄) 和 (y − ȳ)。(3) 将每对差异相乘并求和，得到 Σ(x − x̄)(y − ȳ)。(4) 将差异平方，然后求和，得到 Σ(x − x̄)² 和 Σ(y − ȳ)²。(5) 代入公式。第 3 步中求和值的符号决定了 r 的符号。

In practice, biology students might use a calculator or spreadsheet, but manual calculation with a small dataset reinforces the link between the components of the formula and the spread of points on a scatter graph.

在实践中，生物

Published by TutorHao | A-Level Biology Revision Series | aleveler.com

更多咨询请联系16621398022（同微信）