Correlation is a statistical measure that describes the extent to which two variables fluctuate together. As an example, imagine you measure the mass of a mammal’s heart and plot it on a y-axis and plot its total body mass on the x-axis. You should generate a graph that looks something like Figure 1, where each spot represents a different species. Overall, heavy mammal species have heavy hearts. The heart mass and body mass of a mammal are correlated.
If two variables are correlated, does this mean that a change in one variable causes a change in the other? For total body masses and heart masses, there is probably a causal relationship. After all, bigger bodies have bigger hearts to pump the blood around. But look at Figure 2, which shows a correlation between the number of people in the USA with a diagnosis of chlamydia and US spending on science and technology. Each dot represents a different year. Can you imagine any mechanism where spending more money on science and technology makes more people catch chlamydia? Or did every diagnosis of chlamydia force the US government to spend more money on science? Or was there a confounding variable?
Your organisation does not have access to this article.
Sign up today to give your students the edge they need to achieve their best grades with subject expertise
Subscribe
