If ‘correlation doesn’t imply causation’, how do scientists figure out why things happen?

---

Date: 2024-12-11 01:29

Author: Hassan Vally, Associate Professor, Epidemiology, Deakin University

Original article: https://theconversation.com/if-correlation-doesnt-imply-causation-how-do-scientists-figure-out-why-things-happen-243487

---

Most of us have heard the phrase “correlation does not equal causation”. But understanding how scientists move beyond identifying correlations to establish causation remains a mystery to many.

Finding out what causes a particular outcome is often the primary goal of scientific research, especially in studies relating to our health.

We want to know if a certain factor – say, drinking wine or eating chocolate – will lead to better or worse health outcomes. That way, we can make more informed decisions about our health.

But how do scientists actually get those answers?

Correlation versus causation: the basics

It’s easy to find examples of correlations where two variables are linked, but there’s no causal relationship. For instance, there’s a correlation between chocolate consumption and the number of Nobel Prize winners per capita in a bunch of countries.

Does eating chocolate cause people to win Nobel Prizes? Of course not.

This correlation likely exists because chocolate consumption serves as a proxy for wealth. In turn, wealth relates to educational opportunities and funding for completing high-quality research that might lead to a Nobel Prize.

It’s not enough to just find a link between two things. Scientists need much more evidence before we can start to assume a causal relationship.

Building a case

In chemistry or physics, it’s often possible to conduct experiments under highly controlled conditions to understand how X affects Y. When it comes to human biology, it’s rarely so simple.

In most instances, to establish causality we use indirect evidence (more on that in a moment). It requires an approach called inductive reasoning – a process where scientists make generalisations based on the available evidence.

It’s a bit like how a prosecutor might build a criminal case based on circumstantial evidence. While a single piece of such evidence might not be persuasive on its own, as the pieces add up, they strengthen the case.

There’s one interesting contrast, however. In criminal cases, the stakes are incredibly high, and the threshold for proof is “beyond reasonable doubt”. In science, when we make the case for a causal relationship, it’s usually based “on the balance of probabilities”.

This lower threshold of proof reflects the fact scientists are happy to revise their beliefs if and when better evidence becomes available.

Types of indirect evidence of causation

The type of indirect evidence scientists use to infer causation can take different forms. These include:

1. Temporality

This is the only absolute requirement for a relationship to be causal. That is, an exposure must occur before the outcome for an exposure to cause an outcome.

As obvious as this appears, there can be situations where this isn’t clear cut. For example, there might be a long lag time between the two events. For example, 20–60 years can pass between exposure to asbestos fibres and development of mesothelioma, a type of cancer.

Or it might not be immediately obvious what is the exposure and what is the outcome: do sleep disorders lead to depression, or is disordered sleep a symptom of depression?

2. Strength of association

A strong association between two variables is generally considered suggestive of a causal relationship. That is, if one thing happening means another thing is likely to occur, we generally consider this good evidence for causality.

For example, studies showing that high consumption of alcohol is associated with liver damage demonstrate a strong effect. Therefore, they’re highly supportive of a causal relationship.

3. Consistency across studies

If various studies using different methods all yield the same or similar associations, this also supports the existence of a causal relationship.

We generally have more confidence in scientific findings when they can be replicated using different study approaches.

4. A plausible mechanism exists

Being able to demonstrate a mechanism that could explain the association between an exposure and outcome provides further support for a causal relationship.

For example, if lab or animal studies show how a substance damages cells, this would be supportive of a causal relationship between this substance and disease in people.

5. Dose-response relationship

Observing that higher exposures lead to stronger effects is considered highly supportive evidence for a causal relationship.

However, it’s important to note sometimes there’s a threshold effect when it comes to causation. That is, an exposure doesn’t cause disease until it reaches a particular level. This is generally true for infectious diseases, where a minimum infectious dose is required before a person is likely to get ill.

The power of randomised controlled trials

Indirect evidence usually plays an important role in inferring causality. But there’s one type of study that’s the gold standard for providing direct evidence of a causal relationship. It’s called a randomised controlled trial, or RCT.

In an RCT, participants are randomly assigned to either receive an intervention or to be a “control”. This ensures if you see a difference between the two groups, this can only be due to the effect of the intervention. It effectively proves there’s a causal relationship.

You can think of it as the equivalent of catching a criminal red-handed. Unfortunately, due to ethical and practical considerations, we don’t always have evidence from well-conducted RCTs.

For example, we don’t have RCT evidence that smoking causes lung cancer. The reason is that the strength of the indirect evidence supporting a causal relationship is so compelling, it would be unethical to do these studies.

Causality is complex – so beware of those promoting magic bullets

While it’s easy to assume causality works in a simple way – like flipping a switch to turn on a light – when it comes to our health it’s often complex, and involves multiple factors working together.

For instance, lifestyle, genes and environmental factors often all interact to determine whether a person develops a particular disease.

This complexity is another reason we need to be cautious when people offer a simple solution or magic bullet for improving your health. To achieve optimal health, you’ll need to do a variety of things. No single habit, superfood or supplement is the answer.