What is Correlation?

Correlation is a statistic that measures how strongly two variables move in relation to one another — and in which direction. It's one of the most widely used numbers in finance, sitting behind portfolio diversification, risk management and investment analysis. This guide explains what correlation is, the scale it's measured on, how it differs from covariance, the crucial "correlation is not causation" warning, and why it matters. It builds on the related idea of covariance and is a core topic in qualifications like the FRM.

What is correlation?

Correlation measures the strength and direction of the linear relationship between two variables. Its great advantage is that it's standardised: whatever the variables and their units, correlation always falls on a fixed scale from −1 to +1. That makes it possible to compare the relationship between one pair of variables directly against another — something raw covariance can't do. The most common measure is the Pearson correlation coefficient, usually written as r.

Reading the correlation scale

The value of r tells you two things at once — direction (its sign) and strength (how close it is to the extremes):

• +1: perfect positive correlation — the two variables move in lockstep in the same direction.
• Between 0 and +1: positive correlation — they tend to move in the same direction, more strongly the closer to +1.
• 0: no linear correlation — no consistent linear relationship between them.
• Between 0 and −1: negative correlation — they tend to move in opposite directions.
• −1: perfect negative correlation — they move in exactly opposite directions in lockstep.

So a correlation of +0.9 signals a strong same-direction relationship, −0.8 a strong opposite-direction one, and 0.1 almost no linear link at all.

Correlation vs covariance

Correlation and covariance are closely related — both describe how two variables move together — but correlation is the more useful in practice. Covariance tells you the direction of the relationship, but its size depends on the units of the variables, so it can't be compared across different pairs. Correlation is, in effect, covariance standardised — the covariance divided by the product of the two variables' standard deviations — which rescales it to the −1-to-+1 range. That standardisation is what lets you say one relationship is "stronger" than another in a meaningful way.

The crucial warning: correlation is not causation

The single most important caveat in all of statistics: a correlation between two variables does not mean one causes the other. Two variables can be strongly correlated because one drives the other, because both are driven by a third hidden factor, or simply by coincidence (a "spurious" correlation). Ice-cream sales and drowning incidents rise together — not because one causes the other, but because both increase in hot weather. Treating correlation as proof of causation is one of the most common and costly errors in data analysis, and establishing genuine cause needs more than a correlation coefficient.

Why correlation matters in finance

Correlation is fundamental to portfolio management. The benefit of diversification depends entirely on how the assets in a portfolio correlate: combining assets with low or negative correlation reduces overall risk, because when some fall, others tend to hold up or rise. A portfolio of highly correlated assets, by contrast, offers little protection — they all move together. Correlation is also used in hedging, risk modelling and understanding how different markets relate. A well-known danger is that correlations are not fixed: in a crisis, assets that normally move independently can suddenly become highly correlated, undermining diversification just when it's needed most.

Why it matters for finance professionals

Correlation is part of the essential toolkit for anyone in investment or risk. It turns the vague notion that two things "move together" into a precise, comparable number, and it underpins how diversification and portfolio risk are quantified. Understanding both its power and its limits — especially that it never proves causation and can shift in a crisis — is fundamental to sound financial analysis and a regularly examined topic in professional qualifications.

Frequently asked questions

What does correlation measure?

The strength and direction of the linear relationship between two variables, on a standardised scale from −1 (perfect opposite movement) to +1 (perfect same-direction movement), with 0 meaning no linear relationship.

What's the difference between correlation and covariance?

Both describe how variables move together, but covariance's size depends on the variables' units, while correlation standardises it to a −1-to-+1 range — so correlations can be compared across different pairs of variables.

Does correlation imply causation?

No. A correlation can arise from one variable causing another, from a shared hidden cause, or from coincidence. Establishing causation requires more evidence than a correlation coefficient alone.

Why does correlation matter for investing?

It drives diversification. Combining assets with low or negative correlation reduces portfolio risk, while highly correlated assets move together and offer little protection — though correlations can rise sharply in a crisis.

Build your quant skills with Learnsignal

Correlation is the foundation of diversification and portfolio risk. Learnsignal's tutor-led courses, including the FRM, develop the statistical and portfolio understanding that topics like this build on — with clear teaching that makes the maths genuinely click.