ATLASCorrelation
Investing glossary · Risk and statistics
A number from −1 to +1 that shows how closely two assets move together.
Definition
Correlation measures how closely two series move together. +1 means they move in perfect lockstep, 0 means no linear relationship and −1 means they move in opposite directions. For two stocks, it is usually computed from their returns over a period.
Correlation is what makes diversification work: combining assets that do not move together smooths the portfolio. But correlations are not fixed, and in market crises they tend to rise just when you most want them to be low. It also only captures linear relationships, not every kind of dependence.
Formula
ρ = Cov(A, B) ÷ (σ_A × σ_B)
Cov(A, B) = covariance of the returns of A and B; σ_A and σ_B = their standard deviations.
Worked example
Using 53 weekly returns from the last year, the correlation between Apple and Microsoft is -0.05, while between Apple and Coca-Cola it is -0.07.
The first pair belongs to the same corner of the market and moves together more; the second pair gives more diversification.
How ATLAS uses it
ATLAS uses correlations between positions when it computes the risk of a portfolio and when it suggests diversified portfolios in the Portfolio builder.
Related in ATLAS: Portfolio builder →Browse all ATLAS tools →See it on a real stock
The example above uses these companies. Open their pages for the full numbers:
Frequently asked questions
Does zero correlation mean the stocks are unrelated?
It means no linear relationship in the measured period. They could still be linked in other ways, and correlations change over time.
Why do correlations rise in a crisis?
Because broad selling pushes many assets down together, even those that normally behave differently.
Related terms
Put the idea to work on your own stocks
Open any company in ATLAS to see its fair value, its odds of rising and its risk numbers side by side.
Try ATLAS →Not investment advice. ATLAS estimates are produced by statistical models from public data; they can be wrong and past performance does not predict future results. Consider your own situation before investing. Disclaimer