Correlation Coefficient Formula in Excel

This guide treats “correlation coefficient formula in excel” the way busy spreadsheet users actually want it: answer first, a live tool to prove it on your own data, then the reasoning. It is written for Excel but calls out every place Google Sheets differs, and the platform toggle at the top switches all shortcuts between Windows and Mac so nothing here assumes the keyboard you are not on.

Exact answer

In Excel: use =CORREL(array1, array2) — it returns a correlation coefficient from -1 to 1, where 0 means no linear relationship.

On this page8

Syntax

=CORREL(array1, array2)

Arguments

Argumentrequired / optionalDescription
array1requiredThe first set of values.
array2requiredThe second set, the same size as array1.

Related functions

SLOPE and INTERCEPTFORECASTVAR
ƒxCorrelation & TrendlineLive

6 pairs

Correlation (r)
0.9981

R² = 0.9962

Slope
1.9857

Intercept = 0.1667

=CORREL(A2:A10,B2:B10) · =SLOPE(B,A) · =RSQ()
Ctrl+CthenCtrl+Shift+V+Cthen+Ctrl+VPaste values · WindowsMac

Need it as an auditable file?

Ships inside the linked template — formula-driven, unlocked, audit-ready.

View template

What this does

CORREL measures how strongly two variables move together, on a scale from -1 (perfectly opposed) through 0 (unrelated) to 1 (perfectly aligned). It detects linear relationships only: a strong curved relationship can return a coefficient near zero, which is why plotting the data alongside the number is not optional. The other standing caveat is that correlation says nothing about cause. Both ranges must be the same size; pairs where either value is missing are dropped. Most people learn this as a sequence of clicks and forget it by next week; learning it as a pattern instead is what lets you apply it to the next, slightly different version of the problem without starting from scratch. That is the difference this page is trying to make. The difference between a quick fix and a sheet you can trust is the extra minute you spend validating “correlation coefficient formula in excel”. Start on a copy or a tiny sample, keep the affected formula visible, and compare the result with the tool above before you touch the real workbook. When a formula is involved, keep the inputs labelled beside it, reference cells instead of typing values, and apply number formatting only after the result checks out. The point is a calculation you can defend to a CFO or an auditor, but the practical win is that someone else can open the file and understand what happened without asking you.

A worked example

Marketing spend in B2:B37 and revenue in C2:C37: =CORREL(B2:B37, C2:C37) returning 0.78 indicates a strong positive linear relationship. Squaring it gives R², the share of variance explained: =CORREL(B2:B37,C2:C37)^2 returns about 0.61, matching the R² a trendline reports. CORREL puts a single defensible number on "do these move together", which is the first question any two-variable analysis has to answer. If there is any chance you will reuse this, drop it into a small template tab right now: a labelled input area on the left and the formula beside it, checked once against the tool above. Next time the same question comes up, the answer is a single paste away instead of a rebuild from memory.

In Google Sheets

Everything above works in Google Sheets too. Excel and Sheets share the formula syntax used here; only the surrounding menus are arranged differently. That portability is deliberate — learn it once and it follows you between the two tools and across Windows and Mac. Keep this page bookmarked for the next time the same question comes up. Better still, rebuild the example once in your own sheet — doing it yourself, with the tool above to check against, is what turns a copied formula into a technique you own. Treat “correlation coefficient formula in excel” as a small building block rather than a chore. Once the inputs sit in their own cells and the formula reads from them, the same setup answers a dozen related questions with a tweak, and Excel keeps every dependent figure current as the data changes. The tool above is there so you can rehearse and verify before committing anything to a real workbook; the steps and worked example are there so the logic sticks. Get it right once and it stops costing you time — it starts saving it, every time the question comes back around.

Common mistakes

  • Reading correlation as causation, which the coefficient cannot support in either direction.
  • Trusting a near-zero result without plotting; CORREL is blind to non-linear relationships.
  • Ranges of different lengths, which returns #N/A.

Frequently asked questions

What counts as a strong correlation?

It depends entirely on the field. Above 0.7 is usually called strong in business data and would be weak in a physical measurement.

How do I get R-squared?

Square the coefficient: =CORREL(x,y)^2, or use =RSQ(y,x) directly. Both match the R² a chart trendline displays.

Does correlation prove causation?

No. It measures co-movement only; a lurking third variable explains a great many strong correlations.