PEARSON in WPS Spreadsheet: Measure Linear Correlation in Paired Data

=PEARSON(array1,array2)

Both arrays are required; no optional mode or default is documented. Supply corresponding observations in the same order. WPS describes the first as the independent-variable collection and the second as the dependent-variable collection. Mathematically the correlation is symmetric, so swapping the two complete numeric arrays does not change the result. That symmetry does not make an observational study causal.

Pearson r is the sum of centered cross-products divided by the square root of the product of the two centered sums of squares. Its sign indicates direction, and its absolute magnitude measures linear association. It is not a slope, percentage of matching rows or average error.

Enter =PEARSON(A2:A5,B2:B5) in F2. Independent expectation: 6 / √40 = 0.948683298050514.

The means are 2.5 and 4. Centered cross-products sum to 6. The x squared deviations sum to 5 and the y squared deviations sum to 8, so the denominator is √40. This check needs no fitted regression line.

Put C2:C5 = 102, 104, 104, 106 and D2:D5 = −2, −4, −4, −6. Use F3:F5 for outputs:

Adding a constant leaves correlation unchanged; multiplying one series by a negative constant reverses its sign. Positive rescaling also preserves correlation. Compare this with COVAR, whose magnitude depends on scale.

As a nonlinear control, replace A2:A4 with −1, 0, 1 and B2:B4 with 1, 0, 1, then use =PEARSON(A2:A4,B2:B4). The independent result is 0 despite the exact relationship y = x squared. Use a scatter plot and subject-matter reasoning alongside r; a single coefficient can hide curvature, outliers or separate groups.

The WPS source documents #N/A for empty arrays or unequal numbers of data points. It says text, logical values and blanks in array/reference inputs are ignored, while zeros are included. These statements are not a tested guarantee for how differently positioned nonnumeric entries align. Retain complete numeric pairs and verify their row identities.

If either numeric series is constant, the mathematical denominator is zero and correlation is undefined. No exact WPS error token for that case is asserted here because the reviewed lesson does not specify it. Similarly, one observation cannot establish correlation. Check variation and sample size before interpreting the output.

An unexpected sign often traces to reversed coding or mismatched rows. An implausibly perfect result may come from accidentally referencing the same column twice. Preserve the source columns and review both range addresses. CORREL covers a related coefficient; the inspected documentation does not establish universal bit-for-bit identity across WPS builds, so this guide retains PEARSON’s exact name and signature.

The official WPS PEARSON lesson was published 2019-06-10 and labels its applicable edition WPS Office for Windows Personal. The lesson was checked on October 19, 2026. This establishes a documented-by date, not the release in which the function first appeared. No numeric build, last supported version or retirement date is established. Mac, Linux, web, mobile and global-English edition parity are unverified.

Original expected results here are independent calculations or explicitly labelled test expectations, not native WPS execution. No WPS screenshot or installed-build test is claimed. Formula separators and displayed decimal precision can depend on the target setup; verify the exact function name in that installation before distributing a workbook.