PlanMaker COVARIANCE.P: Population Denominator, Units and Examples

• Introduced: Documented by the PlanMaker 2018 manual; the first introduction release is not established.
• Availability: Documented in PlanMaker 2026; this is not a final working-version endpoint.
• Scope: The reference belongs to the 2026/NX manual family. Individual FreeOffice and mobile-build availability remains unverified.
• Checked: October 14, 2026, against the official function reference. Examples use vendor results and independent calculations; no native PlanMaker test was performed.

=COVARIANCE.P(Range1, Range2)

Both arguments are required cell references. The PlanMaker reference specifies integer contents, ignores empty cells, text and logical values, and documents #N/A when the two sets have different numbers of values.

The 2018 manual did not state the integer restriction. Its omission does not establish fractional-input behavior in the current application. This guide uses complete integer pairs and avoids inferring how differently placed ignored values are aligned.

The P denotes population covariance. The source says it returns the same quantity as COVAR; COVARIANCE.S instead returns sample covariance. English formulas below use comma separators.

Create PopulationPairs with x and y in A1:B1 and these values in A2:B5:

Enter =COVARIANCE.P(A2:A5,B2:B5) in H2; expect 3.5. Put =AVERAGE(A2:A5) in H4 and =AVERAGE(B2:B5) in H5; the means are 5 and 3.

Put dx, dy and Product in C1:E1. Enter =A2-$H$4, =B2-$H$5 and =C2*D2 in C2:E2, then fill down through row 5.

In H7 enter =SUM(E2:E5); expect 14. In H8 enter =H7/4; expect 3.5, reproducing H2. The negative product on row 4 offsets part of the positive co-variation in the other rows.

On PopulationPairs, put these comparisons in H10:H12:

The sample calculation divides the same total 14 by 4−1 = 3. Its larger value does not mean that the underlying observations changed. The distinction concerns which denominator matches the intended population or sample calculation.

A file’s row count alone does not determine whether the observations should be treated as the full population of interest. State that modeling choice when reporting the result.

Enter Squared x deviation in F1, =C2^2 in F2, and fill to F5. The squared deviations are 9,1,1,9.

• J2: =COVARIANCE.P(A2:A5,A2:A5) gives 5.
• J3: =SUM(F2:F5)/4 also gives 5.
• J4: =COVARIANCE.P(B2:B5,A2:A5) gives 3.5, checking symmetry.

Using the same series twice turns each cross-product into a squared deviation. This explains the self-covariance identity without confusing covariance between different variables with a single variable’s variance.

Keep the main table intact. Put y plus ten and x times 100 in L1:M1. Enter =B2+10 in L2 and =A2*100 in M2; fill both to row 5.

Adding a constant leaves deviations from the mean unchanged. Multiplying one series by 100 multiplies covariance by 100 but preserves the unitless correlation. Report covariance in the product of the original measurement units; it is not constrained to −1…1 like a correlation coefficient.

Create VendorPopulation, with 2,5,3 in A1:A3 and 2,7,4 in B1:B3. Enter =COVARIANCE.P(A1:A3,B1:B3) in D1. The exact mathematical result is 23/9, approximately 2.555555556, which rounds to the reference’s 2.55556.

SoftMaker says COVARIANCE.P supplements the older COVAR name and documents Excel support for the dotted function from Excel 2010. That is an Excel compatibility statement, not a PlanMaker introduction date or proof of a workbook round-trip. No retirement of COVAR is stated.

The documented mismatch signal is #N/A; exact empty-only, ignored-entry alignment and fractional-input behavior are not fully established by the short entry. Keep complete paired records, and do not independently sort just one variable.

• COVAR for the older population-covariance name.
• COVARIANCE.S for the sample denominator.
• CORREL for normalized linear association.
• AVERAGE for the two means.