SLOPE in Collabora Office: Regression Rate of Change and Argument Direction

• Introduced: original Collabora release and launch date are not established by the reviewed sources.
• Availability: currently documented in Collabora Office 26.04 desktop help.
• Platform scope: online and mobile deployments are not inferred from this desktop-help release.
• Checked: October 14, 2026. Function-specific documentation and independent calculations; no native Collabora execution.

=SLOPE(data_y;data_x)

Both series are required. The source describes a line fitted to the supplied Y and X data, but does not give a full missing-input, type or native error table. All worked rows here contain numeric paired observations.

The independent ordinary least-squares model divides the centered X/Y cross-product total by the centered X square total. It uses every observation, rather than connecting only the first and last points.

Enter X 0,1,2,3 in A2:A5 and Y 1,3,2,6 in B2:B5:

=SLOPE(B2:B5;A2:A5)

Expected result: 1.4. The means are X=1.5 and Y=3. Centered products are 3,0,-0.5,4.5, totaling 7. Squared X deviations total 5, giving slope 7/5.

The endpoint slope is instead (6-1)/(3-0)=5/3, approximately 1.666667. A regression uses all four records, so the two answers describe different calculations.

The intercept is 0.9, from 3-1.4×1.5. The line is therefore Y=0.9+1.4×X.

Enter this in C2 and fill through C5:

=INTERCEPT($B$2:$B$5;$A$2:$A$5)+SLOPE($B$2:$B$5;$A$2:$A$5)*A2

Expected fitted values are 0.9,2.3,3.7,5.1. Observed-minus-fitted residuals are 0.1,0.7,-1.7,0.9.

The slope summarizes a fitted trend, not an assertion that every observed pair lies on the line. INTERCEPT explains the separate fitted value at X=0.

=SLOPE(A2:A5;B2:B5)

Expected result: 0.5. The centered cross-product total remains 7, but the denominator is now the centered Y square total, 14.

The reciprocal of the original slope is 5/7, approximately 0.714286, not 0.5. Predicting X from Y and predicting Y from X minimize different residual directions. Swapping two arguments does not generally invert the original fitted line.

Multiply every Y by ten. The expected slope becomes 14. Multiply every X by ten instead, and the expected slope becomes 0.14.

Adding 20 to all original Y values leaves the slope at 1.4, because subtracting the new mean removes the common offset. Negating Y produces -1.4.

A unit conversion can change the numerical slope even when the dimensionless correlation magnitude is unchanged. Keep both variable units in a report containing fitted coefficients.

Reverse both original columns together. The same four pairs produce slope 1.4. Sorting one column independently changes record pairing and can produce a different model.

For a separate exact line with X 0,1,2,3 and Y 5,7,9,11, the slope is 2 and intercept is 5. This simple fixture can help verify argument order before a more complicated workbook is examined.

Repeating every original pair also preserves slope 1.4 in the independent model: both its numerator and denominator double. That does not create new independent information or validate duplicate rows.

If X is constant, the mathematical centered-X denominator is zero and a unique ordinary slope cannot be obtained from these observations. The compact Collabora source does not specify its exact native error code, so none is asserted here.

Empty datasets, unequal lengths, text/Boolean conversion, formula-empty values, source errors and extreme floating-point inputs remain unverified. RSQ and STEYX describe different fit properties; a slope alone proves neither causation nor future predictive accuracy.

• Collabora Office 26.04: SLOPE.
• Editorial testing standards.

Complete function-specific documentation reviewed. Worked outputs are independent statistical models or explicitly documented rules, not application screenshots or native test results. Unverified type, error and numerical boundaries retain their stated scope.