Collabora Office CHISQDIST: Legacy chi-square CDF or density
Use the optional cumulative flag in CHISQDIST, distinguish left tails from right tails and document the pinned zero-density boundary convention.
Verification status: See the evidence and test scope described in this guide. How formula examples are checked
Quick answer: =CHISQDIST(4;2) independently gives approximately 0.8646647168, the chi-square left cumulative probability. =CHISQDIST(4;2;FALSE()) gives density approximately 0.0676676416. Omitting the third argument selects the CDF.
Boundary caution: the inspected density helper returns 0 at x = 0, including two degrees of freedom, where the mathematical right-hand density limit is 0.5. Keep that source convention separate from a general mathematical formula for the boundary.
Syntax and defaults
=CHISQDIST(Number; DegreesFreedom [; Cumulative])
Cumulative is TRUE when omitted. FALSE/0 requests density; TRUE/nonzero requests cumulative probability. DegreesFreedom is floored by the evaluator and must then be at least 1. The 26.04 CHISQDIST help documents the optional flag, which distinguishes this contract from dotted CHISQ.DIST’s required third argument.
The CDF is P(X≤x). Density is the height of a continuous distribution curve, not the probability of the exact value x. A probability for an interval is a difference of CDF values. The function does not calculate a chi-square statistic from observed and expected ranges.
Worked example: compare the two modes
Enter B2 = 4 and B3 = 2. In separate cells use =CHISQDIST(B2;B3) and =CHISQDIST(B2;B3;FALSE()).
With two degrees of freedom and x > 0:
- CDF =
1−exp(−x/2). - Density =
exp(−x/2)/2.
At x = 4, the independently calculated CDF is 0.8646647167633873 and density 0.06766764161830635. These are different quantities even though both are dimensionless numbers in the worksheet.
The remaining right-tail probability is approximately 0.1353352832, obtained here by subtracting the CDF from 1 or by the separately documented CHIDIST contract. For very extreme upper tails, directly calculating the survival probability can avoid cancellation from subtracting nearly equal floating-point numbers; the small worked example is not an accuracy guarantee for all tails.
Advanced use: probability within a statistic band
To find model probability between 2 and 6 for two degrees of freedom, enter:
=CHISQDIST(6;2)-CHISQDIST(2;2)
The independent result is 0.3180923728, since the difference simplifies to exp(−1)−exp(−3). The lower CDF is approximately 0.6321205588 and the upper CDF 0.9502129316. Subtracting densities at those endpoints would not calculate the interval probability.
This can help illustrate how a reference distribution allocates mass across ranges. It does not establish that a dataset follows that distribution, estimate degrees of freedom or confirm a statistical hypothesis. If x came from a test, retain the assumptions and degrees-of-freedom calculation belonging to that test.
Zero, negative values and degrees of freedom
The pinned CDF and PDF helpers return 0 for x ≤ 0 in both modes. Accordingly:
| Formula | Source-derived value |
|---|---|
=CHISQDIST(-1;2) |
0 |
=CHISQDIST(0;2;FALSE()) |
0 |
=CHISQDIST(4;2.9) |
Same CDF as degrees of freedom 2 |
The CDF’s zero at or below the support is mathematically natural. The density’s exact-zero assignment is a software boundary convention and is not its right-hand limit for every degree of freedom. At degrees of freedom 1, for example, the mathematical density becomes unbounded as positive x approaches zero, while this helper still returns zero at the exact endpoint.
=CHISQDIST(4;0) follows internal IllegalArgument. A negative x in this legacy function is not itself rejected, but a negative chi-square statistic is usually a warning that the upstream statistic is wrong.
Distinction from dotted CHISQ.DIST
The legacy wrapper accepts two or three arguments. The adjacent dotted wrapper requires three, rejects negative x and applies an additional upper degrees-of-freedom check. Do not treat the names as an unconditional alias pair or mechanically omit a flag after renaming.
The source’s absence of that same upper check in the legacy wrapper is not a promise that arbitrarily large degrees of freedom are safe or precise. Native execution, localized error displays and extreme-parameter numerical behavior were not tested here.
Product scope, compatibility and evidence
This guide covers the new Collabora Office desktop for Linux, using the Flathub source tag coda-26.04.4.3-1 and commit 81339d176148d0d5c81ff05d82540f58f8aaa117. The official desktop release notes and Linux package manifest identify that product/build. The package manifest is a dated observation from October 18, 2026, rather than an installed-binary check.
The 26.04 function help and exact evaluator source were inspected on October 18, 2026. Expected examples were independently calculated; no Collabora application was run. Expected scalar results were derived from the documented contracts, inspected source and independent calculations; native output formatting and error localization have not been tested. Classic, Online/CODE, other operating systems and file-format round trips require their own checks.
These are the documented legacy contracts. A similar dotted name does not establish identical argument order, defaults or boundary behavior. The first Collabora release introducing this function is not established by the reviewed sources. No cited retirement or deprecation notice was found; “legacy” here describes the function contract, not a claim that the function has been removed. File-format round trips require separate verification.
Related functions
- CHIDIST: right-tail probability
- CHISQ.DIST: compare the required flag and stricter domain
- GAMMADIST: related shape/scale distribution with different zero-density rules