FDIST Function (OpenOffice Calc)

• Introduced: First release not established. The OpenOffice.org 3.3 function appendix documents this name; that is presence evidence, not its introduction date.
• Supported in: Apache OpenOffice 4.1.16, with no final supported release established.
• Scope: Desktop Calc; English names and semicolon separators are used below. The numeric contract refers to the cited release.
• Checked: October 14, 2026. Retained official documentation/source and independent mathematics checked; no new Apache OpenOffice Calc execution is claimed.

FDIST evaluates P(F≥x) for an F distribution with two degree-of-freedom parameters. The first belongs to the numerator of the underlying ratio; the second belongs to the denominator. A small value means that a statistic at least as large would be unusual under that specified reference model. It is not the probability that a scientific hypothesis is true. Function reference.

The F distribution arises from a ratio of independent chi-squared quantities divided by their respective degrees of freedom. In a variance comparison, that model requires independent normal samples. The function does not test those assumptions for you.

=FDIST(Number; DegreesFreedom1; DegreesFreedom2)

All three arguments are required. Number must be nonnegative. Both degree counts are floored before the evaluator requires 1≤df<10,000,000,000. The upper limit is excluded, not included. Prefer deliberately chosen integer counts to relying on conversion of fractional values. Pinned release evaluator.

At x=0 the whole distribution lies at or above the threshold, so the result is 1. There is no cumulative-mode switch: this particular function always supplies the right tail. Do not add a fourth cumulative argument copied from a newer function in another spreadsheet.

These are independently calculated reference values, rounded to twelve decimal places. They are not newly captured application outputs.

Suppose two independent normal samples each contain six observations, with sample variances 8 and 4. Define sample 1 as the numerator before inspecting the data. Put 8, 4, 6 and 6 in A2:D2. In E2 enter =A2/B2, and in F2 enter =FDIST(E2;C2-1;D2-1).

The ratio is 2 and both degree counts are 5, giving a one-sided upper-tail value of approximately 0.232511319130. A lower-tail alternative needs a different event. Choosing whichever observed variance is larger as the numerator does not preserve the interpretation of a prechosen one-sided test.

For a positive threshold, the reciprocal of an F variable reverses its two degrees of freedom. Thus =FDIST(2;2;4)+FDIST(0.5;4;2) should be 1. Reversing only the degree counts while keeping the same x is a different calculation.

The probability below x can be written =1-FDIST(x;df1;df2). For a central interval, subtract two lower-tail values or take the difference of the corresponding right tails in reverse order. For example, the probability between 1 and 4 with degrees 2 and 4 is =FDIST(1;2;4)-FDIST(4;2;4), approximately 0.333333333333.

A cutoff for an upper-tail probability is computed by FINV. The full-precision round trip =FDIST(FINV(0.05;5;5);5;5) should recover 0.05. Do not feed a rounded display value back into a sensitive tail calculation.

Negative x or out-of-range floored degree counts follow the invalid-argument branch. In particular, =FDIST(2;0.9;5) and =FDIST(2;10000000000;5) fail those guards. These are source-confirmed conditions, not new native error screenshots.

A degree count usually equals a sample size minus fitted parameters; it is not the number of rows regardless of missing observations. Check that each variance and its sample count describe the same data. Numerical tail accuracy, text coercion and locale-specific input remain separate from the ordinary cases above.

• Function-specific Apache OpenOffice 4.1.16 implementation

The examples were recomputed independently against the retained release contract. Native import, locale and extreme-input behavior is not newly certified.