LOGNORMDIST Function (Gnumeric)

• Introduced: First release not established from the evidence cited here.
• Supported in: Gnumeric 1.12.62, confirmed by its function registration. No retirement is established.
• Scope: Desktop Gnumeric with the Statistics Functions plugin. Tables use English comma-separated formulas.
• Checked: October 14, 2026. Tables were recalculated in 1.12.57 and finite reference values independently checked. Version 1.12.62 was source-checked, not executed.

LOGNORMDIST returns a left-tail cumulative probability for a lognormal variable: Φ((LN(x)−μ)/σ). It has no density selector. The mean and standard deviation refer to LN(X), not X. For example, μ=0 and σ=1 give median 1 and CDF 0.5 at x=1. The function’s implementation has a stricter domain than the general mathematical model: it requires μ≥0. Official function reference.

=LOGNORMDIST(x,mean,stddev)

All arguments shown are required. The version-pinned help and evaluator establish the Gnumeric contract.

The table records the tested release’s outputs, with finite mathematical references rounded to twelve decimal places. Keep full precision when using a result in a later calculation.

Suppose log-duration has mean 1 and SD 0.5. Put a duration threshold of 5 in A2, log-mean 1 in B2 and log-SD 0.5 in C2. =LOGNORMDIST(A2,B2,C2) gives approximately 0.888554336707, the modeled probability of a duration no greater than 5. Keep the threshold and the parameter-estimation units consistent. A probability near 0.89 does not establish that the assumed distribution fits the observations.

With μ=0 and σ=1, the probability between 0.5 and 2 is =LOGNORMDIST(2,0,1)-LOGNORMDIST(0.5,0,1), approximately 0.511782808429. Subtract CDFs at ordered measurement-scale bounds, not at their logarithms. The function itself takes LN(x).

The mean/SD conversion formulas are σ=SQRT(LN(1+(s/m)^2)) and μ=LN(m)−σ²/2 for positive arithmetic mean m and SD s. Check the resulting μ before calling this function: a mathematically valid lognormal model can have negative μ, which Gnumeric rejects here. Rescaling a measurement also changes its log-mean, so do not silently change units just to hide an error.

Gnumeric-specific restriction: x must be positive, mean must be nonnegative and stddev must be positive. Thus LOGNORMDIST(1,-1,1) returns #NUM! even though the mathematical CDF exists. LOGINV does accept negative means, so the pair’s domains are not identical. All three arguments are required; the one-argument form was rejected. At x=0 the mathematical limiting CDF is zero, but this function returns an error.

These additional outcomes were observed in the same native recalculation. F5 was genuinely empty; it is not an omitted argument. Missing inputs still need deliberate validation, even if they are converted to a numeric zero.

The worked calculations do not certify every locale, imported text value, extreme parameter or later binary version. Shared numerical helpers can change even when a function’s wrapper remains the same.

• Gnumeric function reference
• Gnumeric 1.12.62 evaluator

The reference and boundary tables use recorded 1.12.57 command-line recalculation. Further model examples were independently calculated from their stated inputs; they are not additional native test claims.