LOGNORM.INV in Collabora Office: Convert Lognormal Probabilities Into Quantiles

=LOGNORM.INV(Number; Mean; StDev)

All three arguments are required. Number is the cumulative probability. Mean and StDev are the mean and standard deviation of the normal distribution of LN(X), rather than the arithmetic mean and standard deviation of X itself. Use 0<Number<1 and positive StDev for the finite interior examples here.

The dedicated Collabora documentation says this function is identical to LOGINV and was introduced for interoperability. It does not give a release number for that introduction. Keep the exact LOGNORM.INV name when checking imported formulas; the documented relationship does not establish another application’s full compatibility.

Mathematically, if z is the standard-normal quantile at probability p, the lognormal quantile is EXP(mu+sigma*z). The output is a positive measurement, not another probability and not a natural logarithm.

Put probabilities 0.05, 0.5 and 0.95 in A2:A4. Put =LN(2) in F2 for mu and in F3 for sigma. In B2 enter =LOGNORM.INV(A2;$F$2;$F$3) and fill down.

Independent targets are approximately 0.639557676, 2 and 6.254322561. Label B as a quantity, for example “Modeled duration in hours” if the underlying model is in hours. A probability of 0.95 means 95% of the modeled distribution is at or below its corresponding threshold.

The official example =LOGNORM.INV(0.05;0;1) has independent target approximately 0.193040817. It uses different parameters from the table, so its fifth percentile is not expected to match B2.

In C2 enter =LOGNORM.DIST(B2;$F$2;$F$3;1) and fill down. The independent round-trip targets are 0.05, 0.5 and 0.95, matching A2:A4. Use the stored B values rather than retyping their rounded displays.

In D2 use =C2-A2 and fill down as a residual check. Small floating-point differences may occur; these reference calculations do not certify a native Collabora tolerance. A large discrepancy usually points to differing parameters, a density flag instead of a cumulative flag, or a percentage-entry mistake.

Entering 95 instead of 0.95 is not another way to request the 95th percentile. Use 95% or 0.95 in a numeric probability cell, and inspect its stored value if the result is unexpected.

At p=0.5 the normal quantile is zero, so LOGNORM.INV returns EXP(mu). With mu=LN(2), the median is two regardless of the positive sigma used.

The original-scale mean is EXP(mu+sigma^2/2), approximately 2.543074259 for the chosen sigma. The 50th percentile is therefore not the original arithmetic mean. This matters when a specification asks for a percentile rather than an expected average.

Changing an original quantity from hours to minutes multiplies every quantile by sixty. On the log scale, replace mu by mu+LN(60) and leave sigma unchanged.

For the median, =LOGNORM.INV(0.5;LN(2)+LN(60);LN(2)) has independent target 120 minutes, matching sixty times the two-hour median. This is a unit conversion of the same model, not a new fit to observations.

Require an interior probability and positive log-scale standard deviation for these formulas. Endpoint limits and the application’s actual endpoint/error displays are separate issues; this guide does not certify them. A probability above one or below zero is outside the model.

Do not substitute the raw-data mean for Mean. Check whether input statistics describe natural logs, whether the units match, and whether parameters were rounded. The inverse function calculates the requested model threshold; it does not verify distribution fit or estimate uncertainty in the supplied parameters.

The exact function is documented in Collabora Office 26.04 desktop help. Its source snapshot was retrieved on 2026-10-13 and hash-verified for this guide on October 15, 2026. Desktop documentation is not proof of Online or mobile support.

First introduced release and last functioning version are unknown. The available dedicated source does not establish those releases. No native Collabora or WPS run occurred. Numerical values are independent mathematical expectations, not certification of application-specific errors, numerical tolerances or all edge cases. Formulas use English names and semicolon separators.

The help identifies the namespace COM.MICROSOFT.LOGNORM.INV and says this function is outside the cited OpenFormula 1.3 standard. This format disclosure does not prove identical behavior in another product. Keep exact dotted names when checking imported workbooks.

• Collabora Office 26.04: LOGNORM.INV.
• Editorial testing standards.