LOGINV in ONLYOFFICE: Legacy Lognormal Inverse and Migration Limits

Create DurationModel. Put Parameter in A1 and Value in B1, then enter these values and one formula:

This is an assumed lognormal model for a fictional task duration, not observed data. If X is the duration measured numerically in minutes, ln(X) is modeled as normal with mean μ and standard deviation σ. Use natural logarithms, not base-10 logarithms. The numerical unit must stay consistent when transforming data.

Here exp(μ)=10 is the median, not the arithmetic mean duration. The arithmetic mean is exp(μ+σ²/2), approximately 11.3314845306683 minutes; the mode is exp(μ−σ²), approximately 7.78800783071405. Entering 10 as the mean argument instead of LN(10) specifies a radically different model. A positive skew does not by itself prove real data follow a lognormal distribution.

The official reference requires a probability strictly between 0 and 1 and a positive standard deviation of ln(X). Its mean argument is also on the natural-log scale. The inverse is exp(μ+σΦ⁻¹(p)).

The mean parameter LN(10) makes the median 10 minutes. It does not make the arithmetic mean 10 minutes; the latter is approximately 11.3314845306683 for σ=0.5. This distinction is especially important when moving a positive-skewed duration model from a normal to a lognormal formula.

A central 95% interval uses D5 and D6 because 2.5% is left in each tail. D4 and D2 instead enclose 90%. A 95th percentile is a one-sided threshold, not a central interval by itself.

Place =NORM.S.INV(B7) in F2 and =EXP(B2+B3*F2) in F3. Their independent targets are approximately 1.64485362695147 and 22.7601660851432. This decomposes the calculation into a standard-normal quantile, a log-scale shift and scaling, then exponentiation.

For a positive threshold, =LOGNORMDIST(D2,B2,B3) has mathematical target approximately 0.95. Retain full precision in D2; retyping its rounded display can change the reverse calculation. A round trip is a useful numeric control, but is not evidence that a model fits actual durations.

The 5th and 95th percentile product is 100 in this example. This reflects symmetry around μ after taking logs. Adding their original-unit distances from 10 is not the corresponding symmetry rule. Likewise, changing minutes to seconds multiplies every percentile by 60 while adding LN(60), rather than multiplying by 60, to the log-scale mean.

Modern LOGNORM.INV computes the same scalar expression for ordinary valid inputs, but it is a separate source implementation. LOGINV explicitly takes the first element of explicit array arguments and crosses ranges through its scalar path. LOGNORM.INV uses array-oriented argument preparation and evaluation helpers. Do not replace one name with the other and claim universal array parity merely because a scalar example matches.

No native spill, array-entry or import behavior was tested for either name. Use explicit scalar arguments for the exercises here and keep a migration comparison scoped to the exact workbook and release. The source evidence does not establish when the function was introduced or whether every older editor accepts the modern spelling.

The inspected path rejects p≤0, p≥1 or σ≤0 with #NUM!. Therefore =LOGINV(0,LN(10),0.5), =LOGINV(1,LN(10),0.5) and =LOGINV(0.95,LN(10),0) are source-predicted errors. Enter 0.95 or 95%, not the plain number 95.

The exponential transformation can magnify a small log-scale change. Its numerical range is finite even though the mathematical lognormal distribution has no finite upper bound. Overflowed exponentials reach the numeric wrapper, which rejects nonfinite values; underflow can lose very small positive magnitudes. These examples do not certify extreme tails. LOGINV evaluates an inverse expression using a normal-quantile helper, not a solver that estimates distribution parameters or validates observed data.

Checked October 18, 2026 against current official help and SDKJS tag v10.0.0.169, commit 3679e0375a758d7dc59d31337a45461be3525ed8. Introduction dates and a final supported-version endpoint are not established. Desktop Editors, Docs, mobile releases and imported files require separate compatibility checks.

Neither the ONLYOFFICE application nor its calculation engine was executed for this guide. The numerical targets are independently calculated mathematical values; code-path and error observations are manual source traces. They are not screenshots, displayed workbook results or promises of identical final digits. Use English function names and comma separators as shown, adapting separators to the editor’s locale.

Keep inputs and intermediate probabilities numeric and unrounded. Format the display rather than replacing values with rounded strings. These moderate scalar examples do not certify extreme-tail accuracy, unusual type coercion, array entry or dynamic spill. Model assumptions must be checked separately from arithmetic correctness.

• Official LOGINV reference, checked October 18, 2026.
• Pinned implementation.
• Pinned normal helpers and beta helper.
• LOGNORM.DIST.
• LOGNORMDIST.
• LOGNORM.INV.
• NORM.S.INV and NORM.S.DIST.