GAMMA.DIST in ONLYOFFICE Spreadsheet Editor

• Introduced: Original introduction release is not established by the checked sources.
• Available: Listed in current unversioned ONLYOFFICE help, checked October 18, 2026.
• Implementation inspected: Official SDKJS v10.0.0.169, commit 3679e0375a758d7dc59d31337a45461be3525ed8. The snapshot does not prove identical behavior in every installed editor.
• Retired or deprecated: These sources do not establish retirement or formal deprecation. A legacy name alone does not mean the function has been removed.
• Testing: Numerical examples are independent mathematical expectations, and implementation discrepancies are labeled source predictions. No ONLYOFFICE application or calculation-engine execution was performed.

The examples use English function names and commas. Use your locale’s argument separator if different. Retain full precision in formulas; round only the displayed result. The examples describe function mechanics under the stated model, rather than establishing that your observations follow that model.

=GAMMA.DIST(x, alpha, beta, cumulative)
=GAMMADIST(x, alpha, beta, cumulative)

All four arguments are required. Alpha is a positive shape, beta is a positive scale, and x is the measurement. TRUE returns the lower-tail CDF; FALSE returns the PDF. The inspected GAMMADIST class inherits the same calculation as GAMMA.DIST, so these names share the calculation path in this source snapshot.

The mean is alpha*beta and the variance is alpha*beta^2. Beta has the same units as x; it is not a rate. If another model gives rate lambda, the corresponding scale is 1/lambda. With alpha = 1, this is an exponential distribution of rate 1/beta. A density has inverse measurement units and need not be below 1. A continuous point probability is zero; interval probabilities require CDF differences.

Consider a model with shape 2 and scale 2 hours. Its mean is 4 hours and its standard deviation is SQRT(8) hours. This can model the sum of two independent exponential stages of equal rate, if that assumption fits the process.

1. Enter shape 2 in B1 and scale 2 in B2.
2. Put thresholds 2 and 4 in A5:A6.
3. In B5 enter =GAMMA.DIST(A5,$B$1,$B$2,TRUE) and copy down.
4. In C5 enter =GAMMA.DIST(A5,$B$1,$B$2,FALSE) and copy down.

For shape 2, CDF = 1-EXP(-x/beta)*(1+x/beta). At x = 4 and beta = 2, this becomes 1-3*EXP(-2). The density becomes (x/beta)*EXP(-x/beta)/beta, or EXP(-2) at this point. These elementary identities provide independent checks rather than relying on another spreadsheet engine.

The probability of a modeled wait from 2 through 4 hours is =GAMMA.DIST(4,2,2,TRUE)-GAMMA.DIST(2,2,2,TRUE), independently 0.329753032633. Using FALSE and subtracting densities would not calculate this probability.

If you change the measurement unit to minutes, multiply both x and beta by 60: =GAMMA.DIST(240,2,120,TRUE) represents the same event and CDF. The density per minute is the density per hour divided by 60, because its units change. Alpha remains 2. Keeping beta at 2 while changing only x would describe a different distribution.

For an ordinary quantile, GAMMA.INV solves for x at a requested lower-tail probability. It is sensible to substitute a computed quantile into a CDF as a numerical check, but the inspected inverse and distribution functions use different gamma-CDF helper implementations. An exact floating-point roundtrip is not promised.

The inspected wrapper rejects x<0, alpha<=0 and beta<=0 with internal not_numeric (#NUM!). Although current help describes x as positive, the source allows x = 0:

• CDF at zero follows the lower incomplete-gamma calculation and is mathematically 0 for positive shape.
• PDF at zero with alpha = 1 returns 1/beta; for beta = 2 this is 0.5.
• PDF at zero with alpha > 1 returns 0.
• PDF at zero with 0<alpha<1 is mathematically singular. The helper returns undefined and the wrapper predicts internal wrong_value_type (#VALUE!), rather than a useful numeric infinity. This is a source prediction, not a tested display.

The wrapper explicitly rejects a string cumulative argument before numeric conversion. Use TRUE or FALSE, not quoted text. Alpha and beta are not integer counts and should not be rounded merely to satisfy a model: positive fractional shapes and scales are meaningful.

The CDF helper uses series/continued-fraction calculations with iteration limits. Very small tails, extreme parameters and finite-precision subtraction need separate numerical validation; the modest examples above do not establish accuracy over every admissible input.

Recalculate representative formulas when moving a workbook between editors. Matching names do not guarantee identical argument coercion, array behavior, numerical precision or error handling. The scalar formulas here do not establish automatic spill behavior or a general import/export guarantee.

• GAMMA
• EXP
• LN

• ONLYOFFICE GAMMA.DIST help, checked October 18, 2026.
• Official SDKJS implementation, 7452–7520, tag v10.0.0.169 and exact commit above.
• ONLYOFFICE GAMMADIST help, checked October 18, 2026.