GAMMA.INV in Collabora Office: Find Gamma-Distribution Quantiles
Use Collabora GAMMA.INV to calculate thresholds from cumulative probabilities, verify round trips and distinguish the gamma special function.
Verification status: See the evidence and test scope described in this guide. How formula examples are checked
Quick answer: =GAMMA.INV(0.9;2;2) has independently expected result approximately 7.779440340. It finds a value whose gamma cumulative probability is 0.9 for shape two and scale two.
Syntax and inverse target
=GAMMA.INV(Number; Alpha; Beta)
Number is the cumulative probability. Alpha is the positive shape parameter and Beta is the positive scale parameter. The dedicated Collabora help identifies this as the inverse gamma cumulative distribution and says it is identical to GAMMAINV, introduced for interoperability. It does not supply an introduction release.
This function is not the inverse of the special function GAMMA(Number). For example, GAMMA(6)=120 says nothing about whether GAMMA.INV accepts 120 as a probability. A probability input belongs on a zero-to-one scale.
For the worked finite interior quantiles use 0<Number<1. Current Collabora source also handles probability zero explicitly as zero and rejects probabilities at or above one; that source observation is not a fresh native desktop test. Alpha and Beta must remain positive.
Example 1: calculate three percentiles
Put 0.1, 0.5 and 0.9 in A2:A4. Put shape 2 in F2 and scale 2 in F3. Enter =GAMMA.INV(A2;$F$2;$F$3) in B2 and fill down.
Independent expected results are approximately 1.063623217, 3.356693980 and 7.779440340. Label the output with the model’s unit, such as hours. A 90th percentile means 90% of the modeled distribution is at or below that threshold.
The model’s mean is Alpha*Beta=4, whereas the median is approximately 3.356693980. A requirement for an “average” and one for a “50th percentile” are different specifications.
Example 2: verify the cumulative round trip
In C2 enter =GAMMA.DIST(B2;$F$2;$F$3;1) and fill down. The independent targets are the original 0.1, 0.5 and 0.9 probabilities.
For this shape-two, scale-two case, another check is =1-EXP(-B2/2)*(1+B2/2). This closed form should recover the same probabilities mathematically. Keep the full B values rather than substituting rounded displays.
A large residual can indicate that Beta changed between formulas, the forward function used density mode, or a percentage was entered as a whole number. A native tolerance cannot be inferred solely from the independent reference residual.
Advanced application: solve the shape-one case directly
When Alpha=1, the gamma model is exponential with scale Beta. Its quantile is =-Beta*LN(1-p) for an interior probability p.
The official example GAMMA.INV(0.8;1;1) has independent target 1.609437912, which the documentation rounds to 1.61. The direct expression =-LN(1-0.8) supplies a separate mathematical check.
With Beta=2, =GAMMA.INV(0.8;1;2) instead targets 3.218875825. Scale multiplies a quantile; it is not a rate parameter that should be inserted unchanged from a rate-based reference.
Advanced application: rescale a model’s units
For fixed shape and probability, multiplying Beta by sixty multiplies the output quantile by sixty. The shape remains unchanged. This converts an hours-based model to minutes when all quantities are transformed consistently.
For the shape-two median, =GAMMA.INV(0.5;2;120) has independent target approximately 201.401638802 minutes, sixty times the earlier median. A change in scale is not the same operation as changing shape; shape changes the distribution’s relative form.
Errors and troubleshooting
Validate positive parameters and probability units. The function can face numerical convergence or precision limits for extreme inputs; the current source contains an iterative inverse calculation, and the independent controls do not certify all installed-version convergence behavior.
Do not round an intermediate quantile before validating it. If the result seems inconsistent with the mean, remember that a skewed distribution has different mean and median. The function computes thresholds for supplied parameters; it does not fit those parameters or guarantee that the model describes your data.
Availability and verification
The exact function is documented in Collabora Office 26.04 desktop help. The snapshot was retrieved on 2026-10-13 and hash-verified on October 15, 2026. Desktop help is not proof of Online or mobile availability. First introduced release and last functioning version are unknown; the dedicated source does not establish them.
No native Collabora or WPS execution occurred. Numerical values are independent mathematical expectations, not certification of application errors or all numerical limits. Formulas use English names and semicolon separators.
A current Collabora interpreter source snapshot retrieved October 15, 2026 corroborates the described domain or parameter roles. It is from the moving main branch, not a pinned 26.04 binary, and is not an application execution.
The dedicated help identifies namespace COM.MICROSOFT.GAMMA.INV and places the function outside the cited OpenFormula 1.3 standard. This format disclosure does not establish cross-product behavioral identity.