R.QGUMBEL Function (Gnumeric)
Find Gumbel cutoffs with Gnumeric R.QGUMBEL. Reconstruct lower, upper and log probabilities, distinguish the location from the median and check infinite endpoints.
Verification status: 23 reference, boundary and advanced-check formulas were recalculated with Gnumeric 1.12.57 ssconvert. Saved identities, the blank input and numerical results were independently checked. Gnumeric 1.12.62 was source-checked only. How formula examples are checked
Quick answer: =R.QGUMBEL(.5,0,1) gives 0.366512920582 in Gnumeric 1.12.57.
Availability and version history
- Introduced: Introduced in Gnumeric 1.12.25 release notes.
- Supported in: Gnumeric 1.12.62; no retirement is established.
- Scope: Desktop Gnumeric with its Statistical Functions From R plugin. English comma-separated formulas are shown.
- Checked: October 14, 2026. Tables and the named advanced check use 1.12.57 ssconvert. Current 1.12.62 source was inspected; that release was not executed.
What R.QGUMBEL returns
R.QGUMBEL returns the maximum-type Gumbel quantile. For an ordinary lower probability p between 0 and 1, the formula is location−scale×LN(−LN(p)). Upper-tail mode interprets the input as the complement; log_p accepts its natural logarithm. Versioned function help.
Syntax and arguments
=R.QGUMBEL(probability,location,scale[,lower_tail[,log_p]])
Probability, location and scale are required. Scale must be positive. lower_tail defaults to TRUE and log_p to FALSE. Unlike a positive-support distribution, the Gumbel support extends toward both negative and positive infinity.
Brackets mark optional arguments; do not type them. Current worksheet implementation.
Reproducible examples
These self-contained formulas were recalculated natively. Ordinary-domain results were checked against independent mathematics; source guards explain the boundary cases. Results are rounded to twelve decimal places, or thirteen significant digits for small nonzero values. This is presentation precision, not a universal accuracy guarantee.
| Formula | Gnumeric 1.12.57 result |
|---|---|
=R.QGUMBEL(.5,0,1) |
0.366512920582 |
=R.QGUMBEL(.9,0,1) |
2.250367327312 |
=R.QGUMBEL(.1,0,1,FALSE()) |
2.250367327312 |
=R.QGUMBEL(LN(.1),0,1,FALSE(),TRUE()) |
2.250367327312 |
=R.QGUMBEL(.5,2,3) |
3.099538761745 |
=R.QGUMBEL(.25,-1,.5) |
-1.163317129989 |
=R.QGUMBEL(EXP(-1),0,1) |
0 |
=R.QGUMBEL(-1,2,3,TRUE(),TRUE()) |
2 |
Practical worksheet
For location 0 and scale 1, the median is approximately 0.366512920582, so it is not equal to location. The 90th percentile is approximately 2.250367327312. Upper probability 0.1 produces the same threshold.
For location 2 and scale 3, the median is approximately 3.099538761745. The standard median is scaled by 3 and then shifted by 2. This affine relationship is useful when checking parameter order in a worksheet.
Advanced interpretation and checks
A lower probability of EXP(−1) corresponds exactly to location mathematically. The saved formula with standard parameters returns zero; the log-probability form with input −1, location 2 and scale 3 returns 2.
The advanced CDF reconstruction below returns 0.9 at the computed 90th percentile for location 2 and scale 3. The two equivalent log/ordinary probability examples differ only at the last stored place in one native result, so their shared twelve-decimal display is not a claim of bitwise equality.
The saved advanced-check result for =R.PGUMBEL(R.QGUMBEL(.9,2,3),2,3) was 0.9.
Boundaries and troubleshooting
Both probability endpoints require infinite cutoffs and become #NUM!, in either tail convention. Probability below zero or above one is invalid; a positive log probability is also invalid. Log probability zero represents probability one and reaches an endpoint.
Zero or negative scale gives #NUM!. Nonnumeric text gives #VALUE!; empty F5 becomes probability zero and therefore errors. Wrong arity gives #N/A. A quantile is a cutoff in observation units, not a probability or a fitted estimate of the location parameter.
F5 is genuinely empty, rather than a cell containing an empty string.
| Formula | Gnumeric 1.12.57 result |
|---|---|
=R.QGUMBEL(0,0,1) |
#NUM! |
=R.QGUMBEL(1,0,1) |
#NUM! |
=R.QGUMBEL(0,0,1,FALSE()) |
#NUM! |
=R.QGUMBEL(1,0,1,FALSE()) |
#NUM! |
=R.QGUMBEL(-.1,0,1) |
#NUM! |
=R.QGUMBEL(1.1,0,1) |
#NUM! |
=R.QGUMBEL(.5,0,0) |
#NUM! |
=R.QGUMBEL(.5,0,-1) |
#NUM! |
=R.QGUMBEL(0,0,1,TRUE(),TRUE()) |
#NUM! |
=R.QGUMBEL(1,0,1,TRUE(),TRUE()) |
#NUM! |
=R.QGUMBEL("abc",0,1) |
#VALUE! |
=R.QGUMBEL(F5,0,1) |
#NUM! |
=R.QGUMBEL(.5,0) |
#N/A |
=R.QGUMBEL(.5,0,1,0,0,1) |
#N/A |
Official evidence and checking scope
- Current worksheet callback
- Tested-version worksheet callback
- Current qgumbel calculation
- Tested-version qgumbel calculation
- Nonfinite worksheet-value handling
- Statistical Functions From R plugin declaration
The relevant complete worksheet callback and main calculation helper are unchanged between the inspected versions. That does not establish later-version numerical execution. Both stale and uncached SUM controls recalculated correctly. Native XML preserves the R.* identities. The secondary ODF export keeps these calls in the ORG.GNUMERIC namespace; it does not establish execution in another product. GUI entry, other locales and other spreadsheet products were not tested.