PROB in Collabora Office: Sum Probabilities for Discrete Outcome Intervals
Use Collabora PROB with aligned outcomes and probability weights, distinguish interval from exact-value queries, and calculate a conditional probability.
Verification status: See the evidence and test scope described in this guide. How formula examples are checked
Quick answer: For outcomes 10, 20, 30, 40 with probabilities 0.1, 0.2, 0.4, 0.3, =PROB(A2:A5;B2:B5;20;30) has independently expected result 0.6. It adds the probability weights attached to outcomes in the specified interval.
Syntax and argument alignment
=PROB(Data; Probability; Start [; End])
Data is an array or range of outcome values. Probability is the corresponding array or range of probability weights. Start is the lower interval value. End is optional; if omitted, the function calculates the probability for an outcome equal to Start.
Each probability must remain paired with its outcome. Sorting only one column changes the model. These weights describe a discrete distribution; PROB does not fit a continuous probability distribution or estimate probabilities from an unweighted list of observations.
For a valid probability model, use nonnegative probabilities totaling one and matching outcome/weight dimensions. The dedicated Collabora section does not enumerate the native rejection rules or error codes for every invalid table; those mathematical prerequisites should not be confused with a tested native validation matrix.
Example: create a four-outcome distribution
Enter this dataset in A2:B5:
| Row | A: outcome | B: probability |
|---|---|---|
| 2 | 10 | 0.1 |
| 3 | 20 | 0.2 |
| 4 | 30 | 0.4 |
| 5 | 40 | 0.3 |
The weights total 1. The independently expected queries are:
| Formula | Expected probability | Explanation |
|---|---|---|
=PROB(A2:A5;B2:B5;20;30) |
0.6 | Weight at 20 plus weight at 30 |
=PROB(A2:A5;B2:B5;30) |
0.4 | Exact outcome 30 |
=PROB(A2:A5;B2:B5;25) |
0 | No listed outcome equals 25 |
=PROB(A2:A5;B2:B5;10;40) |
1 | All outcomes |
Formatting 0.6 as a percentage displays 60% without changing the underlying probability. Entering 60 rather than 60% is a very different weight.
Omitted End changes the question
=PROB(A2:A5;B2:B5;30) is an equality query, not a shorthand for “at least 30.” For the latter in this finite table, use the upper limit 40:
=PROB(A2:A5;B2:B5;30;40)
The independent result is 0.7. The omitted-End equality rule is explicit in the Collabora documentation and is an important distinction when translating a verbal probability question into a formula.
Advanced example: conditional probability within a selected group
To find the probability of outcome 40 given that the outcome is at least 30, first calculate the denominator 0.7 with the previous interval query. Then calculate:
=PROB(A2:A5;B2:B5;40)/PROB(A2:A5;B2:B5;30;40)
The independently expected result is 3/7, approximately 0.428571429. This is a conditional probability formed by dividing the relevant subset weight by the conditioning group’s weight.
Check that the denominator is positive before division. If the selected conditioning event has probability zero, the conditional ratio is undefined; replacing that denominator with one would change the question.
Advanced check: expectation is a different summary
The expected outcome for the table is 29, calculated as 10×0.1+20×0.2+30×0.4+40×0.3. SUMPRODUCT can express this weighted total as =SUMPRODUCT(A2:A5;B2:B5).
That expected value is not itself a possible outcome in this example, and it is not a probability. A range-probability query and an expected-value calculation summarize different aspects of the same distribution.
For an independent duplicate-outcome illustration, two rows both labeled 20 with weights 0.05 and 0.15 represent total weight 0.20 at that outcome. Preserve and combine weights deliberately when grouping source data; do not delete one duplicate row without considering its probability contribution.
Errors and troubleshooting
Confirm that both ranges cover the same rows and that the probabilities are numeric values in the intended scale. SUM provides a straightforward total-weight check. If a result seems too large, look first for percentages entered as whole numbers or weights paired with the wrong outcomes.
The reviewed section does not supply a complete error/coercion matrix, invalid-limit behavior, tolerance for an imperfect total of one, or limits on array dimensions. This guide’s outputs use a simple, normalized table with ordered limits, and do not certify those untested native edge cases.
Availability and verification
The exact function is documented in Collabora Office 26.04 desktop help, retrieved and reviewed on October 17, 2026. This establishes a documentation scope, not the first release that introduced the function or the last version in which it works; those versions and any retirement date remain unestablished. Collabora Online and mobile support are not inferred from desktop help, nor is behavior in another spreadsheet product.
The examples are documentation-based expectations with independent calculations. They have not been executed in Collabora Office. No application screenshot or native error/coercion certification is implied. Formulas use English function names and semicolon argument separators.
References
- Collabora Office 26.04: PROB (checked October 17, 2026).
- Editorial testing standards.