BETA.INV in Excel: Convert Beta Probabilities Into Bounded Quantiles
Find beta-distribution percentile cutoffs in Excel, verify the cumulative round trip, and distinguish bounds, shape parameters and endpoint evidence.
Verification status: See the evidence and test scope described in this guide. How formula examples are checked
Quick answer: =BETA.INV(0.5,2,3) has independent expected result 0.3857275681. It is the median of the specified standard beta distribution, not the mean 0.4 or the interval midpoint 0.5.
Syntax and inverse meaning
=BETA.INV(probability, alpha, beta, [A], [B])
The required arguments are a cumulative probability and positive shape parameters alpha and beta. Optional bounds A and B default to zero and one when both are omitted. The output is a value within the chosen interval, measured in the same units as the bounds.
BETA.INV inverts BETA.DIST with cumulative=TRUE. It does not invert the density curve. A density can have the same height at different x values and is not the percentile criterion.
The worked calculations use strictly interior probabilities and increasing bounds. This avoids relying on native endpoint behavior that was not executed during this review.
Example 1: inspect three quantiles
Put 0.25, 0.5 and 0.9 in A2:A4. Enter =BETA.INV(A2,2,3,0,1) in B2 and fill down. Independent targets are approximately 0.2430220838, 0.3857275681 and 0.6795394163.
These are the 25th, 50th and 90th percentiles under the supplied model. They are not observed-data percentiles calculated from a range of measurements; no dataset is an argument to this function.
The model is asymmetric because the shapes differ. Its mean is 0.4, while its median is about 0.3857. Substituting a mean for a requested percentile changes the question.
Example 2: verify each result forward
In C2 enter =BETA.DIST(B2,2,3,TRUE,0,1) and fill down. Mathematical targets are the original probabilities 0.25, 0.5 and 0.9.
For these shapes, an independent check is =6*B2^2-8*B2^3+3*B2^4. It evaluates the beta cumulative polynomial and should return the same probabilities. Use the stored B values instead of manually retyping their rounded displays.
A large discrepancy usually indicates changed shapes, different bounds or a FALSE cumulative flag. Small floating-point residuals need a suitable tolerance; the independent high-precision checks do not establish Excel’s native tolerance.
Advanced application: rescale the percentile
For bounds ten and twenty, =BETA.INV(0.5,2,3,10,20) has independent target 13.8572756813. The transformation is A+(B−A)*standard_quantile.
Thus the general-bound result equals =10+10*BETA.INV(0.5,2,3,0,1) mathematically. This identity audits the scale without changing the distribution’s shape. It is not the same as replacing beta=3 with beta=20; the shape argument and upper bound serve different roles.
A percentile interval is a statement about the chosen distribution. It is not automatically a confidence interval for an unknown parameter or a guarantee for future observations.
Advanced application: reproduce the rounded source input
Microsoft uses probability 0.685470581, shapes 8 and 10, and bounds 1 and 3. Its inverse example displays 2. A high-precision independent inversion is approximately two because the supplied probability is rounded from the cumulative value at that point.
If a workflow starts with a BETA.DIST result, pass that cell directly into BETA.INV. Do not first replace it with a seven-decimal display and then insist on exact equality to the original x.
The official reference explicitly states that inverse precision depends on BETA.DIST precision. That is a documentation limit, not a measured error bound for every input.
Errors and endpoint scope
Microsoft documents #VALUE! for nonnumeric arguments and #NUM! for alpha≤0, beta≤0, probability≤0 or probability>1. Notice the probability restriction is not written the same way as the strict interior rules on some other inverse functions: its remarks do not exclude one.
The mathematical upper-end quantile for a bounded beta distribution is B. This guide does not claim a captured native endpoint result; all executable examples use interior probabilities. Validate increasing numeric bounds explicitly, since the dedicated inverse remarks do not enumerate every bounds error.
Check probability units: 90% and 0.9 represent the same probability, while 90 does not. Keep outputs and probabilities separately labeled. BETA.INV evaluates the supplied shapes; it does not fit them from data or validate their suitability.
Availability and version history
- Current documentation: the dedicated Microsoft reference lists Excel for Microsoft 365, Excel for Microsoft 365 for Mac, Excel 2024, Excel 2024 for Mac, Excel 2021, Excel 2021 for Mac, Excel 2019, Excel 2016.
- Introduced: Microsoft’s alphabetical catalog marks the linked BETA.INV function as introduced in Excel 2010. The catalog currently misspells its display label “BETA.INVn”; its destination and the dedicated function page establish the canonical BETA.INV identity. Exact first build and platform-specific introduction dates remain unverified.
- Last functioning version: unknown; a current help listing is not a last-working-build test.
- Evidence checked: October 15, 2026. Official documentation was freshly retrieved; examples were independently calculated. No native Excel, Mac or web-client execution was performed.
References and verification
- Microsoft BETA.INV reference.
- Microsoft function catalog and introduction-marker explanation.
- Editorial testing standards.
Examples use English function names and comma separators. Expected numbers are rounded independent mathematical calculations; documented error expectations are labeled as such. They are not captured Excel output. All illustrative data and policies are fictional.