NORM.S.INV in Collabora Office: Find Standard-Normal Quantiles
Use Collabora NORM.S.INV to convert a cumulative probability into a z cutoff and distinguish central areas from one-tail thresholds.
Verification status: See the evidence and test scope described in this guide. How formula examples are checked
Quick answer: =NORM.S.INV(0.975) has independently expected result approximately 1.959963985. It is the z value with 97.5% of the standard-normal model to its left.
Syntax and input domain
=NORM.S.INV(Number)
Number is a cumulative probability. It is the only required argument. The distribution being inverted has mean zero and standard deviation one, so the returned result is a standardized cutoff, not a raw measurement.
Use probabilities strictly between zero and one for finite quantiles. Values at the endpoints correspond to infinite limits in the ideal distribution. The dedicated help does not specify every native endpoint error, so this guide does not invent an error code.
Enter 97.5% or 0.975, rather than 97.5. A percentage format changes how a value appears but does not rescue an out-of-range number already stored as 97.5.
Example 1: create symmetric cutoffs
Put 0.025, 0.5, 0.975 in A2:A4. In B2 enter =NORM.S.INV(A2) and fill down. Independently expected results are approximately −1.959963985, 0, 1.959963985.
In C2 enter =NORM.S.DIST(B2;1) and fill down. The independent round-trip targets are the original probabilities. Keep B cells at full precision; showing fewer decimals does not require replacing the stored values.
The median is zero because the standard-normal model is symmetric around zero. Equal tail probabilities on opposite sides produce equal-magnitude, opposite-sign quantiles.
Example 2: choose the correct tail
For an upper-tail probability of 5%, the left-tail probability is 95%, so use =NORM.S.INV(0.95), independently approximately 1.644853627.
For a central interval containing 95%, split the remaining 5% equally into two tails and use cumulative probabilities 0.025 and 0.975. Its positive cutoff is approximately 1.959963985, not 1.644853627.
The difference arises from the question’s tail definition. Calling both quantities a “95% cutoff” without further explanation makes a worksheet ambiguous.
Advanced application: return to measurement units
If a normal model has mean 100 and standard deviation 10, the upper central-95% bound is =100+10*NORM.S.INV(0.975), independently approximately 119.599639845. The corresponding lower bound uses 0.025 and gives approximately 80.400360155.
The same transformation can be used for any specified mean and positive standard deviation. It does not estimate those parameters or establish whether a normal model fits observed data.
Do not confuse this population-model interval with uncertainty about an estimated average. Sample size and the inference procedure matter for that different task.
Advanced application: inspect sensitivity near a tail
The 90th-percentile z value is approximately 1.281551566, the 95th is 1.644853627, and the 99th is 2.326347874. Equal changes in probability do not produce equal steps in z.
Build a scenario column of probabilities rather than adding a fixed increment to a previously calculated quantile. The inverse cumulative function is nonlinear, and the effect becomes pronounced near zero and one.
The documented Collabora example =NORM.S.INV(0.908789) targets approximately 1.333334673, which provides another moderate, reproducible control without an extreme tail.
Errors and troubleshooting
If a result has the wrong sign, inspect whether a lower-tail probability was used where an upper-tail exceedance was intended. If it is displayed as a percent, change the format to a number: z itself is not a probability.
The exact dotted function name is preserved. This guide does not merge the legacy NORMSINV identity or assume all import formats use identical names. Extreme numerical cases, native errors and additional application versions remain unverified.
Availability and verification
The exact function is documented in Collabora Office 26.04 desktop help. Its source snapshot was retrieved on 2026-10-13 and hash-verified for this guide on October 15, 2026. Desktop documentation is not proof of Online or mobile support.
First introduced release and last functioning version are unknown. No native Collabora or WPS run occurred. The numerical values are independent mathematical expectations; they do not certify application-specific numerical tolerances, error codes or every edge case. Formulas use English names and semicolon separators.
The dedicated help identifies the namespace COM.MICROSOFT.NORM.S.INV and says this function is outside the cited OpenFormula 1.3 standard. That is a format-namespace disclosure, not evidence of identical behavior in another product. Retain the exact dotted name when checking an imported workbook.