CONFIDENCE.NORM in Collabora Office: Calculate a Normal-Based Margin of Error
Use Collabora CONFIDENCE.NORM to calculate a mean-interval half-width, distinguish alpha from confidence and avoid treating sample size as population size.
Verification status: See the evidence and test scope described in this guide. How formula examples are checked
Quick answer: =CONFIDENCE.NORM(0.05;1.5;100) has independently expected result approximately 0.293994598. This is a margin, or half-width, rather than two completed interval endpoints.
Syntax and statistical inputs
=CONFIDENCE.NORM(Alpha; StDev; Size)
Alpha is the total probability outside the two-sided interval. A 95% confidence construction uses Alpha=0.05, not 0.95. StDev is the positive population standard deviation assumed known for the usual normal-based mean interval. Size is the number of observations used in the standard-error calculation.
The dedicated Collabora help labels Size as population size and calls the result an interval. The corroborating implementation makes the computation precise: normal quantile at 1-Alpha/2, multiplied by StDev/SQRT(Size). For mean inference, Size supplies the sample count, not the count of all possible population members.
This formula has no finite-population correction, no sample mean argument and no survey-design adjustment. It therefore cannot infer a complete interval or fix an inappropriate sampling design from three numbers alone.
Example 1: reproduce the documented margin
Put 0.05, 1.5 and 100 in B2:B4, with labels Alpha, Known standard deviation and Sample size in A2:A4. Enter =CONFIDENCE.NORM(B2;B3;B4) in B5.
The independent standard error is 0.15 and the normal critical value approximately 1.959963985. Their product is approximately 0.293994598, matching the official example.
Enter =NORM.S.INV(1-B2/2)*B3/SQRT(B4) in B6 for a transparent reference construction. Use full stored values rather than a manually rounded 1.96 if checking close agreement.
Example 2: form the endpoints explicitly
Put a sample mean of 10 in B7. Enter =B7-B5 in B8 and =B7+B5 in B9. Independent endpoints are approximately 9.706005402 and 10.293994598.
The total interval width is =2*B5, approximately 0.587989195. Adding the full width on both sides would make the intended interval twice as wide as required.
All results retain the measurement unit of the standard deviation and mean. If the input data are minutes, the margin and endpoints are in minutes; the probability Alpha is unitless.
Advanced application: compare sample sizes
With Alpha=0.05 and StDev=1.5, sizes 25, 100 and 400 give independent margins approximately 0.587989195, 0.293994598 and 0.146997299.
Quadrupling sample size halves the normal margin when the standard deviation and confidence level stay fixed. Merely doubling sample size does not halve it, because the denominator uses a square root.
Changing the confidence level changes the critical value separately. A smaller Alpha requests higher confidence and a wider interval, all else equal. Keep sample-size and confidence changes in separate columns when comparing designs.
Advanced application: distinguish uncertainty in a mean from data spread
The margin here describes uncertainty in an estimated population mean under the chosen model. It is not a range expected to contain 95% of individual observations, and it is not a future-observation prediction interval.
If the population standard deviation is estimated from the same small sample rather than known, a t-based mean construction can be appropriate under its assumptions. Simply using a sample standard deviation in this normal formula does not make it a t interval.
Errors and troubleshooting
Current source approximately floors Size, requires effective Size>=1, StDev>0 and 0<Alpha<1. Enter integer sample counts explicitly. Zero standard deviation follows an error guard in this implementation even though a formal mathematical expression could be zero; do not infer native behavior solely from that algebraic limit.
The guide does not certify native error messages, all text coercions or extreme quantiles. A frequentist confidence level describes the procedure’s repeated-sampling coverage under assumptions; it is not a calculated posterior probability for a fixed parameter inside the particular displayed interval.
Availability and evidence
The exact function is documented in Collabora Office 26.04 desktop help. That documentation snapshot was retrieved on 2026-10-13 and hash-verified on October 15, 2026. It does not establish Online or mobile support. First introduction and last functioning release are unknown in this evidence.
Additional implementation statements come from Collabora’s current engine source, retrieved October 15, 2026. This moving-main source is corroboration, not a pinned desktop 26.04 binary or a native execution. No native Collabora Office run occurred. Worked outputs are independent mathematical expectations.
Formulas use English names and semicolon separators. The help identifies namespace COM.MICROSOFT.CONFIDENCE.NORM, outside its cited OpenFormula 1.3 standard; that does not establish identical behavior in another application.