Z.TEST in Collabora Office: Calculate a Right-Tail Mean-Test Probability

=Z.TEST(Data; mu [; Sigma])
=ZTEST(Data; mu [; Sigma])

Data is the sample array or range. mu is the population mean under the null hypothesis. Sigma is the known population standard deviation, not its variance and not the standard error. Sigma is optional; when omitted, the evaluator estimates standard deviation from this sample using denominator n−1.

The pinned Collabora source gives Z.TEST and ZTEST identical two-required/one-optional argument metadata and sends both to ScZTest without name-dependent behavior. They are covered together here. There is no tails argument.

Use a numeric range without its heading. The source iterates numeric sample values; text and empty cells do not add sample observations, while numerical zero does. Do not turn missing values into zeros. Cell errors and unusual coercions need separate attention; these guides do not claim native tests of every input representation.

Put a heading in A1 and 8, 9, 10, 11, 12 in A2:A6. Enter =Z.TEST(A2:A6;9;2) in C2. The independently calculated target is 0.131776238641. =ZTEST(A2:A6;9;2) has the same expected value.

The sample mean is 10, n=5, and the standard error is 2/sqrt(5). The statistic is z=(10−9)/(2/sqrt(5)) = 1.118033988750. The result is 1−Phi(z), the standard-normal probability to the right of that statistic.

The output is a probability, so General/Number or Percentage formatting is appropriate. A percentage display around 13.18% does not mean that the null hypothesis has a 13.18% chance of being true.

In C3 enter =Z.TEST(A2:A6;9). The sample variance is 2.5 and sample standard deviation is sqrt(2.5). The standard error is sqrt(2.5/5), so z=sqrt(2). The independent right-tail target is 0.078649603525.

The difference from C2 comes from replacing known sigma=2 by estimated sigma≈1.581138830084. The omitted-Sigma path still returns a normal-tail probability. It does not silently switch to a Student t distribution. With a small sample and unknown population spread, choose an appropriate statistical method rather than treating this fallback as automatically justified.

If C2 contains the right-tail result p, a lower-tail alternative uses =1-C2, expected 0.868223761359 here. A symmetric two-sided alternative uses =2*MIN(C2;1-C2), expected 0.263552477283.

Choose the alternative hypothesis in advance. A mean below mu produces a negative z and a right-tail result greater than 0.5; that is not an error. For example, changing mu to 11 with Sigma=2 gives the complementary right-tail result 0.868223761359. When the sample mean equals mu, the expected result is 0.5.

Collabora Help describes a sample from a normally distributed population. A classical known-sigma z test also assumes independent observations and a suitable sampling design. In large samples a normal approximation may be useful under additional conditions, but the function does not check those conditions.

The probability describes a statistic at least as large under the null model. It is not a probability that an individual future observation exceeds mu, and it does not measure the size or practical importance of the effect. Report the mean difference and sample context alongside it.

The pinned evaluator requires more than one numeric observation even when a positive Sigma is supplied. An empty or one-observation sample triggers division-by-zero behavior. Explicit Sigma must be greater than zero; zero and negative values are rejected rather than treated as omission.

If Sigma is omitted and all observations are identical, the zero estimated variance triggers division-by-zero behavior. If a valid positive Sigma is supplied to a constant sample of at least two observations, that particular zero-sample-variance check is not used. Error labels in the GUI and extreme-tail accuracy remain native-unverified.

F.TEST compares two variances, and T.TEST is a different mean-test function. Collabora Help places the dotted Z.TEST spelling in COM.MICROSOFT.Z.TEST outside OpenFormula 1.3; verify compatibility when exchanging files.

Reviewed on 19 October 2026 against saved Collabora Office 26.04 Help retrieved on 17 October 2026 and the Collabora co-26.04 source snapshot at commit c1013fad0d38683630b48c01b6d5208b8d81181e. The repository is hosted under LibreOffice/core, but the evidence used here is the pinned Collabora branch snapshot, not a claim about another spreadsheet product. The Help URL marked latest can change. Fresh Help retrieval was unavailable during this review, so Help statements were checked against the saved first-party pages; the pinned implementation files were freshly retrieved and verified.

Examples are independently calculated expectations, not recorded Collabora output. Native Collabora and its GUI were unavailable for this review; no screenshots or application runs are claimed. The first release introducing this function and the last working binary version have not been established. Online, mobile, older releases, localized function names, and round-trip compatibility need separate verification. Formulas use English names and semicolon separators; use the separators configured in your installation.

• Collabora Help: Z.TEST and ZTEST — reviewed 19 October 2026.
• Pinned normal-tail evaluator and sample handling — reviewed 19 October 2026.
• Pinned same-dispatch spellings — reviewed 19 October 2026.
• Pinned argument metadata — reviewed 19 October 2026.