Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Statistics›Page's L Test for Ordered Alternatives
Hypothesis test

Page's L Test for Ordered Alternatives

Also known as: page trend test, page ordered alternatives test, Page L Testi — Sıralı Alternatifler

Page's L test is a nonparametric hypothesis test designed for repeated-measures (randomized complete block) designs in which the researcher has a specific, pre-stated ordering hypothesis across k ≥ 3 conditions. Introduced by Ellis Batten Page in 1963, it is more powerful than the Friedman test when the alternative hypothesis specifies a monotone trend rather than a general difference among conditions.

ScholarGate
  1. Hypothesis test
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Page's L Test
Friedman test

When to use it

Use Page's L test when you have a repeated-measures or randomized complete block design with k ≥ 3 conditions, the outcome is at least ordinal, and — critically — you have a theoretically motivated, pre-specified monotone ordering of the conditions. The test requires that every subject appears in every condition (complete blocks) and that observations are independent across subjects. The ordering hypothesis must be committed to before data collection; post-hoc ordering would inflate the false-positive rate. If you have no directional prediction, the Friedman test is more appropriate. Minimum recommended sample size is about 10 blocks.

Strengths & limitations

Strengths
  • More powerful than the Friedman test when a directional ordered alternative is theoretically justified.
  • Does not require normality or homoscedasticity — suitable for ordinal data or non-normal continuous measurements.
  • Simple calculation: ranks within blocks, weighted sum, one z-statistic.
Limitations
  • Requires the ordering hypothesis to be specified before data collection; the test is invalid if the order is chosen after inspecting the data.
  • Designed only for complete block designs — missing values in any block are problematic.
  • Tests only the global ordered trend; it does not identify which adjacent condition pairs drive the pattern.

Frequently asked

How is Page's test different from the Friedman test?

The Friedman test is omnibus — it tests whether any difference exists among the k conditions. Page's L test is directional; it concentrates all its power on the single ordered pattern you predicted. When that pattern holds, Page's test is more powerful. When there is no prior ordering hypothesis, the Friedman test is the correct choice.

What counts as specifying the ordering hypothesis a priori?

You must declare the expected ranking of conditions based on theory or prior evidence, before data collection begins, and document it in a pre-registration or methods section. Deciding the order after looking at the data or choosing the order that gives the lowest p-value destroys the validity of the test.

Can I use Page's test with ties in the within-block rankings?

Ties within a block can be handled by assigning mid-ranks. The standard normal approximation remains valid, but for heavy ties the normal approximation may be slightly conservative. Exact critical values from Page (1963) assume no ties.

What should I do if the test is significant but I want to know which conditions differ?

Page's L test provides a global verdict on the ordered trend; it does not decompose the result into pairwise comparisons. If you need to identify which specific adjacent pairs contribute, follow up with appropriate post-hoc nonparametric comparisons, keeping in mind the inflation of Type I error across multiple tests.

Sources

  1. Page, E. B. (1963). Ordered hypotheses for multiple treatments: a significance test for linear ranks. Journal of the American Statistical Association, 58(301), 216–230. DOI: 10.1080/01621459.1963.10500843 ↗
  2. Hollander, M. & Wolfe, D. A. (1999). Nonparametric Statistical Methods (2nd ed.). Wiley. ISBN: 978-0471190455

How to cite this page

ScholarGate. (2026, June 1). Page's L Test for Ordered Alternatives. ScholarGate. https://scholargate.app/en/statistics/page-test

Related methods

Friedman test

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Friedman testStatistics↔ compare
Compare side by side →

Similar methods

Friedman testJonckheere-Terpstra TestWilcoxon signed-rank testNemenyi TestRobust Friedman testCochran Q TestKruskal-Wallis testMann-Whitney U test

Related reference concepts

Rank-Based MethodsStatistical Hypothesis TestingLikelihood-Ratio TestsPermutation TestsHypothesis Testing FrameworkUniformly Most Powerful Tests

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Page's L Test (Page's L Test for Ordered Alternatives). Retrieved 2026-07-20 from https://scholargate.app/en/statistics/page-test · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Ellis Batten Page
Year
1963
Family
Hypothesis test
Type
Nonparametric trend test
Groups
k ≥ 3
Outcome
continuous or ordinal
Parametric
No
Design
Repeated measures / randomized complete block
Statistic
L (Page's L)
AlternativeHypothesis
Ordered (directional)
Related methods
Friedman test
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account