Teaching · For Teachers

The right test for ranks, ratings and counts.

Say what you want to know and what your data look like. The guide names the test, the follow-up if one is needed, the effect size to report and how to write it up.

Choose a testWhat you get
$12one-time · every device you sign in on
Buy · $12

Included with Caveat Classroom and Whole-school licenses. Or get it in the For Teachers toolkit, $79 for 72 items.

The test chooser

One choice per research question. The example is made up.

Loading the form. If nothing appears, turn on JavaScript.

What you get

Teaching · For Teachers$12 · included with Classroom and Whole-school licenses

What you finish with
The test, its follow-up, the effect size, the parametric test it replaces and a reporting template.
Who it is for
Teacher-researchers, education graduate students, program evaluators and school data teams.
Format
Browser form. One saved choice per research question; printed with the result or as a blank decision sheet; CSV across questions; export and import a file.
Access
$12 one-time, yours on every device you sign in on; the tool opens once you are signed in with it. Included with Caveat Classroom and Whole-school licenses. Also in the For Teachers toolkit ($79) and the Teaching Suite pass ($199), and 1 more bundle. Everything you type stays in this browser; nothing is sent to Caveat.
Where it lives
The For Teachers space in Caveat Teaching.
Support
Questions about an order, access or a correction: team@caveatacademic.com.
12345678line them up, then compare the ranks
Drawn for this page. Most nonparametric tests replace scores with ranks and ask whether one group’s ranks sit higher than another’s.

How to use it

  1. Start a choice with a code for the research question.
  2. Say whether you are comparing, relating or testing one group.
  3. Describe the outcome, the groups and the design.
  4. Run the test named in your statistics software.
  5. Report the statistic, p-value and effect size in the form shown.

Choose a test

How the choice is made

When to go nonparametric

Ratings and ranks are ordinal; scores with heavy skew or outliers, especially in small samples, break the assumptions of t tests and ANOVA. Rank-based tests make fewer assumptions and are the standard alternatives.

Medians and shapes

Mann-Whitney and Kruskal-Wallis compare whole distributions. They are tests of medians only when the groups have similar shapes, so report medians with ranges or quartiles.

What this is not

A statistics package. It points to the test; your software runs it.

Sources

  1. Field, A. (2018). Discovering Statistics Using IBM SPSS Statistics (5th ed.). Sage: nonparametric tests and effect sizes.
  2. Conover, W. J. (1999). Practical Nonparametric Statistics (3rd ed.). Wiley.
  3. Tomczak, M., & Tomczak, E. (2014). The need to report effect size estimates revisited. Trends in Sport Sciences, 1(21), 19–25.
  4. Hart, A. (2001). Mann-Whitney test is not just a test of medians: differences in spread can be important. BMJ, 323(7309), 391–393.

The example question is made up. Support: team@caveatacademic.com.