Comparing multiple comparisons: practical guidance for choosing the best multiple comparisons test
Bibliographic record
Abstract
Multiple comparisons tests (MCTs) include the statistical tests used to compare groups (treatments) often following a significant effect reported in one of many types of linear models. Due to a variety of data and statistical considerations, several dozen MCTs have been developed over the decades, with tests ranging from very similar to each other to very different from each other. Many scientific disciplines use MCTs, including >40,000 reports of their use in ecological journals in the last 60 years. Despite the ubiquity and utility of MCTs, several issues remain in terms of their correct use and reporting. In this study, we evaluated 17 different MCTs. We first reviewed the published literature for recommendations on their correct use. Second, we created a simulation that evaluated the performance of nine common MCTs. The tests examined in the simulation were those that often overlapped in usage, meaning the selection of the test based on fit to the data is not unique and that the simulations could inform the selection of one or more tests when a researcher has choices. Based on the literature review and recommendations: planned comparisons are overwhelmingly recommended over unplanned comparisons, for planned non-parametric comparisons the Mann-Whitney-Wilcoxon U test is recommended, Scheffé’s S test is recommended for any linear combination of (unplanned) means, Tukey’s HSD and the Bonferroni or the Dunn-Sidak tests are recommended for pairwise comparisons of groups, and that many other tests exist for particular types of data. All code and data used to generate this paper are available at: https://github.com/stevemidway/MultipleComparisons .
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.213 | 0.590 |
| Meta-epidemiology (narrow) | 0.005 | 0.005 |
| Meta-epidemiology (broad) | 0.006 | 0.008 |
| Bibliometrics | 0.014 | 0.013 |
| Science and technology studies | 0.004 | 0.009 |
| Scholarly communication | 0.010 | 0.014 |
| Open science | 0.012 | 0.008 |
| Research integrity | 0.011 | 0.022 |
| Insufficient payload (model declined to judge) | 0.067 | 0.033 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".