First-Order Correct Bootstrap Support Adjustments for Splits that Allow Hypothesis Testing When Using Maximum Likelihood Estimation
Bibliographic record
Abstract
The most frequent measure of phylogenetic uncertainty for splits is bootstrap support. Although large bootstrap support intuitively suggests that a split in a tree is well supported, it has not been clear how large bootstrap support needs to be to conclude that there is significant evidence that a hypothesized split is present. Indeed, recent work has shown that bootstrap support is not first-order correct and thus cannot be directly used for hypothesis testing. We present methods that adjust bootstrap support values in a maximum likelihood (ML) setting so that they have an interpretation corresponding to P values in conventional hypothesis testing; for instance, adjusted bootstrap support larger than 95% occurs only 5% of the time if the split is not present. Through examples and simulation settings, it is found that adjustments always increase the level of support. We also find that the nature of the adjustment is fairly constant across parameter settings. Finally, we consider adjustments that take into account the data-dependent nature of many hypotheses about splits: the hypothesis that they are present is being tested because they are in the tree estimated through ML. Here, in contrast, we find that bootstrap probability often needs to be adjusted downwards.
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 | 0.032 | 0.352 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".