Evidence that nonsignificant results are sometimes preferred: Reverse P-hacking or selective reporting?
Bibliographic record
Abstract
There is increased concern about poor scientific practices arising from an excessive focus on P-values. Two particularly worrisome practices are selective reporting of significant results and 'P-hacking'. The latter is the manipulation of data collection, usage, or analyses to obtain statistically significant outcomes. Here, we introduce the novel, to our knowledge, concepts of selective reporting of nonsignificant results and 'reverse P-hacking' whereby researchers ensure that tests produce a nonsignificant result. We test whether these practices occur in experiments in which researchers randomly assign subjects to treatment and control groups to minimise differences in confounding variables that might affect the focal outcome. By chance alone, 5% of tests for a group difference in confounding variables should yield a significant result (P < 0.05). If researchers less often report significant findings and/or reverse P-hack to avoid significant outcomes that undermine the ethos that experimental and control groups only differ with respect to actively manipulated variables, we expect significant results from tests for group differences to be under-represented in the literature. We surveyed the behavioural ecology literature and found significantly more nonsignificant P-values reported for tests of group differences in potentially confounding variables than the expected 95% (P = 0.005; N = 250 studies). This novel, to our knowledge, publication bias could result from selective reporting of nonsignificant results and/or from reverse P-hacking. We encourage others to test for a bias toward publishing nonsignificant results in the equivalent context in their own research discipline.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.028 | 0.004 |
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; both teacher heads 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".