Analytics
What 15,661 hedged sentences look like in aggregate. The numbers below count sentences, not papers, because a paper that hedges four times is doing something four times.
The distribution
60.9% of the p-values quoted here fall in the narrow strip between 0.05 and 0.1. That strip is 5% of the probability scale.
Hedging over time
Bars are sentences per year; the line is the median p-value they reported. Note that the upward slope of the bars is mostly the growth of open-access publishing, not a decline in scientific virtue.
The leaderboard
Ranked by how often each phrasing appears. “Worst offender” is the largest p-value any paper described with that phrase, which is the single best measure of nerve.
| Phrase | Sentences | Median p | Closest | Worst offender |
|---|---|---|---|---|
| only marginally significantgold | 3,408 | 0.063 | 0.0001 | 0.610 |
| quite significantgold | 3,374 | 0.009 | 0.0000 | 0.093 |
| nearly significantgold | 2,281 | 0.059 | 0.0000 | 0.890 |
| moderately significantgold | 1,498 | 0.015 | 0.0000 | 0.710 |
| might be significantgold | 1,478 | 0.058 | 0.0003 | 0.250 |
| slightly significantgold | 1,025 | 0.047 | 0.0000 | 0.480 |
| not quite significantgold | 451 | 0.060 | 0.0001 | 0.649 |
| might not be significantgold | 411 | 0.062 | 0.0619 | 0.062 |
| not yet significantgold | 206 | 0.067 | 0.0500 | 0.143 |
| more or less significantgold | 185 | 0.021 | 0.0060 | 0.035 |
| probably not significantgold | 175 | — | — | — |
| not significantly significantgold | 113 | 0.133 | 0.0500 | 0.998 |
| modest significancegold | 111 | 0.043 | 0.0000 | 0.200 |
| hardly significantgold | 109 | 0.069 | 0.0400 | 0.190 |
| probable significancegold | 86 | 0.050 | 0.0010 | 0.100 |
| a tendency toward statistical significancegold | 71 | 0.062 | 0.0380 | 0.131 |
| slight significancegold | 63 | 0.043 | 0.0105 | 0.058 |
| a trend level of significancegold | 52 | 0.074 | 0.0500 | 0.340 |
| a trend approaching significancegold | 52 | 0.066 | 0.0500 | 0.113 |
| significantly not differentgold | 52 | 0.123 | 0.0100 | 0.884 |
| a slight significancegold | 46 | 0.044 | 0.0100 | 0.900 |
| partial significancegold | 42 | 0.050 | 0.0010 | 0.100 |
| at the edge of significancegold | 35 | 0.058 | 0.0500 | 0.081 |
| not strictly significantgold | 33 | 0.070 | 0.0510 | 0.110 |
| a weakly significant differencegold | 33 | 0.049 | 0.0120 | 0.100 |
| noticeably significantgold | 32 | 0.004 | 0.0010 | 0.031 |
| completely significantgold | 27 | 0.006 | 0.0000 | 0.067 |
| closer to significancegold | 26 | 0.105 | 0.0070 | 0.428 |
| essentially significantgold | 25 | 0.053 | 0.0530 | 0.053 |
| almost not significantgold | 17 | 0.051 | 0.0100 | 0.085 |
By journal
Journals with at least 20 hedged sentences. A journal with one is not the most hedging journal in science, so the floor is there on purpose. Volume mostly tracks how much a journal publishes.
| Journal | Sentences | Papers | Median p |
|---|---|---|---|
| PLoS One | 1,593 | 1,577 | 0.060 |
| Sci Rep | 777 | 768 | 0.053 |
| Front Psychol | 376 | 375 | 0.063 |
| Int J Mol Sci | 198 | 197 | 0.054 |
| Cureus | 152 | 150 | 0.050 |
| Heliyon | 151 | 147 | 0.050 |
| Sensors (Basel) | 144 | 143 | 0.050 |
| Nat Commun | 141 | 140 | 0.055 |
| Ecol Evol | 131 | 130 | 0.060 |
| J Clin Med | 113 | 113 | 0.053 |
| BMC Public Health | 111 | 110 | 0.057 |
| Int J Environ Res Public Health | 104 | 103 | 0.060 |
| Front Hum Neurosci | 101 | 100 | 0.062 |
| Materials (Basel) | 91 | 90 | 0.053 |
| Nutrients | 90 | 90 | 0.054 |
| BMC Genomics | 89 | 85 | 0.050 |
| Medicine (Baltimore) | 89 | 89 | 0.060 |
| Br J Cancer | 84 | 83 | 0.060 |
| Elife | 81 | 80 | 0.057 |
| Front Plant Sci | 77 | 76 | 0.067 |
Most persistent papers
Papers that hedge the most times in a single manuscript.