Table 2.
P-hacking | · Checking the statistical significance of results before deciding whether to collect more data |
· Stopping data collection early because results reached statistical significance | |
· Deciding whether to exclude data points (e.g., outliers) only after foreshadowing the impact on statistical significance and not reporting the impact of the data exclusion | |
Rounding off a p value to meet a statistical significance threshold (e.g., presenting 0.053 as P < .05) | |
Cherry-picking | · Failing to report dependent or response variables or relationships that did not reach statistical significance or other threshold |
· Failing to report conditions or treatments that did not reach statistical significance or other threshold | |
HARKing (hypothesizing after the results are known) | Presenting a post hoc finding as though it had been hypothesized all along |