Inference by Eye¶
Cumming, G., & Finch, S. (2005). Inference by Eye: Confidence Intervals and How to Read Pictures of Data. American Psychologist, 60(2), 170-180.
Cited by¶
3 citations across 3 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Confidence Intervals
- Additional canonical references in this cluster: ,
This sourceGuidance on visual/graphical interpretation of confidence intervals, including overlap rules for comparing means. DOI live-confirmed to resolve this session.
- Additional canonical references in this cluster: ,
Mechanisms¶
- Error Bar, Confidence Band, or Quality Flag
- Its most seductive failure mode is the overlapping-intervals fallacy run in reverse: people assume two error bars that overlap are never significantly different and two that don't always are — both are wrong, because the correct comparison is on the difference's interval, not the two individual bars.
This sourceExplains that overlap or non-overlap of two separate confidence intervals is not itself a valid test of their difference; inference must be based on the uncertainty of the difference.
- Its most seductive failure mode is the overlapping-intervals fallacy run in reverse: people assume two error bars that overlap are never significantly different and two that don't always are — both are wrong, because the correct comparison is on the difference's interval, not the two individual bars.
- Paired Confidence-Band Review
- Its failure modes are paralysis, when nothing ever clears the band, and the confidence-interval overlap fallacy, where analysts declare "no difference" merely because two separate intervals overlap — which is not a valid test, since the difference can be significant even when the individual intervals touch
This sourceShows that overlap of separate confidence intervals is not itself a valid no-difference test and that a statistically significant difference can occur despite substantial interval overlap.
- Its failure modes are paralysis, when nothing ever clears the band, and the confidence-interval overlap fallacy, where analysts declare "no difference" merely because two separate intervals overlap — which is not a valid test, since the difference can be significant even when the individual intervals touch
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Not recorded. Neither this nor any other of the 3 citations of this work carries a recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:23d264b6e186 · see in the full table