Stahel 2021 PLOS ONE: Difference between revisions
(Created page with "{{Publication |title=Stahel WA (2021) New relevance and significance measures to replace p-values. PLOS ONE 16:e0252991. https://doi.org/10.1371/journal.pone.0252991. |info=[h...") ย |
No edit summary ย |
||
Line 7: | Line 7: | ||
|abstract=The ''p''-value has been debated exorbitantly in the last decades, experiencing fierce critique, but also finding some advocates. The fundamental issue with its misleading interpretation stems from its common use for testing the unrealistic null hypothesis of an effect that is precisely zero. A meaningful question asks instead whether the effect is relevant. It is then unavoidable that a threshold for relevance is chosen. Considerations that can lead to agreeable conventions for this choice are presented for several commonly used statistical situations. Based on the threshold, a simple quantitative measure of relevance emerges naturally. Statistical inference for the effect should be based on the confidence interval for the relevance measure. A classification of results that goes beyond a simple distinction like โsignificant / non-significantโ is proposed. On the other hand, if desired, a single number called the โsecured relevanceโ may summarize the result, like the ''p''-value does it, but with a scientifically meaningful interpretation. | |abstract=The ''p''-value has been debated exorbitantly in the last decades, experiencing fierce critique, but also finding some advocates. The fundamental issue with its misleading interpretation stems from its common use for testing the unrealistic null hypothesis of an effect that is precisely zero. A meaningful question asks instead whether the effect is relevant. It is then unavoidable that a threshold for relevance is chosen. Considerations that can lead to agreeable conventions for this choice are presented for several commonly used statistical situations. Based on the threshold, a simple quantitative measure of relevance emerges naturally. Statistical inference for the effect should be based on the confidence interval for the relevance measure. A classification of results that goes beyond a simple distinction like โsignificant / non-significantโ is proposed. On the other hand, if desired, a single number called the โsecured relevanceโ may summarize the result, like the ''p''-value does it, but with a scientifically meaningful interpretation. | ||
|editor=Gnaiger E | |editor=Gnaiger E | ||
}} | }} |
Latest revision as of 08:27, 11 October 2021
Stahel WA (2021) New relevance and significance measures to replace p-values. PLOS ONE 16:e0252991. https://doi.org/10.1371/journal.pone.0252991. |
ยป Open Access
Stahel Werner A (2021) PLOS ONE
Abstract: The p-value has been debated exorbitantly in the last decades, experiencing fierce critique, but also finding some advocates. The fundamental issue with its misleading interpretation stems from its common use for testing the unrealistic null hypothesis of an effect that is precisely zero. A meaningful question asks instead whether the effect is relevant. It is then unavoidable that a threshold for relevance is chosen. Considerations that can lead to agreeable conventions for this choice are presented for several commonly used statistical situations. Based on the threshold, a simple quantitative measure of relevance emerges naturally. Statistical inference for the effect should be based on the confidence interval for the relevance measure. A classification of results that goes beyond a simple distinction like โsignificant / non-significantโ is proposed. On the other hand, if desired, a single number called the โsecured relevanceโ may summarize the result, like the p-value does it, but with a scientifically meaningful interpretation.
โข Bioblast editor: Gnaiger E