当前位置: X-MOL 学术Estuar. Coasts › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Ending Reliance on Statistical Significance Will Improve Environmental Inference and Communication
Estuaries and Coasts ( IF 2.7 ) Pub Date : 2019-12-16 , DOI: 10.1007/s12237-019-00679-y
Eric P. Smith

Recently, there has been much discussion about the role of the p-value in scientific research. The American Statistical Association has published an editorial that presents guidelines for the use and interpretation of p-values. Numerous authors have commented and criticized its use as a means to identify scientific importance of results and have called for an end to using the term “statistical significance.” Recent articles in Estuaries and Coasts were evaluated for reliance on the use of statistical significance and reporting errors were identified. Suggestions are made for improving what is reported related to statistical testing. Focus should be on scientific importance of estimates, estimation of the size of the effect and the certainty in the size of the effect instead of simply reporting a p-value and relying on hypothesis tests.

中文翻译:

不再依赖于统计意义将改善环境推断和交流

最近,关于p值在科学研究中的作用已进行了很多讨论。美国统计协会发表了一篇社论,介绍了p值的使用和解释准则。许多作者评论和批评了将其用作确定结果的科学重要性的方法,并呼吁终止使用“统计意义”一词。河口和海岸的最新文章评估对统计意义使用的依赖,并确定报告错误。提出了一些建议以改进与统计测试有关的报告。重点应放在估算的科学重要性,效应大小的估计以及效应大小的确定性上,而不是简单地报告p值并依靠假设检验。
更新日期:2019-12-16
down
wechat
bug