不需要p值。“暴雷酒渣鼻:一种以抗炎为基础的治疗方法”分析决策评论

Yung Gonzaga, Ana Luísa Sampaio
{"title":"不需要p值。“暴雷酒渣鼻:一种以抗炎为基础的治疗方法”分析决策评论","authors":"Yung Gonzaga,&nbsp;Ana Luísa Sampaio","doi":"10.1002/jvc2.533","DOIUrl":null,"url":null,"abstract":"<p>We read with interest the study by Handgretinger and colleagues entitled <i>Rosacea Fulminans: An Anti-inflammatory-based Therapeutic Approach</i>,<span><sup>1</sup></span> and although the topic addressed is of great clinical relevance, the presentation of the results, particularly concerning the choice of the statistical test, warrants discussion.</p><p>The study tracked the evolution of the skin condition in six6 patients diagnosed with Rosacea fulminans before and after treatment with azithromycin. According to the methodological section, a <i>t</i> test for independent samples was used to compare the before and after treatment. This choice seems inappropriate to us, as it overlooks some fundamental assumptions in selecting statistical tests that assess the association between two variables.<span><sup>2, 3</sup></span></p><p>The first issue concerns the independence between observations: The ‘before’ and ‘after’ measurements for the same individual are dependent, as they are related to the same subject. The independent samples <i>t</i> test assumes that the observations in each group are independent, which is not the case here.</p><p>The second issue concerns the nature of the variable being studied. The Clinical Erythema Assessment (CEA), for example, is an ordinal categorical variable. For instance, on a scale from 0 to 4, as in this case, the differences between ‘0 and 1’ may not represent the same quantitative change as a difference between ‘3 and 4.’ The <i>t</i> test assumes that the data are numbers, meaning that the differences between the values are consistent and quantifiable. For example, the difference between ages 25 and 20 is the same as the difference between 37 and 32, which is 5 years. The <i>t</i> test works with numerical variables, making it inappropriate for dealing with categorical variables, even if they are represented by numbers and have a natural order.</p><p>The third issue pertains to the necessity of a statistical test at all. In this regard, we would like to emphasize that the reason for writing this letter is not merely to criticize the choice of the statistical test, but to highlight that the value of a study like this should not rely on statistical significance. It is much more related to the descriptive and visual nature capable of creating a clear sensorial perception of clinical benefit and generating a relevant hypothesis to be explored more thoroughly in future studies.<span><sup>4</sup></span> In this regard, in our opinion, the study by Handgretinger and colleagues achieves the goal. It is a beautiful and illustrative case series that does not need <i>p</i> values to demonstrate its importance.</p><p>Yung Gonzaga conceived and wrote the article. Ana Luísa Sampaio wrote and reviewed the article.</p><p>The authors declare no conflict of interest.</p><p>Not applicable.</p>","PeriodicalId":94325,"journal":{"name":"JEADV clinical practice","volume":"3 5","pages":"1711-1712"},"PeriodicalIF":0.0000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jvc2.533","citationCount":"0","resultStr":"{\"title\":\"No need for a p value. Comments on analytical decisions in “Rosacea fulminas: An anti-inflammatory-based therapeutic approach”\",\"authors\":\"Yung Gonzaga,&nbsp;Ana Luísa Sampaio\",\"doi\":\"10.1002/jvc2.533\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>We read with interest the study by Handgretinger and colleagues entitled <i>Rosacea Fulminans: An Anti-inflammatory-based Therapeutic Approach</i>,<span><sup>1</sup></span> and although the topic addressed is of great clinical relevance, the presentation of the results, particularly concerning the choice of the statistical test, warrants discussion.</p><p>The study tracked the evolution of the skin condition in six6 patients diagnosed with Rosacea fulminans before and after treatment with azithromycin. According to the methodological section, a <i>t</i> test for independent samples was used to compare the before and after treatment. This choice seems inappropriate to us, as it overlooks some fundamental assumptions in selecting statistical tests that assess the association between two variables.<span><sup>2, 3</sup></span></p><p>The first issue concerns the independence between observations: The ‘before’ and ‘after’ measurements for the same individual are dependent, as they are related to the same subject. The independent samples <i>t</i> test assumes that the observations in each group are independent, which is not the case here.</p><p>The second issue concerns the nature of the variable being studied. The Clinical Erythema Assessment (CEA), for example, is an ordinal categorical variable. For instance, on a scale from 0 to 4, as in this case, the differences between ‘0 and 1’ may not represent the same quantitative change as a difference between ‘3 and 4.’ The <i>t</i> test assumes that the data are numbers, meaning that the differences between the values are consistent and quantifiable. For example, the difference between ages 25 and 20 is the same as the difference between 37 and 32, which is 5 years. The <i>t</i> test works with numerical variables, making it inappropriate for dealing with categorical variables, even if they are represented by numbers and have a natural order.</p><p>The third issue pertains to the necessity of a statistical test at all. In this regard, we would like to emphasize that the reason for writing this letter is not merely to criticize the choice of the statistical test, but to highlight that the value of a study like this should not rely on statistical significance. It is much more related to the descriptive and visual nature capable of creating a clear sensorial perception of clinical benefit and generating a relevant hypothesis to be explored more thoroughly in future studies.<span><sup>4</sup></span> In this regard, in our opinion, the study by Handgretinger and colleagues achieves the goal. It is a beautiful and illustrative case series that does not need <i>p</i> values to demonstrate its importance.</p><p>Yung Gonzaga conceived and wrote the article. Ana Luísa Sampaio wrote and reviewed the article.</p><p>The authors declare no conflict of interest.</p><p>Not applicable.</p>\",\"PeriodicalId\":94325,\"journal\":{\"name\":\"JEADV clinical practice\",\"volume\":\"3 5\",\"pages\":\"1711-1712\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jvc2.533\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JEADV clinical practice\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/jvc2.533\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JEADV clinical practice","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/jvc2.533","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

我们饶有兴趣地阅读了Handgretinger及其同事的研究,题为“红斑痤疮:一种基于抗炎的治疗方法”,尽管该主题具有重大的临床相关性,但结果的呈现,特别是关于统计检验的选择,值得讨论。该研究追踪了6名被诊断为暴发性红斑痤疮的患者在阿奇霉素治疗前后皮肤状况的演变。根据方法学部分,使用独立样本的t检验来比较治疗前后。这种选择对我们来说似乎是不合适的,因为它忽略了在选择评估两个变量之间关联的统计检验时的一些基本假设。第一个问题涉及观察之间的独立性:同一个人的“之前”和“之后”测量是依赖的,因为它们与同一主体有关。独立样本t检验假设每组的观测值是独立的,但这里不是这样。第二个问题涉及所研究变量的性质。例如,临床红斑评估(CEA)是一个有序的分类变量。例如,在从0到4的范围内,在这种情况下,“0和1”之间的差异可能与“3和4”之间的差异所代表的数量变化不同。t检验假设数据是数字,这意味着值之间的差异是一致的和可量化的。例如,25岁和20岁之间的差距与37岁和32岁之间的差距相同,相差5年。t检验适用于数值变量,因此不适合处理分类变量,即使它们由数字表示并且具有自然顺序。第三个问题与统计检验的必要性有关。在这方面,我们要强调的是,写这封信的原因不仅仅是批评统计检验的选择,而是要强调这样的研究的价值不应该依赖于统计显著性。它更多地与描述性和视觉性有关,能够创造一个清晰的临床益处感官知觉,并产生一个相关的假设,在未来的研究中进行更彻底的探索在这方面,我们认为Handgretinger及其同事的研究达到了目的。这是一个漂亮的和说明性的案例系列,不需要p值来证明它的重要性。Yung Gonzaga构思并撰写了这篇文章。Ana Luísa Sampaio撰写并评论了这篇文章。作者声明无利益冲突。不适用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
No need for a p value. Comments on analytical decisions in “Rosacea fulminas: An anti-inflammatory-based therapeutic approach”

We read with interest the study by Handgretinger and colleagues entitled Rosacea Fulminans: An Anti-inflammatory-based Therapeutic Approach,1 and although the topic addressed is of great clinical relevance, the presentation of the results, particularly concerning the choice of the statistical test, warrants discussion.

The study tracked the evolution of the skin condition in six6 patients diagnosed with Rosacea fulminans before and after treatment with azithromycin. According to the methodological section, a t test for independent samples was used to compare the before and after treatment. This choice seems inappropriate to us, as it overlooks some fundamental assumptions in selecting statistical tests that assess the association between two variables.2, 3

The first issue concerns the independence between observations: The ‘before’ and ‘after’ measurements for the same individual are dependent, as they are related to the same subject. The independent samples t test assumes that the observations in each group are independent, which is not the case here.

The second issue concerns the nature of the variable being studied. The Clinical Erythema Assessment (CEA), for example, is an ordinal categorical variable. For instance, on a scale from 0 to 4, as in this case, the differences between ‘0 and 1’ may not represent the same quantitative change as a difference between ‘3 and 4.’ The t test assumes that the data are numbers, meaning that the differences between the values are consistent and quantifiable. For example, the difference between ages 25 and 20 is the same as the difference between 37 and 32, which is 5 years. The t test works with numerical variables, making it inappropriate for dealing with categorical variables, even if they are represented by numbers and have a natural order.

The third issue pertains to the necessity of a statistical test at all. In this regard, we would like to emphasize that the reason for writing this letter is not merely to criticize the choice of the statistical test, but to highlight that the value of a study like this should not rely on statistical significance. It is much more related to the descriptive and visual nature capable of creating a clear sensorial perception of clinical benefit and generating a relevant hypothesis to be explored more thoroughly in future studies.4 In this regard, in our opinion, the study by Handgretinger and colleagues achieves the goal. It is a beautiful and illustrative case series that does not need p values to demonstrate its importance.

Yung Gonzaga conceived and wrote the article. Ana Luísa Sampaio wrote and reviewed the article.

The authors declare no conflict of interest.

Not applicable.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
0.30
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信