{"title":"综合检验和事后检验之间的关系:方差分析中F检验性能的调查。","authors":"Tian Chen, Manfei Xu, Justin Tu, Hongyue Wang, Xiaohui Niu","doi":"10.11919/j.issn.1002-0829.218014","DOIUrl":null,"url":null,"abstract":"<p><p>Comparison of groups is a common statistical test in many biomedical and psychosocial research studies. When there are more than two groups, one first performs an omnibus test for an overall difference across the groups. If this null is rejected, one then proceeds to the next step of post-hoc pairwise group comparisons to determine sources of difference. Otherwise, one stops and declares no group difference. A common belief is that if the omnibus test is significant, there must exist at least two groups that are significantly different and vice versa. Thus, when the omnibus test is significant, but no post-hoc between-group comparison shows significant difference, one is bewildered at what is going on and wondering how to interpret the results. At the end of the spectrum, when the omnibus test is not significant, one wonders if all post-hoc tests will be non-significant as well so that stopping after a nonsignificant omnibus test will not lead to any missed opportunity of finding group difference. In this report, we investigate this perplexing phenomenon and discuss how to interpret such results.</p>","PeriodicalId":21886,"journal":{"name":"上海精神医学","volume":"30 1","pages":"60-64"},"PeriodicalIF":0.0000,"publicationDate":"2018-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.11919/j.issn.1002-0829.218014","citationCount":"55","resultStr":"{\"title\":\"Relationship between Omnibus and Post-hoc Tests: An Investigation of performance of the F test in ANOVA.\",\"authors\":\"Tian Chen, Manfei Xu, Justin Tu, Hongyue Wang, Xiaohui Niu\",\"doi\":\"10.11919/j.issn.1002-0829.218014\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Comparison of groups is a common statistical test in many biomedical and psychosocial research studies. When there are more than two groups, one first performs an omnibus test for an overall difference across the groups. If this null is rejected, one then proceeds to the next step of post-hoc pairwise group comparisons to determine sources of difference. Otherwise, one stops and declares no group difference. A common belief is that if the omnibus test is significant, there must exist at least two groups that are significantly different and vice versa. Thus, when the omnibus test is significant, but no post-hoc between-group comparison shows significant difference, one is bewildered at what is going on and wondering how to interpret the results. At the end of the spectrum, when the omnibus test is not significant, one wonders if all post-hoc tests will be non-significant as well so that stopping after a nonsignificant omnibus test will not lead to any missed opportunity of finding group difference. In this report, we investigate this perplexing phenomenon and discuss how to interpret such results.</p>\",\"PeriodicalId\":21886,\"journal\":{\"name\":\"上海精神医学\",\"volume\":\"30 1\",\"pages\":\"60-64\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-02-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.11919/j.issn.1002-0829.218014\",\"citationCount\":\"55\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"上海精神医学\",\"FirstCategoryId\":\"95\",\"ListUrlMain\":\"https://doi.org/10.11919/j.issn.1002-0829.218014\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"上海精神医学","FirstCategoryId":"95","ListUrlMain":"https://doi.org/10.11919/j.issn.1002-0829.218014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Relationship between Omnibus and Post-hoc Tests: An Investigation of performance of the F test in ANOVA.
Comparison of groups is a common statistical test in many biomedical and psychosocial research studies. When there are more than two groups, one first performs an omnibus test for an overall difference across the groups. If this null is rejected, one then proceeds to the next step of post-hoc pairwise group comparisons to determine sources of difference. Otherwise, one stops and declares no group difference. A common belief is that if the omnibus test is significant, there must exist at least two groups that are significantly different and vice versa. Thus, when the omnibus test is significant, but no post-hoc between-group comparison shows significant difference, one is bewildered at what is going on and wondering how to interpret the results. At the end of the spectrum, when the omnibus test is not significant, one wonders if all post-hoc tests will be non-significant as well so that stopping after a nonsignificant omnibus test will not lead to any missed opportunity of finding group difference. In this report, we investigate this perplexing phenomenon and discuss how to interpret such results.
期刊介绍:
Shanghai archives of psychiatry (bimonthly) was founded in 1959 and is sponsored by Shanghai Mental Health Center. The journal is aimed at mental health workers across the country, including psychiatrists and nurses, clinical psychologists, social workers, and people who are committed to the cause of mental health. It focuses on reporting clinical research results and practical experience in the field of psychiatry, and introduces the latest knowledge in psychiatry and related fields. The columns include monographs, case reports, clinical case discussions, reviews, mental health and law, and debates and discussions.