A Comment on “Beyond P-value: the Rigor and Power of Study"
- 18 December 2019
- journal article
- Published by Global Clinical and Translational Research Institute in Global Clinical and Translational Research
Abstract
“As ye sow. So shall ye reap”: For almost 100 years, researchers have been taught that the be-all and end-all in data-based research is the p-value. The resulting problems have now generated concern, often from us who have long so taught researchers. We must bear a major responsibility for the present situation and must alter our teachings. Despite the fact that the Zhang and Hughes paper is titled “Beyond p-value”, the total focus remains on statistical hypothesis testing studies (HTS) and p-values(1). Instead, I would propose that there are three distinct, necessary, and important phases of research: 1) Hypothesis Generation Studies (HGS) or Exploratory Research (2-4); 2) Hypothesis Testing Studies (HTS); 3) Replication and Application of Results. Of these, HTS is undoubtedly the most important, but without HGS, HTS is often weak and wasteful, and without Replication and Application, the results of HTS are often misleading.Keywords
This publication has 12 references indexed in Scilit:
- Beyond p-value: the Rigor and Power of StudyGlobal Clinical and Translational Research, 2019
- “Not just another meta‐analysis”: Sources of heterogeneity in psychosocial treatment effect on cancer survivalCancer Medicine, 2019
- The Mass Production of Redundant, Misleading, and Conflicted Systematic Reviews and Meta‐analysesThe Milbank Quarterly, 2016
- How Many Subjects?: Statistical Power Analysis in ResearchPublished by SAGE Publications ,2016
- A deficiency of the odds ratio as a measure of effect sizeStatistics in Medicine, 2006
- Why Most Published Research Findings Are FalsePLoS Medicine, 2005
- Contradicted and Initially Stronger Effects in Highly Cited Clinical ResearchJAMA, 2005
- Principles and procedures of exploratory data analysis.Psychological Methods, 1997
- Exploratory statistical methods, with applications to psychiatric researchPsychoneuroendocrinology, 1992
- Vote-counting methods in research synthesis.Psychological Bulletin, 1980