A Comment on “Beyond P-value: The Rigor and Power of Study”
Helena Chmura Kraemer
“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.