Portal de Periódicos da CAPES

Effect measure for quantitative endpoints: Statistical versus clinical significance, or “how large the scale is?”

2008; Elsevier BV; Volume: 20; Issue: 5 Linguagem: Inglês

10.1016/j.ejim.2008.10.002

1879-0828

Cristian Băicuş, Simona Caraiola,

Meta-analysis and systematic reviews

Frequently when a study finds a statistical significance for the difference between treatment and placebo, the scientific society of the respective specialty introduces this new treatment in its guidelines [ [1] Baicus C. Chivu R. Drug politics — economic viewpoint of a practitioner. Rev Med Chir Soc Med Nat Iasi. 2004; 108 ([French]): 674-678 PubMed Google Scholar ], leaving apart the intense promotion by the pharmaceutical industry. However, we must always ask ourselves if the differences detected in continuous variables-endpoints with the tested treatment is clinically important. In order to do this, we need to know at least how large is the scale and how clinically significant is the treatment effect.