THE PURPOSE of therapy is to improve the patient's well-being or expectation of well-being. Each piece of therapy, whether allegedly rational or frankly empirical, represents an experiment in that one or more factors affecting the patient's well-being are changed deliberately. In well-designed experiments the results can be interpreted with reasonable clarity; ill-designed experiments yield nothing to the critical investigator.
A major difficulty facing every scientist is that of variability. This is least in the physical sciences, yet even in them it is now fully appreciated that the fundamental laws are laws of probability. In biology the extent of variation is much greater and perhaps reaches its acme in man with his complicated patterns of migration and the extraordinary diversity of his environment. To find one's way through this mass of variability the science of statistics has been introduced. "By statistics... we mean 'quantitative data affected to a marked extent
Pears MA, Pckering GW. Antihypertensive Drug TherapyAnother Appraisal. Arch Intern Med. 1965;115(5):526–528. doi:10.1001/archinte.1960.03860170008003
Customize your JAMA Network experience by selecting one or more topics from the list below.