SEVERAL WRITERS have deplored recently the lack of technical preparation behind much of contemporary clinical research.1-3 On the other hand, the difficulty often seems to be that of the same general nature which may divide a staff conference or a society meeting. It is not so much the marshalling of evidence as it is the use of common sense in interpretation. This point may be illustrated by the controversy over BCG vaccination. There seems to be nothing wrong with the statistical analysis on either side of the question, but statistics are of much less importance than the conclusions which may be drawn legitimately with reference to the same figures. Technical skill in compiling the evidence may help evolve a decision, but the decision is made by the rules of common sense.
There are also rules of common sense inherent in statistical methods, rules derived either from the mathematical theory
Hawkins NG. A Note on Statistical Usage. JAMA. 1961;175(3):236–237. doi:10.1001/jama.1961.63040030006017
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: