FUNDAMENTAL-CONCEPTS IN STATISTICS - ELUCIDATION AND ILLUSTRATION

Fundamental concepts in statistics form the cornerstone of scientific inquiry. If we fail to understand fully these fundamental concepts, th en the scientific conclusions we reach are more likely to be wrong. Th is is more than supposition: for 60 years, statisticians have warned t hat the scientific literature harbors misunderstandings about basic st atistical concepts. Original articles published in 1996 by the America n Physiological Society's journals fared no better in their handling o f basic statistical concepts. In this review, we summarize the two mai n scientific uses of statistics: hypothesis testing and estimation. Mo st scientists use statistics solely for hypothesis testing; often, how ever, estimation is more useful. We also illustrate the concepts of va riability and uncertainty, and we demonstrate the essential distinctio n between statistical significance and scientific importance. An under standing of concepts such as variability, uncertainty, and significanc e is necessary, but it is not sufficient; we show also that the numeri cal results of statistical analyses have limitations.