Place of multivariate statistics in clinical physiological research
Volynskiĭ, I.D.; Kurochkina, A.I.
Kardiologiia 20(5): 88-91
1980
ISSN/ISBN: 0022-9040 PMID: 6993753 Document Number: 157561
On the basis of their own experience of many years in the use of mathematical methods in medicine the authors provide a critical analysis of the results of using computers in making the diagnosis and the main reasons for dissatisfaction with the results. Regarding clinico-physiological studies as a field for the application of modern mathematical statistics, they suggest a logical scheme which they had tested time and again for statistical analysis of the data by multidimensional methods (particularly with the use of the method of principal components, cluster analysis, latent analysis, lambda-moments, etc.) and also some methodological devices which permit keeping the data at hand throughout the entire analysis, resorting time and again to all possibilities for their complete and exhaustive description. The position of the authors in principle consists in the fact that success can only be achieved by constant joint work of the medical specialist and mathematician, beginning with the first stage of formulating both the medical and statistical tasks on condition that the clinico-physiological essence of the problem is comprehended by the mathematician.