Novel approach for statistical inference in survival analysis based on factor or dichotomic variables is proposed. We are seeking for the most informative finitely linear combinations (symptoms) of variables in the finite field. This procedure necessarily yields the new variable of the same nature (e.g. factor). Different measures can be used as an optimality criterion of such combination: entropy, the uncertainty coefficient, p-level of some statistical tests. We use this method to determine the major factors of the glioma postoperation survival. These factors were found to be age, high-grading factor, stage of illness and a factor of the stereotactic cryodestruction.

Abstract-The calculation of variables of one metering type by the variables of others metering types as the process leads to the forms of logic which are described by means of the collineation group of the projective geometry. Missing metering types are replaced with the appropriate logic principles. The logic of sufficiency (preferences) on the basis of orders and the logic principle of duality is considered in detail on an RNA connectivity analysis example. The minimal sum of diagonal elements in the cross-tabulation of two finitely-linear combinations (symptoms) of fragments which differ by a shift on the given quantity of symbols is chosen as a relation between two dichotomizing series. If this relation is zero then correct classification takes place. In this paper the probability of random classification with given number of errors is estimated. Logic principle of duality allows to distinguish between weak and strong statistically significant relations.

No abstract

RETRACTION NOTE This article has been retracted by the publisher as a duplicate translation of one and the same Rus sian article. The original translation is entitled "A discrete optimization method based on a parame terization of a Grassmannian in multidimensional dichotomous data structuring" and published

No abstract