Data upwards excursion algorithm in estimating of parameters of multiple linear regression
Abstract
Data upwards excursion algorithm in estimating of parameters of multiple linear regression
Incoming article date: 28.05.2019This article presents the results which purpose of cases of intentional distortion of "objective" ratings based on individual indicators. The aim of the study was to build an algorithm for determining unfairly placed places in the ranking as a result of manual adjustment. The main tool is the identification of the weight coefficients of private ratings with a known form of the functional dependence of the overall rating. The analysis of techniques of creation of one of popular Russian ratings was for this purpose carried out, mathematical models of dependence of the general rating of higher education institution on its private ratings are received. It was revealed the presence of subjectivity in the construction of the rating, which manifests itself in the form of an unfair score. Standard methods do not allow to reveal such non-random "emissions" and do not provide an objective assessment. The offered algorithm allows to find such "emissions", to exclude them from selection and define fair values. The offered algorithm can be useful for heads of universities to check the correctness of the occupied place in the ranking of their organization and understanding of their real position among other universities.
Keywords: statistical analysis, multiple linear regression, ordinary least squares, approximation, rankings, indicators, higher education