A method for extending the uncertainty paradigm to regression analysis is presented. The properties of the rankmeasure- based algorithm as applied to the classical parametric regression problem are analyzed. The rank measure algorithm is compared with other uncertainty recalculation algorithms and the classical criteria regression algorithms.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
E. V. Chernukho, Uncertainty principle in metrology and statistics: Algorithms and applications, J. Eng. Phys. Thermophys., 87, No. 2, 498–506 (2014).
E. V. Chernukho, Estimation of arbitrary-distribution parameters from the data of a repetitive experiment, J. Eng. Phys. Thermophys., 83, No. 2, 431–437 (2010).
E. V. Chernukho, Substantiation of the rank measure as an effi cient statistic for estimating parameters of distribution of arbitrary form, J. Eng. Phys. Thermophys., 85, No. 1, 239–248 (2012).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Inzhenerno-Fizicheskii Zhurnal, Vol. 88, No. 4, pp. 998–1008, July–August, 2015.
Rights and permissions
About this article
Cite this article
Chernukho, E.V. Regression Algorithm Using the Rank Measure. J Eng Phys Thermophy 88, 1034–1043 (2015). https://doi.org/10.1007/s10891-015-1282-7
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10891-015-1282-7