Biology of Sport
pISSN 0860-021X    eISSN 2083-1862
Archival Issues
Volume 34, 2017
Volume 33, 2016
Volume 32, 2015
Volume 31, 2014
Volume 30, 2013
Volume 29, 2012
Volume 28, 2011
Volume 27, 2010
Volume 26, 2009
Volume 25, 2008
Volume 24, 2007
Volume 23, 2006
Volume 22, 2005
Volume 21, 2004
Volume 20, 2003
Archival Issues 1984-1998
Information for Authors
Special Information
Journal Abstract
Regression shrinkage and neural models in predicting the results of 400-metres hurdles races
Krzysztof Przednowek, Janusz Iskra, Adam Maszczyk, Monika Nawrocka
Biol Sport 2016; 33(4):415-421
ICID: 1224463
Article type: Original article
IC™ Value: 10.00
Abstract provided by Publisher
This study presents the application of regression shrinkage and artificial neural networks in predicting the results of 400-metres hurdles races. The regression models predict the results for suggested training loads in the selected three-month training period. The material of the research was based on training data of 21 Polish hurdlers from the Polish National Athletics Team Association. The athletes were characterized by a high level of performance. To assess the predictive ability of the constructed models a method of leave-one-out cross-validation was used. The analysis showed that the method generating the smallest prediction error was the LASSO regression extended by quadratic terms. The optimal model generated the prediction error of 0.59 s. Otherwise the optimal set of input variables (by reducing 8 of the 27 predictors) was defined. The results obtained justify the use of regression shrinkage in predicting sports outcomes. The resulting model can be used as a tool to assist the coach in planning training loads in a selected training period.

ICID 1224463

DOI 10.5604/20831862.1224463

Related articles
  • in IndexCopernicus™
         Neural Modeling [0 related records]
         regression shrinkage [0 related records]
         400-metres hurdles [0 related records]
         predicting in sport [0 related records]


    Copyright © Biology of Sport  2017
    Page created by Index Copernicus Ltd. All Rights reserved.