REGRESSION ALGORITHMS IN ASSESSING THE IMPACT OF MORPHOLOGICAL AND MOTOR CHARACTERISTICS ON 60-M SPRINT

Abstract

The aim of the present study was to identify the relationship between morphological parameters and motor skills that are important for sprint performance in children aged 8 to 16 years divided into four age groups (U10, U12, U14, U16) in both genders. The sample consisted of two hundred eighty one participant who trained sprinting in various athletic clubs. A prediction set of twenty-five variables for assessing morphological characteristics and motor skills was applied, and the criterion variable was a sprint at 60m. Using multiple correlation, it has been established that a large number of morphological characteristics are statistically significant positive correlation with the sprint, especially the longitudinal variables, while the variables of skinfolds showed a low negative statistical significance in relation to the given criterion. In the field of motor skills, the highest number of positive statistically significant correlations were found in the tests of explosive power of the upper and lower extremities, agility test and horizontal and vertical jump tests. In order to determine which morphological features and motor skills should be applied in sprint running training, we tested related attributes using different algorithms for data mining (LR, M5, KNN, SVM, MLP, RBF). The results suggests that the predictors that we use can continue to be applied with high reliability in assessing sprint performance, but also in the monitoring of the training process in order to profile the better sprint achievements.