Clustering performances in the NBA according to players’ anthropometric attributes and playing experience

Abstract

The aim of this study was: (i) to group basketball players into similar clusters based on a combination of anthropometric characteristics and playing experience; and (ii) explore the distribution of players (included starters and non-starters) from different levels of teams within the obtained clusters. The game-related statistics from 699 regular season balanced games were analyzed using a two-step cluster model and a discriminant analysis. The clustering process allowed identifying five different player profiles: Top height and weight (HW) with low experience, TopHW-LowE; Middle HW with middle experience, MiddleHW-MiddleE; Middle HW with top experience, MiddleHW-TopE; Low HW with low experience, LowHW-LowE; Low HW with middle experience, LowHW-MiddleE. Discriminant analysis showed that TopHW-LowE group was highlighted by two-point field goals made and missed, offensive and defensive rebounds, blocks, and personal fouls; whereas the LowHW-LowE group made fewest passes and touches. The players from weaker teams were mostly distributed in LowHW-LowE group, whereas players from stronger teams were mainly grouped in LowHW-MiddleE group; and players that participated in the finals were allocated in the MiddleHW-MiddleE group. These results provide alternative references for basketball staff concerning the process of evaluating performance.

Does Acute Beetroot Juice Supplementation Improve Neuromuscular Performance and Match Activity in Young Basketball Players? A Randomized, Placebo-Controlled Study

“…Although we did not find any differences regarding the players' specific position, it might be arguable that individual physical characteristics may influence their improvements. Particularly in team sports like basketball, players have well-defined roles that requires specific and distinctive physical attributes [32,33,56]; hence, a different response to BJ supplementation can be expected. In this sense, it can be arguable that athletic and explosive players (e.g., guards or forwards) would have greater benefits.…”

Design and Validation of an Observational Instrument for the Technical-Tactical Actions in Singles Tennis

“…One of the most determining factors in sports performance is the tactical technical analysis of the competition (Cui et al, 2018; Zhang et al, 2018). This type of analysis allows coaches to obtain information about the performance indicators, apart from knowing the weaknesses and strengths from their own and the adversaries, offering the possibility of improving training processes and therefore, increasing the possibilities of performance and success possibilities from the players (O'Donoghue and Ingram, 2001; Sainz De Baranda et al, 2008).…”

Sports potential modeling of young basketball players: a preliminary analysis

“…In addition, it was observed that the sports potential evaluated by coaches privileges athletes with larger body size and biologically more advanced. The sports potential classification of young athletes through multivariate techniques, such as cluster analysis, has aroused the interest of several researchers [14][15][16][17][18] . The use of multivariate statistical techniques allows the establishment of non-linear relationships between the various evaluations, presenting better capacity for the generalization of results, increasing the quality of the evaluation.…”

“…There is scientific evidence that the results obtained in test batteries for young athletes are able to predict sport success. Young people with above-average performance in tests tend to be the most successful in the future 16 and diagnosis using test batteries has shown greater prognostic capacity compared to coach's opinion 30 . In Switzerland, for example, a recent longitudinal study with young soccer players aged 12-15 years found that the most promising ones are not necessarily the best, but rather those who present above-average performance in physicomotor and skill tests consistently over the years, with emphasis on a holistic perspective in the selection of talents, that is, person-oriented 16 .…”

“…In this sense, the current understanding is that multidimensional and dynamic approach must be used to assess sports potential and select athletes 2,3,13 . For this, different multivariate statistical techniques such as discriminant analysis 13,14 , cluster analysis [15][16][17][18] , multiple linear regression 9,10 , multilevel regression models 12 and artificial neural networks 14 have been used for a better understanding of performance-relevant factors, classification of athletes and prediction of potential for certain modalities. Some authors have developed intelligent systems by means of statistical modeling in order to estimate the sports potential of young athletes 19 and even to guide players to game positions with greater probability of success 20 .…”