Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, USA.
Department of Psychiatry, University of California, San Diego, USA.
J Sports Sci. 2024 Apr;42(8):720-727. doi: 10.1080/02640414.2024.2363679. Epub 2024 Jun 4.
A key focus of sports science research is the identification of quantitative assessments that can predict players' on-field performance and developmental potential. Despite efforts to establish predictive models, there are few validated measures that show reliable associations and large gaps in understanding. Here, we test a multidimensional battery of assessments developed through the USA Baseball, Prospect Development Pipeline that capture strength and functional movement abilities, and anthropometric characteristics, in a two-year cohort of collegiate baseball players from the Appalachian League. Swing propensity metrics for Zone Contact Percentage (ZCP: proportion pitches in strike zone swung at and hit) and Hard-Hit Percentage (HHP: proportion in-play balls with exit velocity ≥ 95 mph) were calculated on 189 players. Models testing hierarchical combinations of anthropometric and anthropometric plus assessment data were implemented using nested cross-validation with random forest and elastic net regression. Results indicate that anthropometric features account for 29% of variance in ZCP and 50-55% of HHP, while the addition of assessment contributed an additional 1-3% to ZCP and 5-12% to HHP, with top predictors coming from PDP strength and power assessments. These findings delineate contributions of andromorphic and physical abilities to in-game baseball performance using a validated assessment battery and advanced game statistics.
运动科学研究的一个重点是确定能够预测运动员场上表现和发展潜力的定量评估方法。尽管已经做出了努力来建立预测模型,但很少有经过验证的测量方法能够显示出可靠的关联和理解上的巨大差距。在这里,我们测试了一个通过美国职棒大联盟(USA Baseball)开发的多维评估工具包,该工具包在阿巴拉契亚联盟(Appalachian League)的两年期大学生棒球运动员中,捕捉力量和功能性运动能力以及人体测量特征。针对区域接触百分比(Zone Contact Percentage,ZCP:在击球区挥棒并击中的比例)和强击百分比(Hard-Hit Percentage,HHP:球速≥95 英里/小时的比赛球比例),我们对 189 名球员进行了计算。使用嵌套交叉验证和随机森林以及弹性网络回归,测试了基于人体测量特征和人体测量特征加评估数据的分层组合模型。结果表明,人体测量特征可以解释 ZCP 变异的 29%和 HHP 的 50-55%,而评估的加入可以为 ZCP 增加 1-3%,为 HHP 增加 5-12%,其中来自 PDP 力量和功率评估的预测因素最为重要。这些发现使用经过验证的评估工具包和先进的比赛统计数据,阐明了两性体和物理能力对比赛中棒球表现的贡献。