These datasets come from two independent studies using wearable inertial sensors to estimate countermovement jump performance. The participants were healthy sports science students, free of injury, all of whom had given their prior written consent. Ethical approval was given by the governing institutions’ ethics committees, which included further analysis of the data. Smartphone Dataset: 119 valid jumps Peak power 40.7 +/- 8.9 W/kg 22 males, 10 females (26.5 +/- 4.1 yrs; standing height 1.74 +/- 0.08 m; body mass 70.0 +/- 10.9 kg) Redmi 9T phone (Xiaomi Technology, Beijing, China) 128 Hz sampling frequency Accelerometer & gyroscope Handheld at sternum level Mascia, G.; De Lazzari, B.; Camomilla, V. Machine learning aided jump height estimate democratization through smartphone measures. Frontiers in Sports and Active Living 2023, 5, 1112739. https://doi.org/10.3389/fspor.2023.1112739. Accelerometer Dataset: 347 valid jumps Peak power 45.1 +/- 7.6 W/kg 48 males, 25 females (21.6 +/- 3.3 yrs; standing height 1.75 +/- 0.10 m; body mass 71.2 +/- 15.1 kg) Trigno sensor (Delsys Inc, MA, USA) 250 Hz sampling frequency Accelerometer Taped to lower back (L4) White, M.G.E.; Bezodis, N.E.; Neville, J.; Summers, H.; Rees, P. Determining jumping performance from a single body-worn accelerometer using machine learning. PLOS ONE 2022, 17, e0263846. https://doi.org/10.1371/journal.pone.0263846 MATLAB .mat files This repository was used by the paper currently under review for the open journal Mathematics: White, M.; De Lazzari, B.; Bezodis, N., Camomilla, V. Title. Mathematics 2024, 1, 0. Wearable Sensors for Athletic Performance: A Comparison of Discrete and Continuous Feature Extraction Methods for Prediction Models