Elite Youth Soccer Players Research Articles

Exploring the associations between ankle dorsal and plantar flexion strength, reactive strength index, and balance in elite youth soccer players

Exploring the associations between ankle dorsal and plantar flexion strength, reactive strength index, and balance in elite youth soccer players

Comparison of Metabolic Power and Energy Cost of Submaximal and Sprint Running Efforts Using Different Methods in Elite Youth Soccer Players: A Novel Energetic Approach.

Sprinting is a decisive action in soccer that is considerably taxing from a neuromuscular and energetic perspective. This study compared different calculation methods for the metabolic power (MP) and energy cost (EC) of sprinting using global positioning system (GPS) metrics and electromyography (EMG), with the aim of identifying potential differences in performance markers. Sixteen elite U17 male soccer players (age: 16.4 ± 0.5 years; body mass: 64.6 ± 4.4 kg; and height: 177.4 ± 4.3 cm) participated in the study and completed four different submaximal constant running efforts followed by sprinting actions while using portable GPS-IMU units and surface EMG. GPS-derived MP was determined based on GPS velocity, and the EMG-MP and EC were calculated based on individual profiles plotting the MP of the GPS and all EMG signals acquired. The goodness of fit of the linear regressions was assessed by the coefficient of determination (R2), and a repeated measures ANOVA was used to detect changes. A linear trend was found in EMG activity during submaximal speed runs (R2 = 1), but when the sprint effort was considered, the trend became exponential (R2 = 0.89). The EMG/force ratio displayed two different trends: linear up to a 30 m sprint (R2 = 0.99) and polynomial up to a 50 m sprint (R2 = 0.96). Statistically significant differences between the GPS and EMG were observed for MP splits at 0-5 m, 5-10 m, 25-30 m, 30-35 m, and 35-40 m and for EC splits at 5-10 m, 25-30 m, 30-35 m, and 35-40 m (p ≤ 0.05). Therefore, the determination of the MP and EC based on GPS technology underestimated the neuromuscular and metabolic engagement during the sprinting efforts. Thus, the EMG-derived method seems to be more accurate for calculating the MP and EC in this type of action.

Mapping talent pathways: A comparative study of developmental activities and practice structure in Brazilian and Spanish U-18 elite youth male soccer players

The purpose of this study was threefold: (1) to compare the engagement in various types and amounts of soccer activities during childhood and adolescence between Brazilian and Spanish elite youth soccer players; (2) to test what talent development pathway characterizes youth development in elite soccer in Brazil and Spain and (3) to compare the practice structure between elite youth soccer in Brazil and Spain. Participants were 131 U-18 elite male soccer players from Brazil ( n = 68) and Spain ( n = 63) competing in the national league. The Participant History Questionnaire was used to measure the soccer activities undertaken by players. Developmental activities were analyzed for two age periods: childhood (6–12 y/o) and early adolescence (13–15 y/o). In Spain, players started their involvement in practice and competition in soccer earlier compared to Brazilian players ( p < .05). Brazilian players were more involved in structured activities, such as practice in soccer and futsal, and participated in a greater number of sports in childhood and early adolescence ( p < .05). We found a very similar percentual practice structure (individual, pair, drills, group tactics and collective tactics activities) between Spain and Brazil, although Brazilian players accumulated a greater practice volume. It is concluded that Spanish and Brazilian U-18 elite youth male soccer players were differentiated by their milestones in soccer and their engagement in practice activities during childhood and early adolescence. Talent development pathway of male soccer players in Spain was characterized by the early engagement pathway, while the Brazilian system was characterized by the specialized sampling model.

The interaction between acute emotional states and executive functions in youth elite soccer players.

Executive functions (EFs) are relevant for game performance in soccer and have been investigated in previous research. However, emotions are a well-known performance factor in sport competitions, which may affect performance by means of EFs. The diagnostic of EFs has mainly been performed disregarding the potential impact of emotional states. Thus, we aimed to initially analyze interaction between emotional states and EFs in two studies with male youth elite soccer players. In the first study, 105 players (Mage = 14.97) completed computerized tasks assessing inhibition, cognitive flexibility and working memory. In the second study, 92 players (Mage = 15.17) performed adapted and validated tests of inhibition (n = 45) or cognitive flexibility (n = 47) in a soccer-specific setting (SoccerBot360). Emotional and affective states were assessed using the German Sport Emotion Questionnaire and self-assessment manikins. For the computerized tasks, results showed a significant negative correlation between switch costs accuracy and tension, r = 0.28, indicating lower error rates with higher levels of tension. In contrast, in the SoccerBot360 we found significant positive correlations for response time and tension (no-switch: r = 0.38; switch: r = 0.39) representing prolonged response times related to tension. Further, for soccer-specific inhibition, positive emotions were significantly positively correlated with response time (congruent: r = 0.32; incongruent: r = 0.32). Subsequent regression analyses also demonstrate that valence and arousal effectively explain variance in cognitive performance parameters under neutral conditions. Accordingly, the ambiguity of the results suggests high variability in EF performance, affective and emotional states as well as a potentially moderating influence of other variables such as context and task difficulty. Thus, future cognitive diagnostic research should integrate assessments of emotional and affective states as these may contribute to situational fluctuations in EF performance.

Association between Sprint and Jump Performance and Maximum Strength in Standing Calf Raise or Squat in Elite Youth Soccer Players.

Soccer is a complex sports discipline that requires players to engage in diverse high-intensity and multidirectional activities. The optimization of strength and conditioning programs requires a comprehensive understanding of the physical attributes influencing player performance. While previous research has demonstrated the influence of knee and hip extensor muscles on the performance in sprints and other explosive movements, this study aimed to establish the relationship between plantar flexor muscle strength and high-intensity actions. Back squat (BS) and calf raise (CR) one-repetition maxima as well as linear sprint (5-, 10-, 30 m) and drop jump performance from different heights (15, 30, 45 and 60 cm) were measured in 45 elite youth players (age: 16.62 ± 1.1 years). Results showed significant negative correlations between BS strength and sprint times (r = -0.60 to -0.61), confirming the importance of lower limb extensor muscle strength in short-distance sprints. While no significant correlations were found with sprint performances, CR strength was significantly associated with drop jump test results from 45 and 60 cm drop height (r = 0.36 to 0.46). These findings demonstrate that isolated CR strength positively influences the performance in actions involving rapid stretch-shortening cycles, which suggests that current strength and conditioning programs for youth soccer players should be extended to also include exercises specifically targeting the plantar flexor muscles. While this cross-sectional study provides novel insights into the complex interplay between muscle strength and soccer-specific performance, its findings need to be corroborated in longitudinal studies directly testing the impact of plantar flexor strength training.

The Ratio between Weekly Training and Match External Physical Loads in U17 Elite Youth Soccer Players: Implications for the Training Process.

Research on the external physical load on elite youth soccer players during the weekly training microcycle in competitive periods and official matches is limited. The aims of this study were twofold: a) investigate possible differences in external physical load (PL) across player positions in U17 elite youth soccer players during official matches; b) determine the weekly training to match physical load ratio (WTMLr) across player positions. The sample included 20 outfield players from an elite soccer academy (mean age 15.94 ± 0.25 years) playing in four positions: central defender (CD), full-back (FB), central midfielder (CM) and Striker (S). Data were collected during the spring in-season period for 17 official matches played in a 4-3-3 game format. Indicators of external physical load monitored were: total distance (TD); total distance in high-speed running (HSR; > 16.1 km.h-1); total distance in sprint running (SPR; > 21.6 km.h-1); and relative physical load intensity (%HSR). The WTMLr was calculated for TD, HSR, SPR and %HSR as the ratio of the average weekly sum of training PL to the average sum of PL in an official match for a given players' position. Collectively, the training intensity during a one-week microcycle (%HSR in WTMLr) achieved only 76 % of match demands. CD performed significantly lower in all measured indicators of external PL during the official match than all other positions (p < 0.05; g > 0.80) except for TD in S. S achieved significantly higher SPR during official matches compared to CD (p < 0.05; g > 0.80), CM, and FB (g > 0.80). In contrast, CD reported higher WTMLr (medium-large effect size) in HSR and SPR indicators than all other positions. CM performed significantly higher %HSR in WTMLr than S and FB (p < 0.05; g > 0.80). Results revealed insufficient training intensity relative to match demands and, at the same time, weekly training PL did not meet match demands (especially in HSR and SPR) for players across the different positions. Therefore, practitioners should select appropriate training methods (drills and games) to ensure sufficient training intensity (HSR and SR metrics) and consider using the WTMLr, which can be used to help optimise and individualise training PL for different player positions.

Estimating Maturity Status in Elite Youth Soccer Players: Evaluation of Methods.

The objective of this study is to evaluate the concordance of predicted maturity status classifications (pre-, circa-, or post-peak height velocity (PHV)) relative to observed age at PHV in youth soccer players. Longitudinal height records for 124 male soccer players were extracted from academy records spanning the 2000 to 2022 seasons. Age at PHV for each player was estimated with the Superimposition by Translation and Rotation model. Players were classified as pre-, circa-, or post-PHV using both ±1- and ±0.5-yr criteria to define the circa-PHV interval. Maturity status was estimated with several prediction protocols: maturity offset (Mirwald, Moore-1, Moore-2), maturity ratio (Fransen), and percentage of predicted adult height (PAH%) using the Khamis-Roche and Tanner-Whitehouse 2 equations using several bands: 85% to 96%, 88% to 96%, 88% to 93%, and 90% to 93% for the circa-PHV interval, and visual evaluation of individual growth curves alone or with PAH% based on Khamis-Roche and Tanner-Whitehouse 2. Concordance of maturity status classifications based on complete growth curves and predicted estimates of maturity status was addressed with percentage agreement and Cohen's kappa. Visual evaluation of the growth curves had the highest concordance (≈80%) with maturity status classifications (pre-, circa-, post-PHV) based on longitudinal data for individual players. Predicted maturity offset with the Mirwald, Moore-1, and Fransen equations misclassified about one-third to one-half of the players, whereas concordance based on PAH% varied with the band used, but not with the method of height prediction. Visual assessment of the individual growth curves by an experienced assessor provides an accurate estimate of maturity status relative to PHV. Maturity offset prediction equations misclassify the majority of players, whereas PAH% provides a reasonably valid alternative.

Load and recovery monitoring in Swiss top-level youth soccer players: Exploring the associations of a new web application-based score with recognised load measures

Load and recovery monitoring in Swiss top-level youth soccer players: Exploring the associations of a new web application-based score with recognised load measures

Practice Design and Coaching to Support Learning in Elite Youth Soccer Players: Recommendations From International Coaches, Coach Educators, and Researchers

Providing optimal learning support is a major challenge within talent development settings. To accomplish this challenge, practitioners’ decisions, and actions should be informed by a blend of practical experiences and academic knowledge. This study explored experts’ recommendations on how to facilitate learning in elite adolescent soccer players during practice. Special focus was dedicated to why certain practice and coaching approaches were recommended to better understand experts’ justifications. Eighteen semistructured interviews were conducted with international experts representing three complementary groups of expertise (i.e., six of each soccer coaches; coach educators/developers; and researchers in talent development, motor learning, or coaching pedagogy). By employing a reflexive thematic analysis three themes were constructed: (I) differentiating overarching learning goals to address players’ individual needs, (II) designing purposeful training sessions with the game in mind, and (III) coaching interventions to support player learning within a group environment. Overall, the experts recommended the complementary use of different practice and coaching strategies to address individual learning needs. While some strategies may be associated with conflicting theoretical paradigms and established pedagogical approaches, the findings inform a purposeful integration of those different approaches in practical work. Therefore, participants’ recommendations can be discussed by integrating interdisciplinary theoretical perspectives.

Erratum. Practice Design and Coaching to Support Learning in Elite Youth Soccer Players: Recommendations From International Coaches, Coach Educators, and Researchers

Erratum. Practice Design and Coaching to Support Learning in Elite Youth Soccer Players: Recommendations From International Coaches, Coach Educators, and Researchers

Effects of Two Different Low-Volume Resistance Training Programs Applied During the Off-Season Period on the Speed-Power Performance of Elite Youth Soccer Players.

Loturco, I, Nunes, RFH, Lampert, RR, Silva, RLP, Hespanhol, JE, Novack, LF, Conde, JHS, Pereira, LA, and McGuigan, MR. Effects of two different low-volume resistance training programs applied during the off-season period on the speed-power performance of elite youth soccer players. . J Strength Cond Res 38(3): 571-576, 2024-The aim of this study was to analyze the changes in the speed-power performance of elite youth soccer players submitted to 2 different low-volume resistance training programs during the off-season period. Twenty under-17 players were randomly allocated to "traditional nonballistic" or "ballistic training" groups. Countermovement jump (CMJ), 20-m sprinting speed, and half-squat (HS) power tests were performed after the final match of the season (pretesting session) and at the beginning of the subsequent season (post-testing session), after 4 weeks of detraining. Between-group differences were assessed using a 2-way ANOVA with repeated measures followed by the Tukey's post hoc test. Performance variations were individually analyzed with the use of the "true changes" calculation. At post-tests, CMJ height and HS power remained unchanged ( p > 0.05) but similar and significant improvements in sprint speed were observed in both groups ( p < 0.05). However, notably, a larger number of players in the ballistic group exhibited "true changes" in HS power (i.e., 55 vs. 33%, compared with the traditional group, respectively). In conclusion, either low-volume ballistic or traditional resistance training schemes were able to increase sprint speed and maintain power output during a short interseason break in youth soccer players. Despite this apparent similarity, at the individual level, ballistic movements were more efficient at improving lower-body power. Practitioners can use the strategies described here to improve the sprint and power performance of soccer players during short periods of soccer-specific training cessation.

The relationships between relative age effect, personality constructs and achievement level in soccer.

Youth soccer academies are challenged with the constant recruitment process of young talented players to select those who will achieve long-term success as an athlete. Youth soccer academies strive to enhance the physical and technical skill development as well as personality development of talented players because psychological characteristics play a crucial role in players' future success in their transition to professional soccer. The least mature players and relatively young players may have a greater need to possess superior technical/tactical or psycho-behavioral skills than those relatively older counterparts because of the higher selection rates of early maturing players. Due to RAEs, a significant decrease in the overall quality of professional soccer teams might be observed because of the loss of talent of physically smaller, but psychologically stronger and more versatile relatively young players who possess proper technical and tactical attributes at an early age. The first objective of this study was to examine any possible relationship between RAE and personality constructs. A second objective was to identify factors and effects that can help in the further improvement of talent selection and equal opportunities for elite youth soccer players based on their underlying RAE. The third objective was to consider the impact of RAE on long-term career development. In this retrospective observational study, 151 elite youth soccer players between 15 and 18 years of age were first grouped in birth quartiles. Personality constructs were then assessed, using a combination of observations, interviews, and a self-assessment questionnaire. Next competition level after 8 years was evaluated to identify RAEs, differences in personality characteristics and opportunities to reach professional soccer player status between relatively older vs. younger players. A clear significant RAE was observed for the whole database (Q1 = 38.4% vs. Q4 = 13.9%) with OR of 2.61 (χ2 = 19.46, p < 0.01, r = -0.85). Relatively young players had higher median scores on personality constructs such as self-confidence (p = 0.04), while relatively old players had higher median scores on personality constructs such as team orientation (p = 0.03). In the long term, more players of the youngest birth quartile were signed as professional players (76.2%), compared with relatively old players (46.6%). 65.0% of the 20 players had the highest total score on personality constructs developed as a professional soccer player, vs. 35.0% of the 20 players with the lowest scores. In conclusion, this study showed not only further evidence of the RAE but also provided evidence supporting "the underdog hypothesis" in national elite youth teams. Relatively young players were also more likely to get higher value senior professional contracts in the long term. We propose that this may be due to the relatively young players developing superior psychological skills and technical expertise to compensate for their early physical disadvantage. This in turn suggests the need for greater awareness of the importance of personality constructs in the future development of youth elite soccer players. Therefore, the crux of the issue is how youth soccer academies elicit the "best of both worlds" ie. moderating RAE whilst also gaining the benefits of the underdog hypothesis by creating the right environment for every player to develop to their full potential in elite youth soccer academies.

Inconsistent Effect of Psychometric-Scale Familiarization on the Relationship Between Ratings of Perceived Exertion and External Load Measures in Elite Youth Soccer Players.

To examine the moderating effect of familiarization on the relationship between external load and ratings of perceived exertion (RPEs)in elite youth soccer players. Thirty-five elite male youth soccer players were monitored over a 31-week period. Players had no previous experience using the centiMax scale (arbitrary units[AU]). The final sample included familiarized (blackness test; n = 20) and nonfamiliarized players (n = 15) with the Borg centiMax scale. Players recorded a global RPE and differential RPEs (dRPE) for breathlessness (RPE-B) and leg-muscle exertion (RPE-L) 15 to 30minutes following training sessions and competitive matches. Separate multivariable-adjusted random-effects generalized additive models with restricted maximum likelihood quantified familiarization versus no-familiarization differences in actual perceived exertion score (in AU) by number of accelerations, decelerations, and high-speed running distance (in meters) as predictor variables, respectively. Players improved their blackness test score from 39% to 78%. For explorations by number of accelerations, familiarization effects were not practically relevant for the RPE and RPE-B variables. The width and sign of the effects for the RPE-L variable at 30 efforts of 10AU (95% CI, 4-16AU) suggested thatscores were lower for players who underwent familiarization versus players who did not. Familiarization effects were not practically relevant for any RPE variable irrespective of the number of deceleration efforts and high-speed running distance covered. Improved performance on the blackness test did not have a moderating effect on the relationship between proxy measures of external load and RPEs.

Temporal changes in intensity and volume of external training loads during a 1 × 1 short-bout, small-sided games in elite youth soccer players

This study compared external training load (ETL) and its temporal changes across repetitions during a speed endurance production (SEP) training comprised of 1 × 1 short-bout, small-sided games (SSGs) in elite youth soccer players. Twenty U18 players were divided into two groups (SEP1 and SEP2) performing six 30 s and 45 s bouts of SSG (work-to-rest ratio 1:4) on a 10 by 15 m field. ETL was characterized by the total distance covered, Player Load, the total number of accelerations/decelerations, and their relative values (per minute). Significant overall decreases in the ETL parameter values across six repetitions in both SSG groups were observed relative to the measurement in the first set beginning in 3rd (SEP1) or 4th (SEP2) repetitions. Significant greater decreases in Player Load (F(5.90) = 2.99, p < 0.05, η P2 = 0.14), Player Load per minute (F(5,90) = 11.32, p < 0.001, η P2 = 0.39), total distance per minute (F(3.43,61.73) = 7.72, p < 0.001, η P2 = 0.30) and accelerations per minute (F(5,90) = 2.59, p < 0.05, η P2 = 0.13) were observed in the 30-s games than in the 45-s games. In conclusion, the use of SSGs in SEP training is associated with a decrease in the effectiveness of physical work performed across repetitions. In practice, due to the decrease in the measured ETL indicators already in the 3rd or 4th repetition (especially in the SEP1 group), the work-to-rest ratio could be increased from the applied 1:4 to 1:6.

Relationship between relative age measured through decimal age, physical variables and anthropometry in elite youth soccer players

ABSTRACT Introduction Age differences between athletes born in the same year, as well as an over-representation of older players, are known as the Relative Age Effect (RAE). Players born at the beginning of the selection year have a physical and anthropometric advantage over their younger peers. Experts keep looking for new prediction variables for talent identification. Objectives The aim of the study is to correlate anthropometric, strength and power variables with the relative age (RA) and the level of the teams in which players played in each age category. Methods All players (N = 366) from an elite soccer academy of a Spanish club volunteered to participate in the study (U23-U10). Results There was a significant correlation between the RA of the players and the level of the team in which they played in each age category but no correlation between trimester of birth and level of the team. We found significant correlations between the players’ physical capacities, anthropometry, RA and the level of the team in which they played for the same age category, mainly from U16 to U10. U23 did not show any correlation between RA and physical or anthropometric variables. Conclusion Coaches should be cautious of choosing players based only on anthropometric or physical attributes.

Is there a relationship between executive functions and resilience in youth elite soccer players?

While the relationship between cognitive performance and sport performance in youth elite soccer players has proponents as well as opponents, many aspects of this relationship remain unclear. Therefore, this quasi-experimental study wants to contribute to this relationship including the psychological aspect of resilience when investigating youth elite soccer players during an assessment selection for a representative team. Questionnaires as well as computer-based tests were conducted. Results of this study showed no relationship between resilience and executive function in youth elite soccer players. Furthermore, no differences in executive functions or in resilience were found between those players who are selected for a representative team and those who were not selected. The results indicate that further research needs to be conducted to clarify possible relationships in more detail.

Effectiveness of a Preventative Program for Groin Pain Syndrome in Elite Youth Soccer Players: A Prospective, Randomized, Controlled, Single-Blind Study.

Groin pain syndrome (GPS) is a prevalent issue in soccer. This study assessed the effectiveness of a new preventive protocol on GPS for youth soccer players. The protocol included targeted stretching and strengthening exercises for the adductor and core muscles from preseason to midseason. A questionnaire and two pain provocation tests were used for the evaluation. Mild GPS required positive results in at least two evaluations, while severe GPS was associated with pain incompatible with engagement in any activity confirmed by diagnostic ultrasound. Forty-two elite male athletes (aged 16.9 ± 0.7 years) participated in the study, with half of them assigned to the usual training (control group) and the remaining athletes undergoing the preventive protocol (treatment group) for 24 weeks. GPS rates were 14.3% (three diagnoses: two mild, one severe) in the treatment group and 28.6% (six diagnoses: three mild, three severe) in the control group. Toward the end of the season, three players, one from the treatment group and two from the control group had to stop playing due to severe GPS problems. In addition, one player in the control group stopped midseason. Even though the reduction in the risk of developing GPS was not significant (relative risk of 0.50 ([95%CI 0.14 to 1.74], p = 0.2759), the halved incidence of severe GPS and the increased muscle strength related to the treatment (p = 0.0277) are encouraging data for future studies.

Curved sprinting in soccer: The influence of radius

The aims of this study were (i) to compare the sprint times between linear-sprint (LS) and curved-sprint (CS) tests of different radii, and (ii) to examine the relationships between sprint times in these tests in soccer players. Nineteen elite youth male soccer players (age, 18.6 ± 0.6 years) completed an LS test and three CS tests with different radii both from the left and the right side (11.15-m radius = CSwide, 9.15-m radius = CSmedium and 7.15-m radius = CSnarrow), each with a distance of 17 m. Differences in sprint times were examined using analysis of variance with Bonferroni-corrected pairwise comparisons and Cohen's d effect sizes (ES). Relationships between sprint times were determined by Pearson's product-moment correlations (r). Significantly lower sprint times were evident for LS compared to all three CS tests ( p &lt; .001, MD = 0.08–0.16 s, ES = 0.83–1.49), for CSwide compared to CSnarrow ( p = .02, MD = 0.04 s, ES = 0.47) and for CSmedium compared to CSnarrow ( p &lt; .001, MD = 0.07 s, ES = 0.82). Very large correlations ( p &lt; .001, r = 0.75–0.80) were found between sprint times in LS and the three CS tests. Very large to nearly perfect correlations ( p &lt; .001, r = 0.79–0.91) were found within the three CS tests. Practitioners should be aware that sprint times are lower in LS compared to CS of different radii and that CS times are higher at narrower angles compared to wider angles. Given the high correlations within three CS tests, the application of only one CS (e.g., CSmedium) during a test battery may be sufficient if using different CS is not possible. Results of the correlation analysis also suggest that LS contributes to CS performance, however, to slightly different extents depending on the radius of the CS. Consequently, both LS and CS drills might be incorporated into sprint training practices of elite youth soccer players.

Reliability and sensitivity to change of post-match physical performance measures in elite youth soccer players.

To effectively monitor post-match changes in physical performance, valid, reliable and practical measures which are sensitive to change are required. This study aimed to quantify test-retest reliability and sensitivity to change of a range of physical performance measures recorded during an isometric posterior chain (IPC) lower-limb muscle test and a countermovement jump (CMJ) test. Eighteen Italian Serie A academy soccer players performed three IPC repetitions per limb and five CMJ trials in 4 testing sessions. Test-retest reliability was evaluated between two testing sessions seven days apart using typical error of measurement, coefficient of variation and intraclass correlation coefficient. Sensitivity to change was assessed on two additional testing sessions performed before and immediately after a soccer match through Hedges' g effect size (g) and comparisons to typical error. Absolute reliability (coefficient of variations) ranged from 1.5 to 8.8%. IPC and CMJ measures demonstrated moderate to excellent relative reliability (intraclass correlation coefficients ranged from 0.70 to 0.98). A wide range of physical performance measures showed significant alterations post-match (p < 0.05; g: small to moderate). IPC peak force and torque, CMJ reactive strength index modified, CMJ eccentric forces (mean breaking force, mean deceleration force, peak force, force at zero velocity) and CMJ mean power measures had post-match changes greater than their typical variation, demonstrating acceptable sensitivity in detecting performance changes at post-match. IPC peak force and torque, CMJ reactive strength index modified, CMJ eccentric phase forces and CMJ mean power were found to be both reliable and sensitive to change, and thus may be appropriate for monitoring post-match neuromuscular performance in youth soccer population.

A deep learning factor analysis model based on importance‐weighted variational inference and normalizing flow priors: Evaluation within a set of multidimensional performance assessments in youth elite soccer players

AbstractExploratory factor analysis is a widely used framework in the social and behavioral sciences. Since measurement errors are always present in human behavior data, latent factors, generating the observed data, are important to identify. While most factor analysis methods rely on linear relationships in the data‐generating process, deep learning models can provide more flexible modeling approaches. However, two problems need to be addressed. First, for interpretation, scaling assumptions are required, which can be (at least) cumbersome for deep generative models. Second, deep generative models are typically not identifiable, which is required in order to identify the underlying latent constructs. We developed a model that uses a variational autoencoder as an estimator for a complex factor analysis model based on importance‐weighted variational inference. In order to receive interpretable results and an identified model, we use a linear factor model with identification constraints in the measurement model. To maintain the flexibility of the model, we use normalizing flow latent priors. Within the evaluation of performance measures in a talent development program in soccer, we found more clarity in the separation of the identified underlying latent dimensions with our models compared to traditional PCA analyses.