Description:
Background Functional data analysis (FDA) is increasingly being used to better analyze, model and predict time series data. Key aspects of FDA include the choice of smoothing technique, data reduction, adjustment for clustering, functional linear modeling and forecasting methods. Methods A systematic review using 11 electronic databases was conducted to identify FDA application studies published in the peer-review literature during 1995–2010. Papers reporting methodological considerations only were excluded, as were non-English articles. Results In total, 84 FDA application articles were identified; 75.0% of the reviewed articles have been published since 2005. Application of FDA has appeared in a large number of publications across various fields of sciences; the majority is related to biomedicine applications (21.4%). Overall, 72 studies (85.7%) provided information about the type of smoothing techniques used, with B-spline smoothing (29.8%) being the most popular. Functional principal component analysis (FPCA) for extracting information from functional data was reported in 51 (60.7%) studies. One-quarter (25.0%) of the published studies used functional linear models to describe relationships between explanatory and outcome variables and only 8.3% used FDA for forecasting time series data. Conclusions Despite its clear benefits for analyzing time series data, full appreciation of the key features and value of FDA have been limited to date, though the applications show its relevance to many public health and biomedical problems. Wider application of FDA to all studies involving correlated measurements should allow better modeling of, and predictions from, such data in the future especially as FDA makes no a priori age and time effects assumptions.
Description:
Background Functional data analysis (FDA) is increasingly being used to better analyze, model and predict time series data. Key aspects of FDA include the choice of smoothing technique, data reduction, adjustment for clustering, functional linear modeling and forecasting methods. Methods A systematic review using 11 electronic databases was conducted to identify FDA application studies published in the peer-review literature during 1995–2010. Papers reporting methodological considerations only were excluded, as were non-English articles. Results In total, 84 FDA application articles were identified; 75.0% of the reviewed articles have been published since 2005. Application of FDA has appeared in a large number of publications across various fields of sciences; the majority is related to biomedicine applications (21.4%). Overall, 72 studies (85.7%) provided information about the type of smoothing techniques used, with B-spline smoothing (29.8%) being the most popular. Functional principal component analysis (FPCA) for extracting information from functional data was reported in 51 (60.7%) studies. One-quarter (25.0%) of the published studies used functional linear models to describe relationships between explanatory and outcome variables and only 8.3% used FDA for forecasting time series data. Conclusions Despite its clear benefits for analyzing time series data, full appreciation of the key features and value of FDA have been limited to date, though the applications show its relevance to many public health and biomedical problems. Wider application of FDA to all studies involving correlated measurements should allow better modeling of, and predictions from, such data in the future especially as FDA makes no a priori age and time effects assumptions.
Description:
Background: Enjoyment and play during school lunchtime are correlated with children's physical activity. Despite this, there is an absence of studies reporting children's enjoyment of play during school lunchtime breaks. The purpose of this study was to examine the intraday and interday reliability of children's enjoyment of school lunchtime play. Methods: Surveys used to assess children's enjoyment of lunchtime play were distributed to and completed by 197 children (112 males, 85 females), aged 8-12 years attending an elementary school in Victoria, Australia. Children completed the surveys during class before lunch (expected enjoyment) and after lunch (actual enjoyment) for 5 days. The intra- and interday enjoyment of school lunchtime play reliability were determined using a weighted kappa. Results: Intraday kappa values ranged from fair (0.31) to substantial (0.75) within each of the 5 days (median kappa = 0.41). In comparison, "expected" (0.09-0.40; median 0.30) and "actual" (0.05-0.46; median 0.28) interday enjoyment of lunchtime play displayed low reliability. Conclusions: Children's enjoyment of lunchtime play appears to be more consistent within days than across days. The findings suggest that assessment of children's enjoyment of lunchtime play once on a single day would be representative of a particular day but not necessarily that particular school week.
Ensuring implementation success: how should coach injury prevention education be improved if we want coaches to deliver safety programmes during training sessions?
Description:
Coaches play a major role in encouraging and ensuring that participants of their teams adopt appropriate safety practices. However, the extent to which the coaches undertake this role will depend upon their attitudes about injury prevention, their perceptions of what the other coaches usually do and their own beliefs about how much control they have in delivering such programmes. Fifty-one junior netball coaches were surveyed about incorporating the teaching of correct (safe) landing technique during their delivery of training sessions to junior players. Overall, >94% of coaches had strongly positive attitudes towards teaching correct landing technique and >80% had strongly positive perceptions of their own control over delivering such programmes. Coaches’ ratings of social norms relating to what others think about teaching safe landing were more positive (>94%) than those relating to what others actually do (63–74%). In conclusion, the junior coaches were generally receptive towards delivering safe landing training programmes in the training sessions they led. Future coach education could include role modelling by prominent coaches so that more community-level coaches are aware that this is a behaviour that many coaches can, and do, engage in.
Description:
Coaches play a major role in encouraging and ensuring that participants of their teams adopt appropriate safety practices. However, the extent to which the coaches undertake this role will depend upon their attitudes about injury prevention, their perceptions of what the other coaches usually do and their own beliefs about how much control they have in delivering such programmes. Fifty-one junior netball coaches were surveyed about incorporating the teaching of correct (safe) landing technique during their delivery of training sessions to junior players. Overall, >94% of coaches had strongly positive attitudes towards teaching correct landing technique and >80% had strongly positive perceptions of their own control over delivering such programmes. Coaches’ ratings of social norms relating to what others think about teaching safe landing were more positive (>94%) than those relating to what others actually do (63–74%). In conclusion, the junior coaches were generally receptive towards delivering safe landing training programmes in the training sessions they led. Future coach education could include role modelling by prominent coaches so that more community-level coaches are aware that this is a behaviour that many coaches can, and do, engage in.
Description:
Objectives: Well-developed physical qualities may protect against contact injuries. However, the potential contribution of physical qualities as risk or protective factors to contact injury risk is yet to be determined for rugby league. This study applied a frailty survival model that accounts for recurrent injury to identify risk factors for all physiotherapist-reported contact injury in professional rugby league players. Design: Prospective cohort study. Methods: Sixty-six professional rugby league players participated in this three successive year prospective study. At the start of each season, all players underwent measurements of standard anthropometry (height, body mass, and sum of seven skinfolds), speed (10 m and 40 m sprint), muscular strength (1 repetition maximum [RM] bench press, 1RM squat, 1RM weighted chin-ups), power (vertical jump, bench throw, 1RM power clean, jump squat), and endurance (maximum repetition bench press with 60 kg resistance), repeated-sprint ability (12 × 20 m sprints performed on a 20 s cycle), prolonged high-intensity intermittent running ability (8 × 12 s maximal effort shuttles performed on a 48 s cycle), and maximal aerobic power (multi-stage fitness test). Data was used to demonstrate the application of the frailty model extension of the Cox proportional regression model for recurrent events to identify factors associated with a high hazard ratio (HR) of injury. Results: Heavier (body mass, HR = 2.6, 95% CI = 1.2-5.7), and faster (40 m sprint, HR = 2.1, 95% CI = 1.0-4.2) players, and those with poorly developed prolonged high-intensity intermittent running ability (HR = 2.9, 95% CI = 1.7-5.0) and upper-body strength (chin-up, HR = 2.2, 95% CI = 1.3-3.7) had a higher incidence of contact injuries. Conclusions: This study demonstrates application of a novel statistical approach for the analysis of injury data that is recurrent in nature. This approach identified that the greater impact forces generated from heavier players with faster speed may result in an increase in recurrent contact injury rates. However, the development of prolonged high-intensity intermittent running ability and upper-body strength and power may assist to reduce the risk of contact injury in professional rugby league players.
Implementing an exercise-training programme to prevent lower-limb injuries : Considerations for the development of a randomised controlled trial intervention delivery plan
Description:
Objective To identify important considerations for the delivery of an exercise training intervention in a randomised controlled trial to maximise subsequent participation in that randomised controlled trial and intervention uptake. Design A cross-sectional survey, with a theoretical basis derived from the Health Belief Model (HBM) and the Reach, Efficacy/Effectiveness, Adoption, Implementation and Maintenance (RE-AIM) framework. Participants 374 male senior Australian Football players, aged 17-38 years. Main outcome measurements Beliefs about lowerlimb injury causation/prevention, and the relative value of exercise training for performance and injury prevention. The data are interpreted within HBM constructs and implications for subsequent intervention implementation considered within the RE-AIM framework. Ordinal logistic regression compared belief scores across player characteristics. Results 74.4% of players agreed that doing specific exercises during training would reduce their risk of lower-limb injury and would be willing to undertake them. However, 64.1% agreed that training should focus more on improving game performance than injury prevention. Younger players (both in terms of age and playing experience) generally had more positive views. Players were most supportive of kicking (98.9%) and ball-handling (97.0%) skills for performance and warm-up runs and cool-downs (both 91.5%) for injury prevention. Fewer than three-quarters of all players believed that balance (69.2%), landing (71.3%) or cutting/stepping (72.8) training had injury-prevention benefits. Conclusions Delivery of future exercise training programmes for injury prevention aimed at these players should be implemented as part of routine football activities and integrated with those as standard practice, as a means of associating them with training benefits for this sport.
Description:
Objective To identify important considerations for the delivery of an exercise training intervention in a randomised controlled trial to maximise subsequent participation in that randomised controlled trial and intervention uptake. Design A cross-sectional survey, with a theoretical basis derived from the Health Belief Model (HBM) and the Reach, Efficacy/Effectiveness, Adoption, Implementation and Maintenance (RE-AIM) framework. Participants 374 male senior Australian Football players, aged 17-38 years. Main outcome measurements Beliefs about lowerlimb injury causation/prevention, and the relative value of exercise training for performance and injury prevention. The data are interpreted within HBM constructs and implications for subsequent intervention implementation considered within the RE-AIM framework. Ordinal logistic regression compared belief scores across player characteristics. Results 74.4% of players agreed that doing specific exercises during training would reduce their risk of lower-limb injury and would be willing to undertake them. However, 64.1% agreed that training should focus more on improving game performance than injury prevention. Younger players (both in terms of age and playing experience) generally had more positive views. Players were most supportive of kicking (98.9%) and ball-handling (97.0%) skills for performance and warm-up runs and cool-downs (both 91.5%) for injury prevention. Fewer than three-quarters of all players believed that balance (69.2%), landing (71.3%) or cutting/stepping (72.8) training had injury-prevention benefits. Conclusions Delivery of future exercise training programmes for injury prevention aimed at these players should be implemented as part of routine football activities and integrated with those as standard practice, as a means of associating them with training benefits for this sport.
Description:
The ageing of the population is one of the major transformations being experienced in Australia, with falls a significant threat to safety, health and independence. There is now substantial evidence regarding effective interventions for preventing falls among older people living independently in the community. The aim of this project was to develop and apply a framework for epidemiological modelling of the population level impact of proven interventions on future fall rates, providing a powerful policy-setting tool for prevention. We used the Cochrane review to source current best efficacy evidence from randomised controlled trials which have provided evidence of minimising the incidence of falls among older people living in the community. Six interventions defined in that review as most promising for community dwelling older people were modelled. Additionally, one other intervention not in the Cochrane review, expedited cataract removal, was also modelled. Occupational therapy delivered home hazard assessment and modification for those with recent fall history, as modelled here, represents the best falls prevention investment. Cardiac pacing is a good falls prevention investment over the medium term, although is unlikely to have a major impact on population level hospital admission rates. The relative cost-effectiveness of psychotropic medication withdrawal appears high, although some implementation issues would need to be addressed and further costs included. Multi-disciplinary multi-factorial risk management represents good clinical practice for high risk individuals, but is not relatively cost-effective for widespread implementation. Tai chi programs may represent good value for falls prevention resources, if local circumstances allow the cost per participant to be substantially lower than modelled here. Predicted reductions in national fall-related hospital admission rates for people aged 65 years and over ranged from 0.4% to 4.6% for five of the six falls prevention strategies implemented over a one year period. These reductions, however, suggest that substantial investment in falls prevention will be required to have large effects on the fall-related hospitalisation rates. In addition, the costeffectiveness of a number of the modelled interventions could be improved by variations to the implementation processes such as measures to increase uptake, or decrease the cost per participant. The framework developed provides the potential for the research evidence base to better guide policy and practice with respect to reducing falls and future fall-related hospitalisation rates.
Description:
Objective: To model the population level impact of tai-chi on future rates of falls and fall-related injury in older people as a tool for policy development. Design: An epidemiological and economic model for estimating population-level effectiveness of tai-chi. Setting: Australia, 2009. Patients or subjects: Australian community-dwelling population aged 70+ years, ambulatory and without debilitating conditions or profound visual defects. Intervention: Group-based tai-chi, for 1 h twice weekly for 26 weeks, assuming no sustained effect beyond the intervention period. Main outcome measure: Total falls and fall-related hospitalisation prevented in 2009. Results: Population-wide tai-chi delivery would prevent an estimated 5440 falls and 109 fall-related hospitalisations, resulting in a 0.18% reduction in the fall related hospital admission rate for community-dwelling older people. The gross costs per fall and per fall-related hospital admission prevented were $ A4414 ((sic)3013) and $A220 712 ((sic)150 684), respectively. A total investment of $A24.01 million ((sic)16.39 million), equivalent to 4.2% of the cost of fall-related episodes of hospital care in 2003/4, would be required to provide tai-chi for 31 998 people and achieve this effect. Conclusions: Substantial investment in, and high population uptake of, tai-chi would be required to have a large effect on falls and fall-related hospitalisation rates. Although not accounted for in this study, investment in tai-chi is likely to be associated with additional significant health benefits beyond falls prevention. This approach could be applied to other interventions to assist selection of the most cost effective falls-prevention portfolio for Australia and other countries.
Description:
AbstractObjectives Australian Football League (AFL) players have a high risk of injury. Anecdotally, this injury risk is greater in emerging players (i.e. those in their first year), compared with established players (with 3+ years of experience). This study aimed to conduct the first comparison of injury risk and playing experience in these two player groups across a large number of AFL clubs. Design Prospective, cohort. Methods Injuries, game participation and training participation were collected weekly by 8 AFL clubs for 61 emerging and 64 established players. Injury incidence rates (IIR) and Cox proportional hazard models for time to first injury, separately for games and training, were computed. Results The game IIR was significantly higher for emerging than established players: 45.6 (95% CI: 35.7, 57.6) versus 18.3 (95% CI: 13.1, 24.9) per 1000 game-hours. Emerging players also had a higher training IIR than did the established players: 9.6 (95% CI: 7.6, 11.9) versus 8.9 (95% CI: 7.0, 11.1) per 1000 training-hours. Emerging players were significantly less likely to remain injury free in games than established players (HR = 3.46, 95% CI: 1.27, 9.45). A similar outcome was seen in training sessions, although to a lesser degree (HR = 1.41, 95% CI: 1.19, 1.69). Conclusions Despite efforts to modify the playing/training program of emerging players, this group remain at greater risk of injury in games and training sessions, compared with established players. Continued efforts should be made toward understanding reasons for this increased risk to better prevent injury during the early years of a professional football career.
Description:
Background: Injuries are often recurrent, with subsequent injuries influenced by previous occurrences and hence correlation between events needs to be taken into account when analysing such data. Objective: This paper compares five different survival models (Cox proportional hazards (CoxPH) model and the following generalisations to recurrent event data: Andersen-Gill (A-G), frailty, Wei-Lin-Weissfeld total time (WLW-TT) marginal, Prentice-Williams-Peterson gap time (PWP-GT) conditional models) for the analysis of recurrent injury data. Methods: Empirical evaluation and comparison of different models were performed using model selection criteria and goodness-of-fit statistics. Simulation studies assessed the size and power of each model fit. Results: The modelling approach is demonstrated through direct application to Australian National Rugby League recurrent injury data collected over the 2008 playing season. Of the 35 players analysed, 14 (40%) players had more than 1 injury and 47 contact injuries were sustained over 29 matches. The CoxPH model provided the poorest fit to the recurrent sports injury data. The fit was improved with the A-G and frailty models, compared to WLW-TT and PWP-GT models. Conclusions: Despite little difference in model fit between the A-G and frailty models, in the interest of fewer statistical assumptions it is recommended that, where relevant, future studies involving modelling of recurrent sports injury data use the frailty model inpreference to the CoxPH model or its other generalisations. The paper provides a rationale for future statistical modelling approaches for recurrent sports injury.
Description:
Background: Injuries are often recurrent, with subsequent injuries influenced by previous occurrences and hence correlation between events needs to be taken into account when analysing such data. Objective: This paper compares five different survival models (Cox proportional hazards (CoxPH) model and the following generalisations to recurrent event data: Andersen-Gill (A-G), frailty, Wei-Lin-Weissfeld total time (WLW-TT) marginal, Prentice-Williams-Peterson gap time (PWP-GT) conditional models) for the analysis of recurrent injury data. Methods: Empirical evaluation and comparison of different models were performed using model selection criteria and goodness-of-fit statistics. Simulation studies assessed the size and power of each model fit. Results: The modelling approach is demonstrated through direct application to Australian National Rugby League recurrent injury data collected over the 2008 playing season. Of the 35 players analysed, 14 (40%) players had more than 1 injury and 47 contact injuries were sustained over 29 matches. The CoxPH model provided the poorest fit to the recurrent sports injury data. The fit was improved with the A-G and frailty models, compared to WLW-TT and PWP-GT models. Conclusions: Despite little difference in model fit between the A-G and frailty models, in the interest of fewer statistical assumptions it is recommended that, where relevant, future studies involving modelling of recurrent sports injury data use the frailty model inpreference to the CoxPH model or its other generalisations. The paper provides a rationale for future statistical modelling approaches for recurrent sports injury.
Description:
Objective To examine the appropriateness of different statistical models in analysing falls count data. Methods Six count models (Poisson, negative binomial (NB), zero-inflated Poisson (ZIP), zero-inflated NB (ZINB), hurdle Poisson (HP) and hurdle NB (HNB)) were used to analyse falls count data. Empirical evaluation of the competing models was performed using model selection criteria and goodness-of-fit through simulation. Data used were from a prospective cohort study of women aged 40-80 years. Results Of the 465 women analysed, 330 (71%) did not fall at all. The analyses identified strong evidence of overdispersion in the falls data. The NB-based regression models (HNB, ZINB, NB) were better performed than the Poisson-based regression models (Poisson, ZIP, HP). Vuong tests favoured the HNB model over the NB and ZINB models and the NB model over the ZINB model. Model accuracy measures and Monte Carlo simulation of goodness-of-fit confirmed the lack of fit of the Poissonbased regression models and demonstrated the best fit for the HNB model with comparable good fit for the ZINB and NB models. Conclusions Falls count data consisting of a considerable number of zeros can be appropriately modelled by the NBbased regression models, with the HNB model offering he best fit. The evaluation procedure presented in this aper provides a defensible guideline to appropriately odel falls or similar count data with excess zeros.