Announcement

Collapse
No announcement yet.

Advanced Statistical Analysis of Biomechanical Time Series: Seminar at WCB

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • Advanced Statistical Analysis of Biomechanical Time Series: Seminar at WCB

    Advanced Statistical Analysis of Biomechanical Time Series: PCA, FDA and SPM

    This summer, we will be hosting a pre-World Congress of Biomechanics seminar on advanced statistical analysis of biomechanical time series, in particular focusing on Principal Components Analysis, Functional Data Analysis, and Statistical Parameter Mapping. This session will run from 13:30 to 16:30 on Saturday July 7th 2018 at the Trinity Biomedical Sciences Institute (12 minute walk from the WCB conference venue - further details in Eventbrite link below).

    Seminar speakers: Todd Pataky (Kyoto University, Japan), Mark Robinson (Liverpool John Moores University, UK), Jos Vanrenterghem (KU Leuven), Drew Harrison (University of Limerick, Ireland), John Warmenhoven (University of Sydney and Australian Institute of Sport, Australia)

    Seminar description: Traditional biomechanical analysis focusing on discrete points, such as local minima or maxima, can result in elimination of much data which is still relevant to understanding the mechanics of an individual or group. Full-trajectory analysis techniques are being increasingly applied to healthy and patient population kinematic, kinetic, and neuromuscular data as they include all of the original data acquired, but their correct application and interpretation can be challenging.

    The purpose of this seminar is to present an overview of the theoretical underpinnings of the most commonly used full-trajectory analysis techniques in biomechanics (Principal Components Analysis, Functional Data Analysis, and Statistical Parameter Mapping), discuss the purpose, advantages and limitations of these techniques, and present applications of how these techniques can be applied to data from both healthy and clinical populations.

    By the end of this seminar, audience members should be able to identify the most appropriate technique(s) for use with their dataset, and have a working knowledge of the strengths and limitations of the various techniques under consideration. The lecture theatre is fully equipped with 220 V power supply at each seat if attendees wish to bring laptops for use during the session.

    Attendance fee: There is no charge for attendees registered for the World Congress of Biomechanics – please give your full name as used for your WCB registration when you book your ticket so we can verify this. For non-conference attendees, there is a nominal charge of €10 which will be collected at the registration desk on the day.

    To register: Please follow this Eventbrite link https://www.eventbrite.co.uk/e/advan...262727?aff=es2
    Last edited by Laura-Anne Furlong; June 12, 2018, 08:33 AM.

  • #2
    Re: Advanced Statistical Analysis of Biomechanical Time Series: Seminar at WCB

    Is there any possibility of making slides or lecture materials available for those that cannot attend WCB this year? I'd happily pay the fee you're charging to get an introduction to this field. Thank you.

    Comment


    • #3
      Re: Advanced Statistical Analysis of Biomechanical Time Series: Seminar at WCB

      Adam,

      Unfortunately we cannot use lecture capture for this session, but if you are interested in this area the following resources will be helpful for you:

      http://www.spm1d.org/ (this site also has some slides from previous workshops)

      SPM literature:



      FDA literature:
      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.



      SPM and FDA:


      (links kindly courtesy of John Warmenhoven)

      I hope this you find these a good starting point,
      Laura-Anne

      Comment


      • #4
        Re: Advanced Statistical Analysis of Biomechanical Time Series: Seminar at WCB

        Resources to be used for this workshop are currently available at the following GitHub folder (thanks to Todd Pataky for creating):
        Material associated with the 2018 Dublin seminar: "Advanced statistical analysis of biomechanical time series: PCA, FDA and SPM" - GitHub - 0todd0000/fda-pca-spm: Material associated with...


        Slides used will be uploaded after the workshop.

        Looking forward to seeing everyone on Saturday,
        Laura-Anne

        Comment

        Working...
        X