Posts tagged with ‘R’

  • Fantastic Sport Analytics Papers & Resources

    By Mladen Jovanovic on 03/03/2018

    I have recently stumbled on a few great papers that outline very useful statistical techniques, that are VERY applicable to sport and training analytics. If you are interested in analytics, this is a gold mine.

  • Few Simple Improvements to Monitoring Data Analysis

    By Mladen Jovanovic on 22/02/2018

    Most of us are collecting and analyzing training load data and readiness metrics (i.e. GPS training load, sRPE and wellness). The most common analysis method is to use two rolling averages windows – acute (around 7 days) and chronic (around 28 days) and to calculate their ratio, referred to as ACWR (Acute to Chronic Workload Ratio), or TSB (Training...

  • Why The Concept of Biomotor Abilities is Bullshit

    By Mladen Jovanovic on 23/01/2018

    In my opinion, biomotor abilities are ‘dimension reduction’ of the complex perceptual-motor space. Suppose we perform 500 various tests of performance for at least 5000 athletes.

  • How to Analyze Training Load and Monitoring Data?

    By Mladen Jovanovic on 21/11/2017

    In this video I am sharing my viewpoints, as well as the dashboard I've built in Shiny, regarding how to make sense of longitudinal training load and monitoring data.

  • Shuttle Run Beep Test Improvement & New Test

    By Mladen Jovanovic on 12/10/2017

    I decided to compile 20m shuttle run test with 1.2s correction per turn. This is great for testing bigger athletes, like NFL or Rugby players.

  • To Turf or Not to Turf, That is the Question [Part 2]: Applications

    By Mladen Jovanovic on 26/07/2017

    In this video I am deploying the model to make the decision between 5 variations of weekly plan. The goal is to minimize the morning soreness on the day of the game.

  • To Turf or Not to Turf, That is the Question [Part 1]

    By Mladen Jovanovic on 05/07/2017

    In this video I am presenting my “solution” to the problem and provide fake data set, as well as R code for analyzing the data. Having decent predictive model can help us run different optimization algorithms to find the “best” scheduling to minimize/maximize injury risk or performance.

  • Netflix Prize and Injury Prediction Prize

    By Mladen Jovanovic on 13/03/2017

    The Netflix Prize was an open competition for the best collaborative filtering algorithm to predict user ratings for films, based on previous ratings without any other information about the users or films, i.e. without the users or the films being identified except by numbers assigned for the contest. Which made me think – why don’t the “rich” clubs, such...

  • Thoughts on Injury Prediction

    By Mladen Jovanovic on 08/12/2016

    In the following article, I am discussing the famous “J” curve in injury prediction, as well as simulate some data to show how that curve is estimated. I also show the distinction between association and prediction, as well as how to make training decisions based on the different costs of committing false positive and false negative errors.

  • The Dowry Problem

    By Mladen Jovanovic on 18/10/2016

    In this video I am solving the famous dowry problem using the simulation in R. It is interesting to see how we can test the assumptions and heuristic easily with simulations.