Predicting Injuries Using Banister Model – The Addendum

Predicting Injuries Using Banister Model – The Addendum

A year ago I tried to use Banister model to predict injuries, but I recently realized I made an error implementing link function. So, I decided to do one more try and correct the problem.

In the video below I am using three training load metrics (RPE Load, Odometer and High Speed Distance) to predict soft tissue injuries for one athlete. I have covered a lot of topics regarding modelling in general, Banister model and its pro’s and con’s, as well as potential solutions. Also, I will talk more about using heuristics, rather than analysis in helping decision making.

The members of Complementary Training can download the Excel workbook and follow the video. Enjoy and let me know what you think!

To Download Excel Workbook Please Join Us Today Become Member

I am a physical preparation coach from Belgrade, Serbia, grew up in Pula, Croatia (which I consider my home town). I was involved in physical preparation of professional, amateur and recreational athletes of various ages in sports such as basketball, soccer, volleyball, martial arts and tennis. Read More »

Home Forums Predicting Injuries Using Banister Model – The Addendum

This topic contains 2 replies, has 2 voices, and was last updated by  Mladen Jovanovic 9 months ago.

Viewing 2 posts - 1 through 2 (of 2 total)
  • 19/01/2017 at 21:14 #19081

    Hi Mladen,

    First, congrats for the post, is it such a great job. I´m starting with data analysis so I really appreciate your help.

    One time you change variables and instead of “RPE”, “Odometer” and “HS distance” you may use “Acute TL”, “Chronic TL”, “Ac:Ch” for example. How could you calculate the threshold number for the link function?. In the workbook is using 10 and -10 for those variables. How can you estimate threshold when using diferent variables?


    Hugo Salazar

    20/01/2017 at 02:31 #19084

    Hi Hugo,

    Thanks for the message. To be honest I am not sure what do you refer to? I have standardized the values for the solver to converge easier, you can use the raw numbers but the search might take forever

Viewing 2 posts - 1 through 2 (of 2 total)

You must be logged in to reply to this topic.