Statistics & Data Analysis

• Uncertainty, Heuristics and Injury Prediction

I was asked by Rod Whiteley and Nicol van Dyk to contribute to the Aspetar Journal targeted topic issue that just got released off the press. I tried to combine my knowledge of predictive analytics, machine learning, philosophy of science, heuristics and practical experience as coach & sport scientist into one article. Hopefully I managed to create readable narrative.

• What Is Propensity Matching and How Can We Improve Validity of Causality Claims?

Researchers usually try to randomize correctly, but sometimes the effect is not in the treatment, but maybe in the difference between group (pre-treatment) or during the treatment (for example volume of training) which should be similar/same so we can judge the effects of something else of interest (for example novel periodization). The solutions are to involve covariates in the…

• Effect of Typical Variation of a Test on Confidence Interval

Confidence intervals gives us the range of a given statistic when generalizing from a sample to a population. The simplest example could be mean of a sample (e.g. average height) – what we are interested in are the generalizations (or inferences) from this sample to a population (e.g. average height in population). Due the sampling error we are not…

• Making Sense Out of the Session GPS Data

We collect more and more data and it is becoming increasingly difficult to make meaning out of it. What I would like to do is to present one simple way to make the meaning out of session GPS data using LOF and Clustering. Most GPS units produce multiple features p compared to number of observations n, so we are…

• Importance of Context in Evaluating Wellness Questionnaires

Importance of Context in Evaluating Wellness Questionnaires In the previous post I’ve shared the novel idea on how to ‘aggregate’ wellness categories into positive/negative wellness score. In the video below I talk about importance of context when evaluating the wellness data and I also provide couple of ways to quantify context or smooth it. If you are interested in the wellness questionnaires...

• How to (Pretend to) Be a Better Coach Using Bad Statistics

How to (Pretend to) Be a Better Coach Using Bad Statistics Here is a simple scenario from practice: Coach A uses YOYOIRL1 test and Coach B uses 30-15IFT (for more info see paper by Martin Buchheit, which also stimulated me to write this blog) to gauge improvements in endurance. Coach A: We have improved distance covered in YOYOIRL1 test...

• Analysis of Metabolic Power Data Using Power-Duration Profile in Team Sports

This is the idea I got from the Training and Racing with a Powermeter book by Hunter Allen and Andrew Coggan. It is an excellent and must read book on cycling, but also great book about endurance training in general…

• How to Visualize Test Change Scores for Coaches [Part 2]

To continue the previous How to visualize test change scores for coaches blogpost, here is another way to visualize individual change scores without falling for group averages. This way we can easily see individual ranks in both pre- and post- test, along with change score (which is also color coded). Quite easy to identify the outliers.

• Understanding Inferential Statistics Using Correlation Example

In the following R and knitr experiment/blog post I will be documenting my play with correlation and inferences. I am just reading Discovering Statistics Using R by Andy Field and I am trying to code some staff from the book, plus experiment and see how inferential statistics work.