Gregory Roe

🏉 Funded 4-Year PhD Opportunity | RU-InSiGT Project in collaboration with the @RFU, @premrugby, @ThePWR & @catapultsports FIND OUT MORE & APPLY HERE: bit.ly/RU-INGST_PhD

A monumental effort by a huge team to complete the first large replication project in sports and exercise science. Part 1 includes the results of the replication project: doi.org/10.1007/s40279… Part 2 includes reflections: doi.org/10.1007/s40279… @ExPhysStudent @JoeWarne1

Massive publication selection bias in economics? pubmed.ncbi.nlm.nih.gov/38327122/ "After adjusting for publication selection bias, the median probability of the presence of an effect decreased from 99.9% to 29.7% in economics" 😮

📣Our 🆕 paper Causal Inference is Not Just a Statistics Problem is out! @malco_barrett, @travisgerke, and I show that you can have 4 data sets with identical summary stats & visuals but very different data generating mechanisms-statistics alone can't tell you what to adjust for!

Looking for a world class person to join our medical and performance team ⁦@LeicesterTigers⁩. Any questions, please contact me. Please share and retweet. uksport.gov.uk/jobs-in-sport/…

New paper by Cristian Mesquida @JennyMurphy2 @JoeWarne1 and me in the Journal of Sport Sciences: “Publication bias, statistical power and reporting practices in the Journal of Sports Sciences: potential barriers to replicability” tandfonline.com/doi/full/10.10… Some results:

So much discussion of statistical methods is centered on case analysis like "is your output value discrete or continuous?" or "is your output always positive?" But my experience is that the most important question, "does your data behave like a IID sample?", is just not asked.

I want to do a follow-up to the blog series above, focusing on confounded mediation. But until I can get that done, please accept the prior art and join me in the humble epistemic stance of: If we don't state how the variables influence one another, we can't infer anything.

“To say that the world consists of qualities does not entail or imply that it consists of the qualities of our perception.” @BernardoKastrup writes on the demise of scientific materialism and what the view of reality as made up of consciousness entails. iai.tv/articles/reali…

Timeless

Excited to be pulling this event together! Stay tuned for further details. @RFU @TheRFL @SeanScants @annastoDr @JamesWoodward97 @psrve @donbarrell @KathrynDane2 @statman_sean @sportex_dr_amal @LaurenVeronaD

For those interested in the topic of statistical models vs reality, have a look at Stark, "Pay No Attention to the Model Behind the Curtain" link.springer.com/article/10.100…

Congrats Dr @Marco_Zanin_ , it was a privilege to supervise you with @J_Darrall_Jones. Thanks to @SarahRWhitehead and @MarcoBeato1 for the great discussion of his “long” thesis.

I heretofore propose that all p-values between 0.1 and 0.05 shall be described as: "trending away from significance"

NEW PAPER on which and how external load factors 🕺 drive internal load 🔥 during small-sided games 🎮 in professional rugby union 🏉 frontiersin.org/articles/10.33… @GregoryRoe @J_Darrall_Jones @DanWeaving @FrontiersIn #Rugby #sportanalytics #r #rstats

@Shaun_McLaren1 👊

In psychometrics, response bias is the mismatch between a perception (e.g., of effort) and its rating. Non-validated, custom scales like the below introduce conscious bias with RPE and other subjective measures. As a discipline, we need to do so much better

PhD vacancy evaluating contact load in rugby Join @leedsbeckett @Carnegie_Sport working with @WorldRugby @Springboks @TheCurrieCup & international researchers @GregoryRoe @jamesbrown06 @Sharief_H @drkeithstokes @Starling_Linds @Scienceofsport @GTBiomech leedsbeckett.ac.uk/courses/studen…

@Carnegie_Sport and @WorldRugby are looking for a motivated individual to undertake a fully funded PhD to quantify contact load in professional rugby union. leedsbeckett.ac.uk/courses/studen…

New 📑 on the differences among small-sided games 🎮 in a professional rugby union club 🏉 during preseason💥 @GregoryRoe @J_Darrall_Jones @SAGE_Publishing journals.sagepub.com/doi/10.1177/17…