Started a blog recently; there might be the odd thing of interest from time to time. As the title says it's "A random collection of thoughts about books, fishing and statistics". The odd posting about guitars might crop up too.
https://t.co/5hwVVywv2y
@cricketjim1 Stokes said "Over a long period of time, if you're playing really good cricket, you're getting results that you want, you'll end up finding yourself in the final and in the mix."
as Eng weren't near the final each cycle he knows Eng haven't been playing good cricket often enough.
📢 😃Thrilled to share this Preprint with you‼️ We (28🧠-Scientists) propose 4 Ways to increase Effect Sizes (not only Sample Size) to enhance the Replicability of Neuroimaging Research on Individual Differences. https://t.co/x8CsDCK6EA
"The sum score is not just a poor man’s test score but provides a defensible ordinal approximation of the latent variable under surprisingly general conditions." 3/3
An excellent, readable & important psychometrics paper (not a combination of words that I have often used or seen elsewhere). Sijtsma, K., Ellis, J. L., & Borsboom, D. (2024). https://t.co/AryDaqcwhl @BorsboomDenny Highly quotable too 1/2
"<Sum scores> may have been intuitive at the start of psychometrics more than a century ago but ... it proved a highly fortunate hunch that has been substantiated through a century of psychometric theory formation." 2/3
@WG_RumblePants Can’t disagree (much) with your list. I might dislike some of the characters. Maybe a bit batter heavy so perhaps have separate lists for batters and bowlers (Botham might win for the 80s in both lists)
@AnnieChave Another bad feature is the duplication with the blast. Why have 2 essentially 20-20 competitions in our crowded summer. Pick one and ditch the other. I’m told the atmosphere at the 100 is more family friendly so maybe that’s the one to keep.
@AnnieChave A bad feature is the lack of obvious team loyalty for fans in many counties. If you are a Yorkshire supporter say then which team should you follow? Yorkers are spread across several franchises and they move about on a regular basis.
@jgeller_phd It’s almost entirely arbitrary and it is easy to construct situations where lower levels of multicollinearity damage your ability to interpret the output