Desk census complete. Of nearly 100 items/groups of items, about 15% were where they belonged (counting all the tech stuff as one group).
About a fifth belonged somewhere else - or just over half if you count what belonged in the bin*.
The remaining approximate third belonged nowhere, which is probably why they ended up on my desk. Still working on finding suitable homes for them all.
*Recycling, compost, logburner, or rubbish. #tidying#desk#statistics
You'll be working with another reviewer to read and run the code, make sure it fills a basic checklist which usually only takes a few hours, and beyond that whatever youd like to focus on. Both of these are collaborative review processes where the goal is to help these packages be usable, well documented, and maintainable for the overall health of free scientific software.
Its fun, I promise! Happy to answer questions and boosts welcome.
Edit: feel free to volunteer as a reply here, DM me, or commenting on those issues! Anyone is welcome! Some experience with the language required, but other than that I can coach you through the rest.
A question for methodologists: How can I conduct a priori power analyses for a 3-way interacion in a 2x2x2 ANOVA (all within-subjects)? #statistics#psychology#methodology
I was excited to present a new workshop for teachers tonight titled "The Geometry of Statistics"! I love that I am continually learning as a teacher, and I'm fortunate to have opportunities to share what I learn with other teachers.
Keynote by the hugely influential Nobel laureate and education economist James Heckman on education policy, data, and an integrated understanding of education and skills and capabilities over the lifecycle.
Broad ranging and a real treat to watch.
UNESCO Conference on Education Data and Statistics, 7 February 2024
What model #statistics should one report after using multiple #imputation and #multilevel regressions, and how are they obtained? I'm using the #mice package in #rstats, and #lme4 on each imputed dataset. When pooling results, summary() yields what I need for each model term, but nothing for the whole model. If I didn't impute but deleted listwise, I would normally report AIC, BIC, Loglik. These are all in the mipo object, for each result for each imputed dataset, but they're not pooled. I'm sure I'm missing something here. Does anyone know an example article where such results are presented neatly?
We're being told by a reviewer that there is a scientific consensus that specificity and sensitivity do not have any statistical meaning if you're not in a diagnosis/prognosis setup. We have a very classical cases (samples from cancer patients) vs controls (samples from cancer-free controls) setup and do not claim what we are doing is directly applicable to a clinical setup.
Is it valid to say 40% of American police officers perpetrate domestic violence?
After half an hour digging through empirical #research I think I can confidently say "no." Why? Because we have no real idea how much DV is perpetrated by cops. Because nobody can really study it with solid methods. Because (IMO, anyway) a lot of scholars are kind of scared of #cops .
One guy testified for Congress in 1991, and he gets cited a lot, but his #ResearchMethods were not perfect. Then the rate of good research on this went down for the next 30 years.
Lots of opinions, "perceptions of...", etc., but `` numbers? I'm currently not finding any I trust a whole lot. One lit review (2016) found estimates of #DomesticViolence rates from 5% to 40%. Another article just said "Probably about the same as the general public," after clearly misreading a couple of previous estimates.
Anyway, nobody knows how much domestic violence police commit, and it sort of feels like the police want it to stay that way.
es ist Samstag, der 27. Januar 2024. Die Sternzeit beträgt: -298927.76865776.
Wir befinden uns hier auf https://lsbt.me
Wir haben aktuell 138 User. Diese haben bisher 18681 Tröts geschrieben. Das sind 135.37 Tröts pro Rüssel.
Es folgt die Weisheit des Tages:
Mancher wird auch für seine Wahrheiten und Siege zu alt; ein zahnloser
Mund hat nicht mehr das Recht zu jeder Wahrheit.
-- Friedrich Wilhelm Nietzsche (Also sprach Zarathustra)
🚀 Dive into the world of statistical magic with TidyDensity's bootstrap_stat_plot()! 📊✨ Uncover the nuances of your data using R with this powerful function. 🤓
Example 1 explores central tendency, visualizing bootstrapped means, mins, maxes, and standard deviations. Example 2 customizes the plot for a cleaner look. 💡
Maraming salamat muli sa Philippine Statistics Authority para sa oportunidad na magbahagi tungkol sa Python at ang gamit nito sa larangan ng pagmamapa!
Last week, we successfully completed a Python and QGIS training attended by participants from different offices, services, and divisions of the PSA.
The five-day course—characterized by BNHR's hands-on approach, exercise-driven methodology, and a strong focus on tangible outcomes—culminated with the participants showcasing Python and QGIS projects that included processing automations and models, custom QGIS scripts and widgets for easier layer styling, as well as interactive maps using Python.
So, people with more knowledge on these things. I have two questions that won’t let go off my head:
Is electricity generally gettting cheaper/more expensive and at what rate per year? When I say generally, I am not talking about short-term government subsidies.
is the number of computing operations/s getting higher for the same amount of electricity spent, and at what rate per year?
Stats fellows, where can I get back-of-the-napkin-number?