Search results for tag #statistics
📺 https://peer.adalta.social/w/mY87PhmiF9NdaQ2bfrWZq1
🔗 [🇩🇪🇺🇸🇫🇷](https://adalta.info/articles/prstn_steam_116324138632636820_fr)
🔗 [ℹ️](https://gstats.app/steam")
L'augmentation des données de jeu confirme une activité utilisateur accrue sur la plateforme Steam.
That weird feeling when grading a #statistics exam: Yes, I guess, but...
Problem: three events that might happen, with probabilities:
- p(A) = .05
- p(B) = .02
- p(C) = .70
Question: what's the probability of at least one happening? (assume all events are non-disjoint and independent of each other)
Easy answer (according to what we've learned so far): .05 + .02 + .70 = .77
Student's answer...
Step 1:
- (1-.05) = .95
- (1-.02) = .98
- (1-.70) = .30
Step 2: (.95)(.98)(.30) = .279
Step 3: 1-.2793 = .721 <-- Student's answer
I stared at that for a bit figuring out what she'd done. I think the logic tracks, at least for how I phrased things. I'm not an expert by any means in probability theory but I think she did this:
- find probability of each event not happening
- find the probability of all of the events not happening (i.e., none of the events)
- find the probability of None of the events not happening
There's some kind of pedagogical lesson here. I suspect it's "Maybe the student should study the provided materials more; however, if you're quick enough to do it, it's also OK to freak out during the open-book/open-notes exam, find a website with a strange process on it, and work out how to apply it to this process."
An interesting explanation of why ‘AI’ generated prose is bland an unnatural. And that is before the other snafus. And some new phrase for my vocabulary, ‘semantic ablation’, ‘metaphoric cleansing’, ‘lexical flattening and (in this context), ‘structural collape'
https://www.theregister.com/2026/02/16/semantic_ablation_ai_writing/
On today's episode of worlds most believable statistics...
"U.S. employers added a surprisingly strong 130,000 jobs last month, but government revisions cut 2024-2025 U.S. payrolls by hundreds of thousands.
The unemployment rate fell to 4.3%, the Labor Department said Wednesday."
https://www.huffpost.com/entry/ap-us-economy-jobs-report_n_698c87c5e4b01dbafe65f9d8
Sooo… weird question. Is anybody aware of a good #statistics package for #Java (or callable from Java, so #Scala, #Kotlin, or other #JVM languages) that supports #PERMANOVA?
Or a way to run #R from Java? #Renjin or #JRI (part of #rJava)? adonis/adonis2 supposedly supports PERMANOVA.
📺 https://peer.adalta.social/w/h7XA6TDhbAFqMNnNEQzZcF
🔗 [🇩🇪🇺🇸🇫🇷](https://p4u.xyz/ID_RY9SHQF4/1)
Neue Statistiken untermauern die anhaltende Marktdominanz der Plattform
📺 https://peer.adalta.social/w/g6KLyKhBwb8QNjVXQcNcGx
🔗 [🇩🇪🇺🇸🇫🇷](https://p4u.xyz/ID__7OT0NWD/1)
Ein quantitativer Sprung in Spielen, Achievements und Spielzeit unterstreicht die anhaltende Dominanz der Plattform.
✨ The #Gstats Global #Update: Quantifying a #Gaming Ecosystem
A single user's data surge reflects the massive, continuous data generation within the #Steam platform.
🇩🇪🇺🇸🇫🇷 🔗 https://p4u.xyz/ID_BWRQBYJ2/1
Fun with Correspondence Analysis and my big new dataset. Starting to wonder if maybe the chronological sequence is BAC, not ABC like Baudou thought.
Our download stats visualization just received an update, with focus on usability and accessibility. You will certainly enjoy finally seeing the names of the apps!
https://stats.izzyondroid.org/
Alt...
Screenshot of the new statistics visualization, showing this year's downloads of Catima
Question: There are maps and statistics which show the median income of each country.
However, are there any similar maps and statistics which show the income at the bottom 20 percentile?
I think this might be a better indicator of human development of a country than the overall median income.
author unknown
Alt...
A photo of 3 black kittens in nature.
Caption: Scientists have proven that only 1 out of 4 cats is good at camouflage
#LabPlot is under continuous #development.
We’ve just introduced a new option to define the y-offset for curves to quickly create #StackedLinePlot in #LabPlot. 🎅 🎄
@labplot@lemmy.kde.social
@opensource
#OpenSource #FreeSoftware #FLOSS #FOSS #DataViz #DataViz #DataAnalysis #Plots #Chart #KDE #Statistics
Alt...
Image: Stacked Line Plot in LabPlot
I am realizing something about #LLM use and teaching: it means, if I want to make sure I'm assessing student learning and not student saying-stuff-to-chatgpt, I can't trust students as much or give them the benefit of the doubt. Tonight a student produced some graphs for her results on a stats project that had an extra variable thrown in that wasn't part of her original hypotheses. It was in her dataset, so it wasn't bizarre, and it made some sense, but there were a few things that in the past I would have said were just students being students: no error bars, odd wording of axis labels, and like that. Historically, these (for me) have been within the bounds of "students kind of missing the boat a bit."
Now I think it could be that or it could be that chatGPT or grok or some other LLM cranked these graphs out, or possibly spit out the instructions for making them in #JASP.
I can't trust the student anymore. I can't give her the benefit of the doubt. There is an ever-present alternative explanation for all faults in student work, and it's a very strong explanation.
I made the last exam for my introductory #statistics course optional. How many of 25 students (current exam averages ranging from 20% to 95%) do you think opted to take the optional exam?
#professor #teaching #HigherEd
| Zero: | 0 |
| 0 (note: this is a numeral not "zero" the word): | 0 |
| None: | 0 |
| Why did you even bother making this poll: | 0 |
The Customer-Service-Corporate-Middle-Management-ification of #higherEd makes me unhappy on a regular basis. The craven approval-seeking and weaponization of student sentiment by quasi-competent (or fully incompetent) "leaders" means my work, year by year, has been consumed more and more by dealing with mostly bullshit student complaints with heavy pressure and subtle job threats from my bosses.
But good things still happen. Two students were just in my office getting help on a #statistics project and they have done some great work. They are also genuinely interested in their results. An absolute superstar in my my statistics course is someone who, through past experiences, I misjudged early on: a women's basketball athlete. She works her ass off and it shows. She's doing extremely well, and she's the person whose assignments make me say, "Why can't the rest of the students be more like this?". I have students in Research Methods doing above-and-beyond stuff to not only check the boxes on their research projects but actually find interesting insights. In another class, a student took me up on a half-assed joke comment and is going to perform an interpretive dance version of two or three related psychological concepts.
Some of the pathological beliefs we attribute to techbros were already present in this view of statistics that started forming over a century ago. Our writing is just data; the real, important object is the “hypothetical infinite population” reflected in a large language model, which at base is a random variable. Stable Diffusion, the image generator, is called that because it is based on latent diffusion models, which are a way of representing complicated distribution functions--the hypothetical infinite populations--of things like digital images. Your art is just data; it’s the latent diffusion model that’s the real deal. The entities that are able to identify the distribution functions (in this case tech companies) are the ones who should be rewarded, not the data generators (you and me).
So much of the dysfunction in today’s machine learning and AI points to how problematic it is to give statistical methods a privileged place that they don’t merit. We really ought to be calling out Fisher for his trickery and seeing it as such.
#AI #GenAI #GenerativeAI #LLM #StableDiffusion #statistics #StatisticalMethods #DiffusionModels #MachineLearning #ML