Konsta Happonen
Youth researcher. Bayesian surveyor of inner worlds. Tired baritone.
- I don't know who needs to hear this, but nattō omelettes are the perfect breakfast.
- Smartphones are weird because now, if you slightly continue the hand movement that turns off your alarm clock, you might end up watching an entire lecture about statistics before getting out of bed.
- This time I try to explain group-level confounding and some ways to deal with it. Lecture B04 of Statistical Rethinking 2026 - fixed effects, Mundlak machines, latent Mundlak machines, intro to social network analysis and the social relations model. Full lecture list: github.com/rmcelreath/s...
- Reading Kuang's Katabasis (it's about PhD students traveling to hell to get a recommendation letter from their dead advisor). It's just such a spot on description of academia, I feel I've met all the characters somewhere.
- Reposted by Konsta HapponenThe reality is that we have failed to teach, incentivize, and practice principled science, and prioritized quantity, prestige, performative acts and heuristics of success over thoughtfulness, diligence, curiosity, honest exploration, and humility. This is a disaster we have already created.
- Nice, short paper on how adjusting for survey mode might sometimes cause more problems than it solves. Collider bias is fascinating.
- Users of survey data, lovers of DAGs, and general methodological enthusiasts, gather round! I'm so excited to share this new paper, joint work with my brilliant colleagues @rjsilverwood.bsky.social, @pwgtennant.bsky.social, and Liam Wright. 🧵
- Reposted by Konsta HapponenIn sum: all global prevalence rates about gaming addiction/disorder seem to be a partial combination of both gaming *and* gambling prevalence. The same applies to other studies, which use gaming measures in relevant languages. Chinese seems to be a major exception.
- Cool paper and nice example of how the language a study was conducted in can create / ameliorate measurement problems.
- Reposted by Konsta Happonen[Not loaded yet]
- Reposted by Konsta HapponenAfter 5 years I can finally share a full WP of our project conducting cognitive interviews of life satisfaction reporting. Main findings: 1. LS scales are psychometrically valid, but... 2. Standard statistical assumptions made when analysing LS data are not credible. osf.io/gv5e3/files/...
- Reposted by Konsta Happonen[Not loaded yet]
- Reposted by Konsta Happonen[This post could not be retrieved]
- Reposted by Konsta Happonen[Not loaded yet]
- Reposted by Konsta HapponenOUP want $8500 to publish a 400 word letter to the editor 🤣
- Reposted by Konsta HapponenThe trick here is basically to run screaming away from dichotomizing findings and into the warm and loving embrace of the vast language we have for describing uncertainty and scale, interpreting whether it matters accordingly. Use figures that make it clear.
- Reposted by Konsta Happonen[Not loaded yet]
- Vantaa river is not a very impressive river by international (or even national) standards, but it's the river where me and my friends swam when I was growing up.
- It looks like nothing, but I spent four hours making this Ethiopian vegetarian doro wat + injera. Worth every minute.
- The most important skill I learned last year is unrelated to research: I learned how to open a coconut. It's so easy and fresh coconut is so good, I'm almost ashamed I didn't do it earlier.
- Revelation of the year: ice skating is actually kind of fun now that I don't have to do it like I did back at school. It's probably been more than 15 years since I last had skates on before this winter.
- My main gripe with causal inference is that it has made understanding what the abbreviation CI refers to even more confusing than before.
- Reposted by Konsta Happonen[Not loaded yet]
- Reposted by Konsta Happonenhello skyline it is time to post the song of the season ~it's beginning to look a lot like FISHMEN~ www.youtube.com/watch?v=3tTH...
- It seems my family has me all profiled: I got two sets of comics for my birthday. Both came with a botanical illustration of a buttercup species.
- Merry christmas to me: I just reduced the runtime of a nonlinear Stan model from one hour to ~ 15 minutes. Perfect way to slide into the holidays.
- I finally have an excuse to try the sum_to_zero_vector in Stan and it's awesome.
- Reposted by Konsta HapponenGrading and googling hallucinated citations, as one does nowadays, and now that LLMs have been around for a while, I've discovered new horrors: hallucinated journals are now appearing in Google Scholar with dozens of citations bc so many people are citing these fake things
- Reposted by Konsta HapponenThe "smartphones/social media" discourse suffers from some amazing historical amnesia. There was no 2008 financial crisis and no global pandemic starting in 2020, it's all SCREENS SCREENS SCREENS. Major world events? Just the backdrop against which SCREENS happened.
- I recently subscribed to a music streaming service called Presto, and it has made listening to classical music much more enjoyable. Searching by works and rich metadata about albums are missing from the likes of Spotify. I've been blasting Bach, Schubert and Shaw from my headphones all week.
- Reposted by Konsta Happonen[Not loaded yet]
- I am not a fan of cooking, but two food-related things have recently increased my happiness by a factor of >1: getting a rice cooker and learning to open coconuts.
- why. Timezones, not even once. #rstats
- Reposted by Konsta Happonen[Not loaded yet]
- This side project brings me joy: a fully Bayesian model of CO₂ fluxes, where the fluxes (slopes) are a nonlinear function of available photosynthetically active radiation.
- Reposted by Konsta Happonen[Not loaded yet]
- The scientist-statistician was one of the most common professions in 21st century universities. In this era, statistics was seldom conducted by trained statisticians. Instead, subject experts, who possessed hard- and software, were responsible for tasks ranging from study design to causal inference
