Ilmiötä voi käyttää ehtymättömänä helpotuksen lähteenä: 1. Mene tarkastamaan viimeisimmät luvut. 2. Havainnoi, että pahin on ohi. 3. Toista ensi viikolla uudelleen, jättäen huomiotta että mennyt data muuttuu joka päivä, kun viivästyneitä lukuja lisätään siihen.
2/
Alan huolestua koronatutkijoiden tilannekuvasta, mistä olin ajatellut #WELGO-väen olevan hyvin perillä. Keskustelussa kaikki näyttivät olevan samanmielisiä siitä, että pandemian opit koskevat (ylimitoitettuja) rajoituksia.
Ehkä parhaat palat olivat muussa seminaarissa, mutta siitä striimattiin vain paneelikeskustelu, josta jäi kuva, ettei oheisessa twiitissä kuvattua tilannetta ole olemassa.
Paikalla olleet: jakakaa tilaisuuden huippukohdat!
Say you want to figure out which beliefs to target in a behaviour change campaign, and as part of the evaluation look at correlations between two self-reports, like beliefs and intentions:
A Tale of Non-linearity 🧵👇
1/
In the process of Confidence-Interval Based Estimation of Relevance (CIBER) you aim to find variables that are both a) correlated with something more "downstream" (such as behaviour or behavioural intentions), and b) changeable (not maxed out already)
It's not uncommon to end up with highly skewed distributions. This doesn't of course always happen, but it does sometimes, even though people try to craft their questions such that the middle answer is the most common, and the rest are symmetrically less so.
1/4 In the absence of a physical law forcing boundaries on a metric, it becomes fat-tailed, i.e. a single observation can be more important than everything that came before, combined.
2/4 There is this parameter called alpha, which quantifies the thickness of the tail, i.e. how bad the situation is compared to one where you can happily just use normal approximations and non-parametrics.
3/4 Turns out that the alpha exponent is actually pretty well-behaved, that is, you don't need a ton of data to estimate it, and it gives you veeeeery important information as regards the actions you should be taking.
I wondered, what kind of OBJECTIVE data I'd have that could show periodicity and chaos in time (like in fig) and realised I could play around with the inter-response intervals from our study, where office workers were beeped 5/day to answer motivation surveys
SHOULD WE TREAT FEVER [in children]? Thread based on a quick literature search for personal interest's sake.
I'm either missing major pieces of evidence, or the #1 Finnish authority for health information gives strange advice. /1
Some background: The aforementioned organisation, @DuodecimFi, disseminates information to doctors and the general public. Their article [terveyskirjasto.fi/terveyskirjast…] is v. positive towards fever reduction and says there are no adverse effects. /2
According to Duodecim, you should use antipyretics (paracetamol, ibuprofen etc.) for fever higher than 38.7°C/101.7°F. In Helsinki, we also have consultation service which tells you that for 2-year-olds, you need to medically lower fever if ear measure reaches 37.8°C. /3
Ok, the Russians were here, and I didn't understand a thing. Next up @trishankkarthik, who's claiming Quantum Supremacy isn't a racist thing. Let's see how this goes.
Taking an integrative non-segregationist view, he's explaining that all computers are basically the same. #RWRI
Ok, so, point is that some things are logically impossible. There is a perfect answer but it takes a shitton of time (which you don't have) to find it out... But if you're given an answer, much easier to figure out if it's right or not. #RWRI