Ruben ~ Kedara.eu<p><a href="https://kedara.social/tags/til" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TIL</span></a> at work: sometimes, it may be okay to force a linear regression through the origin.<br><br>Normally speaking, you should use "y=ax+b" as model for your linear regressions and correlation indices. Because fixing "b=0" introduces a bias in the estimator "a".<br><br>However, today, someone argued that if you're using a regression to measure the predictive power of a model with respect to measurement data, you should fix "b=0".<br><br>Now, intuitively this makes some sense, but I haven't been able to find clear proof pro or against it.<br><br>So, if you know more about this *and* have relevant references to papers to backup your claim, I'd very much love to hear from you. Statistics is not really my field.<br><br><a href="https://kedara.social/tags/correlation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>correlation</span></a> <a href="https://kedara.social/tags/regression" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>regression</span></a> <a href="https://kedara.social/tags/stats" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>stats</span></a> <a href="https://kedara.social/tags/statistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>statistics</span></a> <a href="https://kedara.social/tags/math" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>math</span></a> <a href="https://kedara.social/tags/maths" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>maths</span></a></p>
#correlation
0 posts0 participants0 posts today
To all the people who are scared of 5G.
Replied in thread
@GottaLaff
NOTE that there is a HUGE flaw in this study due to #causation vs #correlation. The people being studied were all in higher-risk groups ALREADY, and a large percentage of them would have been on a #diet which required sugar substitutes-- and most of those #diets would have included #erythritol.
#Diabetes is already a high-risk factor for #heartproblems and #stroke. My husband is #TypeII and almost every #LowCarb and #SugarFree drink he likes (besides water) uses #erythritol for sweetening.
There is almost no escaping it for him.
This study was inherently flawed & very slanted, and the reporting on it has been even worse.
Calorie Control CouncilCCC Statement on “The Artificial Sweetener Erythritol and Cardiovascular Event Risk” - Calorie Control CouncilA study was published in Nature Medicine entitled, “The Artificial Sweetener Erythritol and Cardiovascular Event Risk,” in which the authors sought to examine potential links between the sugar substitute erythritol and atherothrombotic disease risk. The findings indicate that varying levels of erythritol found in the body were associated with increased risk of cardiovascular events and could […]
Mumblemumblemumbleentropymumblemumblemehfuhgeddaboudit.
.
.
.
.
.
.
.
.
.
.
.
.
(I wrote that as a response to some FaceBook post that stated that people who confuse causality with correlation will die. I kind of like it more as a stand-alone post though.)
Replied in thread
@strange_new_words I had no idea about the #correlation between #iambic #pentameter and the #human heart.
I just listened to Ghirawen's heart. It's the same thing for #kangaroos.
I wonder whether #Russian #hearts are the same as #humans?
Amazing.
The last two times we visited my young nephews in Canberra, my son broke his arm playing chasies.
They're about to come and stay, so now we're having a conversation about why #correlation does not equal #causation.
Continued thread
Les personnes qui adorent tant asséner « #corrélation n'est pas #causalité » ont bizarrement oublié d'appliquer leur formule. Le fait que Greenpeace s'oppose au riz doré ne prouve pas qu'elle ait une responsabilité dans le délai pour les premières récoltes.
20/
Bewickwren 
Almost 20 years after the adoption of #hydraulic #fracturing began to supercharge US production of oil and gas, there’s growing evidence of a #correlation between the industry’s activities and an array of #health #problems ranging from childhood cancer and the premature death of elderly people to respiratory issues and endocrine disruption.
https://e360.yale.edu/features/fracking-gas-chemicals-health-pennsylvania
Yale E360As Evidence Mounts, New Concerns About Fracking and HealthTwo decades after the advent of fracking, a growing number of studies are pointing to a link between gas wells and health problems, particularly among children and the elderly. Researchers are now calling for new regulations restricting where wells can be located.