They already do acknowledge socioeconomic (and other confounding factors) in the analysis.
The primary analysis they perform is a ‘Propensity Score Match’ which is a technique used specifically to address for confounders in observational studies, and they do report balanced cohorts.
Still they write in their discussion “Although we adjus-
ted for several available proxies of socioeconomic and lifestyle status,
direct measures of income, insurance coverage, or out-of-pocket
payment were not available in the TriNetX database. Residual confounding related to unmeasured socioeconomic factors, therefore,
cannot be excluded“
Given the size of the dataset, the effect size, significance and sensitivity testing they did I think it’s very strong evidence for GLP1s causing this and it would be very very surprising to me to see the effect disappear even if they had perfect socioeconomic data.
With so many signs of improvement, even if some of them happens to be just flukes, from so many different areas, it feels like a penicillin moment. And i suppose penicillin also was initially mostly available to the ones with better socio-economy.
Your exact intuition about the implausibility of many large effect sizes is called the “Piranha problem” by my favourite statistician Andrew Gelman first here in a blog post:
https://statmodeling.stat.columbia.edu/2017/12/15/eats/
Perhaps its not quite 'dumb' enough for you, and they have yet to ship so no one can really speak to the quality but this product https://clicksphone.com/communicator might fit your needs. I'm thinking to get one myself but not yet decided. Will probably wait for a review or two.
People I know will google that information when they care. Or are already aware for product categories they care about like buying a SkiDoo vs Polaris.
But also there’s an app for that:
https://www.oscanadaapp.ca/
Interestingly this was found by a “hobbyist tiler”, David Smith, who is the first author. He was interviewed on how he found it in this YouTube video: https://youtu.be/4HHUGnHcDQw?si=VsHLqVUdw6ihERg2
No, nothing quite like HN (aggregator) exists that I've found, which is unfortunate. In this space a lot it seems most of the discussion happens on twitter, discord, or between blog posts and for the most part not in comment sections. Additionally med/bio is such a wide field I get the sense most people stick to their niche and struggle to keep up with that. However for news sites and latest:
Ball corporation, the largest manufacturer of aluminum cans, commissioned a study of the environmental impact of aluminum cans against cartons, PET, and glass:
and if you go to page 121, you can see figure 5-6 "Global Warming Potential [kg CO2 eq.] per gallon of fill volume, cradle-to-grave incl. transports, US, TRACI 2.1" which shows that for non-carbonated beverages the 16.9 oz clear PET bottle has the lowest total lice cycle impact, by a fairly large margin. The paragraph following the figure:
"The 16.9oz PET bottle for non-carbonated water has the lowest impact overall due to its extremely thin-wall design. The second place among non-carbonated drinks packaging is a close match between aluminum cans and beverage cartons, with very similar overall burdens. Glass bottles, by a large margin, come in last. Among options for carbonated drinks, aluminum performs strongest, followed by PET bottles and finally glass. The low mass and high recycled content of aluminum cans enable consistently low impacts of this packaging format. The lightweight nature of the PET bottles make them a highly efficient packaging format, where the majority of climate change impacts are coming from the fossil-based raw materials"
CO2 is only one measure of environmental impact. Pollution is a very big problem for disposable beverage containers, and the good thing about aluminum is that it is highly recyclable and also has a significant enough scrap value that it incentivizes collecting the waste instead of discharging it into the environment.
This is (unsurprisingly!) also in that source:
> Aluminum cans have relatively high MCI scores of ~0.7, which reflects the highest average recycled content (55% of can stock, 3% of end and tab stock) and end of life recycling rate (69%) of all beverage packaging materials.
Now if only Canada’s largest bookstor, Indigo, would do this. Instead their CEO is intent on moving in the opposite direction.
“Mr. Ruis is planning a major expansion in categories such as cookware, tech gadgets and beauty products. “It’s not four or five things; it’s about 400 or 500 that we’re busily beavering away, trying to bring them to market,” he says, sitting in a boardroom at Indigo’s Toronto offices.”
I recently visited my local Indigo after having not gone for a couple of years, and was surprised at how little space was dedicated to bookshelves. And even those shelves were surprisingly empty.
I'm sure that those other categories have higher margins, but I can't help but think that Indigo is shooting itself in the foot in the long term: none of those other products are paricularly good in quality or value and I can't imagine people would go to Indigo for many of those products. Instead, I get the sense that people go to Indigo for books, and see and buy those products while they are in the store. With an ever-decreasing selection of books, who knows how they're going to keep up the traffic required.
Given the size of the dataset, the effect size, significance and sensitivity testing they did I think it’s very strong evidence for GLP1s causing this and it would be very very surprising to me to see the effect disappear even if they had perfect socioeconomic data.