Graham Macklin

I haven't used chatgpt yet, so I'm interested to see what I can do! My email is graham.macklin@tse-fr.eu

I'd also be happy to look at your code at some point this weekend if that would be helpful

I'm also a little surprised by how much the positive oversample pulls down the upper end of the CI for p, although again that might be a bootstrap artifact

It generally looks good to me! The one thing that stands out are the confidence intervals, especially sensitivity and specificity - they seem a little tighter than I'd expect and the CI for sensitivity doesn't even include the true value. Is that just an artefact of bootstrapping?

It definitely seems like someone should have! But I don't know where. It's pretty far outside what I typically read, though, so that's not particularly informative. If you come across something or write it up yourself, please send it along, I'd love to read a more formal treatment!

Yeah, depending on your priors and how many re-tests you do, your new confidence interval for the prevalence is probably something like 0.039 - 0.047, and that also means that your specificity has a CI of something like ~0.953/0.96 - ~1

But you need significantly more gold-standard tests than 1/prevalence in order to estimate the prevalence in the first place.

I need to write it out more formally to check, but I think that if you have a good measure of the prevalence, then yes. In the extreme scenario where you know the prevalence exactly and get a positive retest on all of the cheap test's positives, then you know that the false negative rate must be 0.

I don't think that it is possible to reliably say anything about the specificity in this scenario. If 1/1000 people have the disease even with a false negative rate of 100% and all 200 tests used in the negative group, there is still over an 80% chance of observing 0 false negatives in your sample.

Everyone was complaining that the Thucydides Trap between the US and China wasn't real but the Trump 2.0 policy will be to demand endless tribute from *allies* and destroy his own position of power, which was also the exact same playbook of the Athenians

Many of us can save a child’s life, if we rely on the best data There are many ways to improve the world, but their cost-effectiveness varies immensely. You can achieve a lot more if you rely on the best data on where to donate.

What is an important fact about the world that you wish more people would know?

Here is my answer: If we rely on the best data, many of us can save a child's life.

And here is my article about it.
ourworldindata.org/cost-effecti...

American democracy is doomed Vox is a general interest news site for the 21st century. Its mission: to help everyone understand our complicated world, so that we can all help shape it. In text, video and audio, our reporters expl...

Say what you will about MattY, but he absolutely cooked here
www.vox.com/2015/3/2/812...

we should fire every single American transit profesional and replace them with Spaniards

Happy thanksgiving everyone

it's gonna turn out that people maximize the utility of making a decision subject to the cost of the decisionmaking itself and we'll all just be back at neoclassical micro 101 but with a turducken of utility functions

People have been puzzling over Scott Bessent's claim that tariffs can't be inflationary — which is, by the way, completely different from Trump's claim that foreigners will pay. The thing is, there is a kind of model here — one that is clear, consistent, and totally false 1/

This is important: Trump's "across the board tariffs" will not be across the board. Companies and industries will besiege the administration asking for exemptions and carve-outs, which will be granted to the ones who find favor with the toddler emperor.

I wrote an intro to the literature on simple mechanisms. Out now in the JEP.

It’s a short (14-page) plain-language summary, designed to get students to the research frontier. 📈📉

pubs.aeaweb.org/doi/pdfplus/...

Insightful and important analysis of the returns and costs of tax audits across the income distribution by Boning, Hendren, and Sprung-Keyser (@bsprungkeyser.bsky.social) now in the QJE (@qjeharvard.bsky.social)

Recent work by Stefanie Stantcheva confirms an old argument by Robert Shiller: people don't think of wage rises and price increases as part of a common process, they attribute wages to their own efforts and prices as an external imposition.

No doubt linked to downward nominal wage rigidity

It is no exaggeration to say that the smearing of Adeel Mangi radicalized me. If this man doesn’t represent the best of America then I don’t know who we are. He must be confirmed. www.nytimes.com/2024/04/05/o...

The conscious embrace and enabling of anti-vax by the GOP leaders, the ones who know better, is probably one of the most unambiguously evil things I’ve seen in my lifetime.

The Democrats’ Shameful, Foolish Surrender on Immigration Kamala Harris apparently believes—wrongly—that she has no influence on anti-immigrant sentiment in America, because she has effectively capitulated to MAGA messaging.

I’m in @tnr.bsky.social arguing for a full, alternate, message-disciplined competing vision of immigration pushed forcefully and cohesively by national Dems

water supplies are a) not a problem in the east b) a big problem in the west that could be more or less solved overnight by cutting livestock feed agriculture by like a fifth. data centers are a rounding error

So US taxpayers can send their subsidy money abroad instead of letting Chinese subsidy money put cheap solar panels on American rooftops.

The obsession with spending gov money to manufacture solar panels is nonsensical.

Here is Vol. 1 of the Bluesky Energy & Environmental Economics starter pack.

If your account is still active at the Nazi Bar, feel free to share there to help get new feeds primed--there are a lot of people here!

Let me know if you'd like to be included in the next batch!

bsky.app/starter-pack...

Of all the examples to choose! A major contributor to the crisis was that utilities could not raise retail rates when their input costs went up.

Anticipating they were not going to be paid for their output, generators shut down.

Market power raised prices, but a *PRICE CAP* turned out the lights!

California’s Exploding Rooftop Solar Cost Shift In 2024, residential PV will shift nearly $4 billion onto others’ bills, more than double the 2020 amount. There’s a lot of anger in California right now about rising electricity prices. Since 2020, r...

My blog post today digs deep on California's $4 billion rooftop solar cost shift, up more than 100% since 2020. Households now get ~20% of their electricity from tooftop PV. Those kWhs don't pay for most fixed costs of the grid and climate policies. energyathaas.wordpress.com/2024/04/22/c...

Blinken Is Sitting on Staff Recommendations to Sanction Israeli Military Units Linked to Killings or Rapes A special State Department panel told Secretary of State Antony Blinken that the U.S. should restrict arms sales to Israeli military units that have been credibly accused of human rights abuses. He ha...

“If we had been applying Leahy...like we do in other countries, maybe you wouldn’t have the IDF filming TikToks of their war crimes now because we have contributed to a culture of impunity,” said Josh Paul, a former director in the State Department"

www.propublica.org/article/isra...

old school political liberalism: still hits