RSS.Social

Chris Said

follow: @[email protected]

Posts

Beef-o-tuna-tarianism: The low effort way to improve animal welfare

No, we are not underinvested in squishy charities

Bounty hunters for science

Scientific whistleblowers can be compensated for their service

The case for criminalizing scientific misconduct

The respiratory infection study to end all respiratory infection studies

The Air Quality Index doesn’t make any sense

The El Chapo model of AI containment

Double descent in human learning

A map of laboratory-acquired infections

Small correlations can drive large increases in teen depression

The uncertainty pill

Ke (2021) is not logarithmic

10x the live viral count, 10x the infectiousness

Waning immunity and the little paradox of R0

Pandemic virus prediction: All risk and minimal benefit

Teens, loneliness, and the social media paradox

The FDA is 5X too worried about long term credibility

Autism, folic acid, and the trend without a blip

You’re probably measuring your treatment effect incorrectly

Instrumental variables analysis for non-economists

Things that confused me about cross-entropy

Contagiousness sensitivity: The metric that could control the pandemic

Upgrading to MathJax 3.0 after the Kramdown update in Github Pages

Why low sensitivity antigen tests are better than slow PCR tests

Everything I've learned about solar storm risk and EMP attacks

Coronavirus and fragmented data pipelines

The shower problem

Optimizing sample sizes in A/B testing, Part III: Aggregate time-discounted expected lift

Optimizing sample sizes in A/B testing, Part II: Expected lift

Optimizing sample sizes in A/B testing, Part I: General summary

Variance after scaling and summing: One of the most useful facts from statistics

Using your ears and head to escape the Cone Of Confusion

Hyperbolic discounting — The irrational behavior that might be rational after all

Religions as firms

Three questions for social scientists: Internet virtue edition

Keyboard shortcuts I couldn't live without

Learning by flip-flopping

Empirical Bayes for multiple sample sizes

Optimizing things in the USSR

Comparing the opinions of economic experts and the general public

Four pitfalls of hill climbing

How to make polished Jupyter presentations with optional code visibility

New Blog Address

10 classic dialogues you can find on the internet

Across industries, we’re getting better at picking metrics

Independent t-tests and the 83% confidence interval: A useful trick for eyeballing your data.

Jumping quickly between deep directories

How failed replications change our effect size estimates

Jason Mitchell's essay

How I use Twitter

High School STEM curriculum wishlist

Is your job in another state?

My Insight Data Science Project

FAQ for Which Famous Economist

New model of binocular rivalry

Canadian funding models for all

Eight Lessons from the Reproducibility Crisis

In defense of correlation/causation blowhards

New paper on autism

Why are contrast response functions linear in fMRI and nonmonotonic in EEG?

National labs for all the sciences

FAQ

It’s the incentive structure, people! Why science reform must come from the granting agencies.