Contrary to common wisdom and a sizeable literature, longitudinal research (with a natural experiment) in Australia by @maximananyev.bsky.social et al suggests there is no causal effect of getting a pet on life satisfaction, loneliness, mental health, and general health:

buff.ly/iYkVfCQ

Media ownership and ideological slant: Evidence from Australian newspaper mergers This study examines how media acquisitions by corporate conglomerates influence the political slant of Australian newspapers. Using a comprehensive measure based on the language of over 30 million new...

📰📊Media mergers and political bias

A new study investigates how takeovers of Australian newspapers affect political slant. Analysing 30M+ articles, it found News Corp mergers pushed conservative bias & other acquisitions shifted coverage left.

🔗 doi.org/10.1371/jour...

#MediaBias #SciComm 🧪

Interesting! Thanks!

I think the latest Adobe Creative Suite has such capacity, but I did not use it myself.

Somehow only just became aware of LlooM, a toolkit that uses a combination of clustering and prompts to extract concepts and describe custom datasets — similar to a topic model. Looks nice, with lots of documentation and open colab notebooks!

Has anyone used it?

stanfordhci.github.io/lloom/about/

An abstract: we show that Evangelical movement decreased female labour force participation.

Geographical distribution of Liberty University alumni.

A regression table showing negative effects of Evangelical Christianity on female labour force share

Excited for this year’s Australian Gender Economics Workshop, organised by @alfredopaloyo.com.

I’ll present a paper, co-authored with Michael Poyker and Alexander Yarkin, on the effects of Evangelical movement.

Looking forward to discovering new research and catching up with old and new friends.

Thanks, John! it looks good! We'd have to try it out!

DeepSeek-R1 and exploring DeepSeek-R1-Distill-Llama-8B DeepSeek are the Chinese AI lab who dropped the best currently available open weights LLM on Christmas day, DeepSeek v3. That model was trained in part using their unreleased R1 …

DeepSeek released a whole family of inference-scaling / "reasoning" models today, including distilled variants based on Llama and Qwen

Here are my notes on the new models, plus how I ran DeepSeek-R1-Distill-Llama-8B on my Mac using Ollama and LLM

simonwillison.net/2025/Jan/20/...

Behavioural biologists have known for many years that birds try to combat traffic noise by becoming louder. For example, the Max Planck Institute for Ornithology has found that Berlin nightingales chirp an average of 14 decibels louder than their counterparts in the forest.
😱

Must have been a real mindfuck living in the B.C. times and not knowing what the years were counting down to.

Who Are You? The Art and Science of Measuring Identity As a shop that studies human behavior through surveys and other social scientific techniques, we have a good line of sight into the contradictory nature of human preferences. Here's a look at how we c...

Here's a great essay from my colleagues (including @pollcat.bsky.social & @aebrown.bsky.social) about how @pewresearch.org measures characteristics it's often awkward to ask about, including religion, income, political affiliation & gender.

A meme in honor of one of the most fascinating stories in economic research.

Personal news: my dearest friend and love, Tatiana Ershova, said yes to marrying me.

Are there any #Rstats users with Databricks experience who have opinions about it as a product?

I am NOT a geographical determinist

But…

This map does help us understand why the Khasi hills remained matrilineal

Why might torrential rains help women??

😀

open.substack.com/pub/dralicee...

Why we (usually) don't have to worry about multiple comparisons Applied researchers often find themselves making statistical inferences in settings that would seem to require multiple comparisons adjustments. We challenge the Type I error paradigm that underlies t...

Since it is inefficient to attempt to educate every reviewer individually, I am yeeting into your feed this clear paper from Gelman, Hill, and Yajima on how Bayesians can do even better than correcting for multiple comparisons. arxiv.org/abs/0907.2478

AGEW 2025 6–7 February 2025 University of Wollongong

The keynote speakers for the Australian Gender Economics Workshop are Prof Paola Profeta (Bocconi) and Prof Doris Weichselbaumer (Linz). Also, the website is now live: t.ly/mWzth. Please join us in Wollongong next year!

It's misleading to portray culture as static.

Actually, there's considerable contestation & flux.

While India's urban FLFP is extremely low, Hindu British women work at high rates!!

This tells us something important!!

www.ggd.world/p/can-archit...

Arranged some of my Econ books. There's a system.

We still have a relatively poor understanding of the relationship between evidence and policy. Program evaluation in particular is often motivated by a desire to make policy better. But how effective is program evaluation itself?Michelle Rao's JMP tackles this question. www.michellerao.com/research

These are actually two pictures.

A difference between ChatGPT and Claude in one picture.

INSIDE SCOOP: This book is awesome.

Fantastic! Congratulations, Jan!

I've been a paid subscriber to Alice Evans's brilliant blog for over a year now, and I absolutely love it.

The topics she writes about—gender, identity, status, norms, and beliefs—are close to my research interests.

But beyond that, I believe anyone can benefit from her insatiable curiosity.

to catch a bus you must think like a bus

These high childcare costs are pushing mothers not only out of the workforce but also--and maybe ironically--into political conservatism. Because moms pushed out of paid work often struggle with loss of identity. And because conservative Christian moms' groups often step in to fill that void. 1/🧵

ANU's Research School of Economics has three excellent job market candidates on the market this year, doing very interesting work. Take a look. 👀
rse.anu.edu.au/research/job...

Australian economists on this platform.

Thanks @petrkuzmin.bsky.social for the photo.