Here's a few recent papers you might find helpful or fun if you're interested in replication in social science.

These papers help us answer the question: Given finite resources, what papers should we replicate?

A thread 🧵 Paper #1

"Making replication mainstream"

DOI:

This is a nice paper with commentaries (36!!) and a response. I really enjoy these and this is a good one!

The Ioannidis comment is especially 🔥.

See also Kochari and Ostarek, and others. doi.org/10.1017/S01405…

🆕 "The Data Availability Policies of Political Science Journals" is on @socarxiv

1️⃣ 20% of political science journals require sharing data.

2️⃣We should remain mindful of the effectiveness and rarity of requiring data sharing.

👇links + discussion below You can find the preprint on @socarxiv; the paper is currently under review.

CC: @RoeHarley

osf.io/preprints/soca…

🚨 New Paper (Open Access!) 🚨

Twitter title: "{marginaleffects} Does This Thing Well (And You've Never Fully Appreciated It)"

doi.org/10.1017/psrm.2…
I've taught MLE for a long time. Since the start, I struggled to connect the carefully constructed theory of MLE with the "average-of-simulations" point estimate of King, Tomz, and Wittenberg.

I had to tell students: "this kinda works." 🤷‍♂️

This paper makes the connection.

Do you use logistic regression? If so, you’ll want to read the thread below.

⚠️ Warning: Memes, charts, #rstats, and practical advice ahead. If you don’t like Twitter shenanigans, I’ll give it away.

For logit models with small-to-moderate samples (maybe N < 1,000), you should consider Firth’s penalized estimator.

I talk about it in this paper with Kelly McCaskey (open access!).

cambridge.org/core/journals/…