Joe Ornstein

🚨 New R package and paper! 🚨

fuzzylink is a method for merging datasets with non-exact matches on key variables. The paper walks through several useful political science applications--linking voter files, campaign contribution data, and even multilingual records. The package is available on CRAN.

29.08.2025 13:23 — 👍 4    🔁 1    💬 0    📌 1

Screenshot of the linked Quarto website, with input checkboxes to change different conditions for a regression model that predicts economic performance based on US political party, with a reported p-value

I’ve long used FiveThirtyEight’s interactive “Hack Your Way To Scientific Glory” to illustrate the idea of p-hacking when I teach statistics. But ABC/Disney killed the site earlier this month :(

So I made my own with #rstats and Observable and #QuartoPub ! stats.andrewheiss.com/hack-your-way/

20.03.2025 18:30 — 👍 1468    🔁 439    💬 58    📌 30

🦜Do you want to train your stochastic parrot?

➡️ @joeornstein.bsky.social @enblasingame.bsky.social @jaketruscott.bsky.social share best practices for using large language models (LLMs) in social science measurement tasks and processing large text-as-data projects www.cambridge.org/core/journal...

20.01.2025 07:26 — 👍 17    🔁 1    💬 2    📌 0

promptr: Format and Complete Few-Shot LLM Prompts Format and submit few-shot prompts to OpenAI's Large Language Models (LLMs). Designed to be particularly useful for text classification problems in the social sciences. Methods are described in Ornste...

3. 🦜R package alert! 🦜

With promptr, R users can easily format and complete few-shot LLM prompts for document labeling and scaling tasks.

cran.r-project.org/web/packages...

14.01.2025 19:37 — 👍 2    🔁 0    💬 0    📌 0

2a. If you're a social scientist using crowd-coding platforms to label documents in 2025, you're spending 1,000 times more money to ask someone else to put your text into an LLM for you.

14.01.2025 19:37 — 👍 2    🔁 0    💬 1    📌 0

2. When we started the project in fall 2021, our analyses cost a few hundred dollars in API fees. Today, the the same tasks would cost around $3. That's about 1,200 times cheaper than performing the same tasks on crowd-coding platforms.

14.01.2025 19:37 — 👍 2    🔁 0    💬 1    📌 0

1. It's remarkable that, in 2025, GPT-3 still performs as well if not better than GPT-4 and its offshoots at our document labeling and scaling tasks. RLHF is great for making chatbots, but for text-as-data tasks you're often better off with the base models.

14.01.2025 19:37 — 👍 2    🔁 0    💬 1    📌 0

Some thoughts about this paper, on the long-awaited day of its publication:

14.01.2025 19:37 — 👍 3    🔁 1    💬 1    📌 0

How to train your stochastic parrot: large language models for political texts | Political Science Research and Methods | Cambridge Core How to train your stochastic parrot: large language models for political texts

After what felt like ages, very(!) excited to finally see this work in print with @joeornstein.bsky.social & @enblasingame.bsky.social

Link: bit.ly/409THxY

14.01.2025 14:13 — 👍 4    🔁 1    💬 0    📌 0

drake meme. top panel: subject: scheduling committee meeting. bottom panel: YOUR FAVORITE ESTIMAND MIGHT BE UNIDENTIFIED IN OUR MODEL, ACT NOW TO LEARN MORE

there are two profs on my committee who don't respond to emails so i've started turning my subject lines into research clickbait and it's criminally effective

12.12.2023 23:31 — 👍 277    🔁 70    💬 3    📌 4

Joseph T. Ornstein

New website just dropped! joeornstein.github.io

Remarkable how much easier it is to build a site with Quarto than my old blogdown/Hugo monstrosity.

05.10.2023 19:56 — 👍 4    🔁 0    💬 0    📌 0

Cool. Everyone is here now.

21.09.2023 13:51 — 👍 2    🔁 0    💬 0    📌 0