After three years of telling my class that I wish R had Stata's `teffects`, I went and did it :-) github.com/kylebutts/te...

GitHub - kylebutts/teffects-r: teffects in R

teffects in R . Contribute to kylebutts/teffects-r development by creating an account on GitHub.

github.com

Last minute semester prep and I find this paper. Adding to my slides ASAP!

A quote that I think is particularly relevant in thinking about AI doing writing for us. From Deirdre McCloskey's brilliant Economical Writing www.deirdremccloskey.com/docs/pdf/Art...

Another day, another DID paper review where the authors "randomize treatment across locations" as a robustness check. *Sigh*

Anyone want to see what a DID "paper mill" I've discovered while refereeing?

TIL you can calculate the mean and the variance in one pass through a vector 🤯 Really nice article showing how: nullbuffer.com/articles/wel...

Come be a razorback! We are hiring two positions this year at the U of Arkansas! Macro/General Equilibrium: www.aeaweb.org/joe/listing.... Applied Micro: www.aeaweb.org/joe/listing.... Northwest Arkansas is consistently ranked one of the best places to live. Here's some highlights!

Does anyone have really good examples of a github repository for a research paper. Trying to get good examples for a lesson I'm giving

github.com/kylebutts/vs... If you are using vscode and stata, you should try out my extension. It uses interactive window which let's you write in a `.do` file but get a notebook type experience.

The answer is all 0s !!! what a frustrating choice !!!!

Kyle Butts@kylefbutts.bsky.social · 2y ago

Stata quiz. what do you think the output of `tab` will be? ``` sysuse auto, replace reg mpg i.rep78 if rep78 == 2, nocons predict xb tab xb if rep78 != 2 ```

Stata quiz. what do you think the output of `tab` will be? ``` sysuse auto, replace reg mpg i.rep78 if rep78 == 2, nocons predict xb tab xb if rep78 != 2 ```

kylebutts.com/blog/2025-04... A short blog post for efficient stats coding. All about the importance of dimensionality when doing matrix operations ft. 100x speed-up of my code

Kyle Butts

Kyle Butts -- Urban Economics and Applied Econometrics

kylebutts.com

TIL how to download census data (www2.census.gov) super simply. Finder: Go > Connect to Server > ftp://ftp2.census.gov/. Login as guest and 🤯

great little explanation on why to avoid passive voice refactoringenglish.com/chapters/pas...

R tip: If you run code but forget to save it in a variable, you can use `.Last.value` in the console. More, if you want to copy the result to your clipboard, use `clipr::write_last_clip`:

🚨 The "penguins" data is coming to the base #rstats{datasets} in 4.5.0! @ellakaye.co.uk & @HeathrTurnr.fosstodon.org.ap.brid.gy r prepared an adapted and a raw version of the data set based on the {palmerpenguins} 📦 by @allisonhorst.bsky.social @apreshill.com and Kristen Gorman. 📈 Scatter plot:

snow day in Fayetteville

👀 github.com/posit-dev/po...

Positron Assistant by georgestagg · Pull Request #6361 · posit-dev/positron

Initial Positron Assistant scaffolding. FAO @jmcphers.

github.com

Quick tip: If you store a pdf on GitHub, like this: github.com/kylebutts/Ge... You can make an easy to view link by replacing `github.com/` with `nbviewer.org/github/` and it looks like this: nbviewer.org/github/kyleb...

You can tell companies’ AI projects are going really well because every app is bait-and-switching their most commonly pressed button with something called like “Answers By Glorp” to get people to even accidentally use it

judge: “so you said the true vote share is in this interval 95% of the time? how could that be true if the true vote share is not in that interval”

The New Republic@newrepublic.com · 2y ago

Donald Trump is suing the Iowa paper because he’s still mad about an election poll he didn’t like. The paper isn’t standing for it.

Working on a new R package. Looking for applications that do two things: 1. DID with y to show an effect 2. DID with X to show a possible “mechanism” of why treatment changed y This could be a published paper or a paper you're working on (that I might help make "fancier" / cooler !!)

Is there a better sign of AI hype than MICROSOFT creating a package to convert docx/pptx -> md USING CHAT GPT ????https://github.com/microsoft/markitdown

never felt so seen

Now would be a great time for overleaf users (my coauthors) to delete their account and stop making me use the bad web app

The Environmental Inequality Lab is hiring 2 new pre-docs to join our team! We do research in environmental economics but those with interests in labor/public/urban/spatial/development economics should def apply. Apply here: tinyurl.com/EIL-pre-doc @AereOrg

Pre-Doctoral Fellow, Department of Economics and Frank Batten School of Leadership & Public Policy in Charlottesville, Virginia, United States of America | Research at University of Virginia

Apply for Pre-Doctoral Fellow, Department of Economics and Frank Batten School of Leadership & Public Policy job with University of Virginia in Charlottesville, Virginia, United States of America. Res...

tinyurl.com

Working on my applied metrics course; Here are my figures using Ashenfelter's dip (1978 paper)

In Judge FE style settings, how many observations are usually available per judge? Is there ever settings with few number of observations?

Been formalizing a lot of my workflow into R packages. Today, I have added `tikzsave` to `kfbmisc` package for making figures: ggplot() -> tikzpicture -> pre-compiled into pdf (using latex themes) gist.github.com/kylebutts/9c...

Metrics question: I have a simple regression: y_i = \beta x_i + u_i y_i is an estimated quantity from a survey and I have the standard error on that estimate. What's the "correct" way to upweight observations with small standard errors?