Show newer

If you download your Twitter archive it arrives wrapped as a static HTML page, which is not very useful for doing anything with, and worse: it requires the original account to be still active to do useful things like enlarge the images since they use t.co links.

So here's a Python script to convert a Twitter archive to markdown or other formats: github.com/timhutton/twitter-a

Now you can archive your tweets in any way you want.

(not) hot take:

Only people who know or care nothing about freedom and open source and reproducibility in software will use Matlab or Stata.

There is no clear-cut in human hearts, and the "real world" is something that we should respect and adapt our theory to, not the other way around. I feel very lucky to have learnt this from my undergrad supervisor, and to have held tight to it.

Show thread

I know that I have a tendency to trust theory and technology too much, but it is the nuances and subtleties in econ such as this that help me stay focused on the humanity side of it, rather than get lost in the science part of it. I am deeply grateful.

Show thread

Sometimes perfect information helps with decision making, while other times imperfect information helps with mistake/bias correcting. It seems a kind of art to me.

A short example of how to update a replication package.

For those wanting to "unthread", the full post is at aeadataeditor.github.io/posts/

🧵

First time seeing someone commissioning a research paper…

My students often struggle with selection bias and measurement error bias in linear regression models. So I have made a couple of Shiny apps to help visualize these concepts.
Selection bias: apps.biostat.au.dk/stefan/sele
Measurement error: apps.biostat.au.dk/stefan/meas

Feel free to use them in your teaching #rstats #datascience #stats

Code is available at my GitHub.

First post here, so be nice :kirbyroll:

Wow, I did not notice how many stars the repo for my Julia for Econ bootcamp has (310)! Thank you, everyone!

Might as well link em' here for folks too:

GitHub: github.com/cpfiffer/julia-boot

YouTube recordings: youtube.com/playlist?list=PLbu

#julialang #econ

ggplot 3.4.0 is on CRAN now and comes with a few important (potentially breaking) changes, notably with the linewidth argument. You may see a bunch of console output asking you to use "linewidth" instead of "size" for setting line thickness. There's also a change in the defaults for border lines in the sf package's geom_sf(). @thomasp85 provides a helpful overview at the Tidyverse blog: tidyverse.org/blog/2022/11/ggp

Cool air conditioning in bus during winter while no air conditioning in bus during summer. Cool.

I hate ambiguously answered textbook questions so much.

Very entertaining to see people discover Fedi for the first time after all these years…

Exchange student who never dealt with data before: I feel like stuck and lost in the code and books

Me: You just summarised my past ten years

There is no hope, my throat just cannot handle talking aloud two hours straight, no matter how much water is supplied. It is what it is.

However, one thing I did find dislikable about Moodle is that privileged users (including administrators and TAs) can see the IP address for all submissions. Huge user privacy implications.

Show thread

Damn…

Klaus Pforr  
Just wondering how this would have turned out if Elon Musk had bought Elsevier

Just wondering how this would have turned out if Elon Musk had bought Elsevier

Show older
CleverLibre Social

CleverLibre Social is an inclusive social instance for open discussion, learning, and community.
All cultures welcome.
Hate speech and harassment strictly forbidden.