Lightnews — Scholar-powered news

David Johnson @davidblakejohnson.bsky.social · 21h

Guys. 7 with 4 preps across 3 different addresses is a bit much.

David Johnson @davidblakejohnson.bsky.social · 1d

m.youtube.com/watch?v=fUww...

1 1 1

David Johnson @davidblakejohnson.bsky.social · 1d

real footage of me working with brightspace

a black and white drawing of a person holding a fork in front of a computer .

ALT: a black and white drawing of a person holding a fork in front of a computer .

media.tenor.com

David Johnson @davidblakejohnson.bsky.social · 2d

I honestly can't get over how terrible Brightspace is. I miss blackboard so much.

1

David Johnson @davidblakejohnson.bsky.social · 7d

Halfway serious question: Can we call leaders "Authoritarian Christian Nationalists" without getting into trouble? Or does it need to be "Christian Nationalist with Authoritarian leanings"?

1

David Johnson @davidblakejohnson.bsky.social · 8d

btw, when the outcome variable is logged gun sales, a panel regression (county fixed effect) with only year fixed effects has an r^2 of over .9. the within unit r^2 is also near .6.

David Johnson @davidblakejohnson.bsky.social · 8d

You can do the same exercise with actual gun sales! year fixed effects are even more similar across the two outcome variables (gun sales and estimated gun sales).

1

David Johnson @davidblakejohnson.bsky.social · 12d

Oh! The R^2 for a model estimating logged cc permits at the county level using ONLY year and county fixed effects is.....

R-squared = 0.9356
Adj R-squared = 0.9313
Within R-sq. = 0.6761

David Johnson @davidblakejohnson.bsky.social · 12d

ta-da!

Almost parallel!

Which makes perfect sense because not every permit is going to come with a new gun

1 1

David Johnson @davidblakejohnson.bsky.social · 12d

Not great but not bad either. Blows up a little later in the panel ☹

But here is a thought: a lot of these CC permits are going to be renewals. So what if I also control for the number of permits issued 5 years in the past (common permit length)?

1

David Johnson @davidblakejohnson.bsky.social · 12d

Then do the same with our logged gun sales estimates.

If we are right, then both models should produce similar year fixed effects.

Here is what happens when I try it:

1

David Johnson @davidblakejohnson.bsky.social · 12d

@troach.bsky.social and I's shitck is changes in gun sales are national vibes, & refs at some of the leading economic journals don't seem to buy it.

There is a natural test though: estimate logged county-level CC permits using fixed effects panel and only year fixed effects.

1

David Johnson @davidblakejohnson.bsky.social · 14d

~36% of the guns recovered in DC from November 2021 to August 2025 were Glocks.

David Johnson @davidblakejohnson.bsky.social · 15d

I think it is that but also law enforcement. I have a paper that looks at it in detail, FWIIW. Heavily influenced by the Kansas City Gun Experiment.

1

David Johnson @davidblakejohnson.bsky.social · 15d

Watching Time Cop on Netflix. Whew. Movie goes hard.

1

David Johnson @davidblakejohnson.bsky.social · 15d

August and September are generally pretty average in terms of accidents (February is the low).

Hasn’t been this low since COVID.

1

David Johnson @davidblakejohnson.bsky.social · 15d

Also a big drop in traffic accidents.

1

David Johnson @davidblakejohnson.bsky.social · 21d

Just submitted the proofs for my job market paper from 2015.

Whew, what a journey.

1

David Johnson @davidblakejohnson.bsky.social · 27d

I ”jokingly“ suggested to my wife we put this guy out.

After she found out about Kimmel, she became very open to it.

David Johnson @davidblakejohnson.bsky.social · 27d

Gave up resisting it and updated the academic website.

sites.google.com/view/davidbl...

David Blake Johnson

My name is David Blake Johnson. I am an Associate Professor of Economics at the University of Central Missouri, where my research lies at the intersection of applied microeconomics and behavioral econ...

sites.google.com

2

David Johnson @davidblakejohnson.bsky.social · 28d

Use the wayback machine to see how much of the tariff you had to eat! should be easy to find historical prices.

2

David Johnson @davidblakejohnson.bsky.social · 28d

Sadly, I think you are right. Everyone can grasp it, so it ends up sucking all the air out of the room. Lowest common denominator.

David Johnson @davidblakejohnson.bsky.social · Sep 13

This isn’t a new thing. I have paper that used stormfront as a group. Part of the experiment asked students how much the agreed with stormfront’s motto/description. I was taken aback by how much agreement/support there was among undergraduates.

David Johnson @davidblakejohnson.bsky.social · Sep 4

This wasn't surprising to me.

Population tends to change in a linear way, while gun transactions change quite a bit y2y.

In other words, you are taking something that varies a lot and dividing it by something that doesn't, so of course, the numerator is going to dominate.

David Johnson @davidblakejohnson.bsky.social · Sep 4

Got a comment that the accuracy of our gun sales estimates is just due to population (e.g., pop grows -> sales grow).

Big nope there. Correlation between standardized gun sales estimates per capita and NICS gun checks per capita is about .8.

1