dumbmatter.com

Online home of Jeremy Scheff

A simple explanation for why modeling COVID-19 is hard

Over at FiveThirtyEight there is a great article about why it's so hard to model the effects COVID-19. Basically their answer is that there are many factors that go into a model, but many of them are very uncertain, and many of them are also dynamic. For instance, what is the probability of transmission when an infected person interacts with a non-infected person? There's a lot of uncertainty in that estimate. But also, it's going to change over time. Particularly, as the pandemic worsens, people will likely do more social distancing and other mitigation strategies, resulting in a lower transmission rate.

Tricky stuff to predict precisely! But I think that's not quite the complete picture, and there's an even simpler and clearer explanation.

Read more...


Which NBA players take the most shots with their foot on the three point line?

Which NBA players take the most shots with their foot on the three point line? If you want the answer to that question, check out the post I wrote on the Basketball GM blog.

Why there and not here? I figure, when the hordes of highly interested basketball fans find this spectacular blog post, I'd rather BBGM gets some shine than dumbmatter.com.


The double Dunning-Kruger effect

Wikipedia defines the Dunning-Kruger effect as:

a cognitive bias in which people of low ability have illusory superiority and mistakenly assess their cognitive ability as greater than it is

Look it up on Google Images and you'll find various summary images, like these:

Read more...


Age gaps and death gaps

As you may have noticed, relationships often have age gaps. This is fine, but it does imply that the younger partner is likely to outlive the older partner. Further compounding this problem is that the older partner usually is the man, and men tend to die younger than women to begin with.

So here is a calculator to show the probability distribution of the number of years between the deaths of two partners, based on age and gender. Of course there are many other factors at play besides those two, but this should give you a rough estimate.

Read more...


Side projects galore

God damn, I've been neglecting this blog. It's sad really, because I do have a lot to say. I guess I've just been talking to myself instead of blogging lately, which maybe says something about my mental stability, but whatever. I'm blogging now, and I'm going to blog the fuck out of this blog.

It's 2016. My job is pretty cool in some ways, but in some other ways it bothers me a great deal. It's probably not in my best interest to go into that in great detail here (as if anyone is reading this, right?) so I will leave the rest unsaid, and just get to the broader point. I am someone who cares a great deal about science, engineering, creating cool things, doing things the right way, etc. And when I say "cares a great deal" I mean probably more than I can adequately articulate with my pedestrian writing skills. It's almost like a spiritual thing. So for someone like me, what do you do when your day job is preventing you from attaining your desired level of spiritual satisfaction?

Side projects!

Read more...


The Bishop Sankey Diagram

Or, my best pun ever:


Basic income vs. basic job

Chris Stucchio wrote an article about the differences between basic income and basic job policies, based on relatively straightforward math. Briefly, basic income says give everyone money with no strings attached and get rid of other forms of welfare. Basic job is the same, except anyone who can work is mandated to work, either in a normal job like today or in a New Deal-style government works program.

Chris's main conclusion was that basic job came out looking way better than basic income. Additionally, a major purpose of his post was to encourage other people to play around with the math as well rather than just bloviating. Since I'm a big basic income proponent and have some quibbles with how he came to conclude that basic income doesn't look too good, I will follow his lead and play around with the math.

Read more...


Did Adrian Peterson actually rush for more yards than Eric Dickerson but have it go unnoticed due to measurement error?

Despite miraculously recovering from ACL surgery and successfully leading his team to the playoffs, Adrian Peterson tragically missed the all time rushing record by 9 yards.

...or did he?

Let's think about how the NFL measures yardage. They take the difference between where the ball was before the play and where the ball is after the play, and then they round to the nearest integer. What happens if you rush for half a yard? It'll get recorded as either 0 yards or 1 yard. Spread out over an entire season, and this kind of rounding error can have a big impact.

Read more...


Vote and die: are you more likely to cast the deciding vote in the election, or to die on your way to your polling place?

Vote or die? Or, vote and die?

Here is a calculator that will compare the odds of your single vote swinging the 2012 US presidential election with the odds of you dying on the way to your polling place.

Read more...


Relationship between Ames Straw Poll and Iowa Caucuses results

In recent weeks, there have been a lot of people decrying the importance of the Ames Straw poll, likely because the mainstream media is worried that Ron Paul will win it. Here's one prominent example, titled "The Ames Straw Poll Has Limited Predictive Value". Of course, if you actually read the article, it doesn't really demonstrate what is claimed in the title. So, I wanted to look at this issue a little more systematically. Unfortunately, I got scooped by that bastard Nate Silver who wrote an article about this exact issue this morning, after I had already almost finished mine. So instead, this will be an exercise in open source journalism.

Read more...