NBA player career projections

As the NBA basketball season gets started, FiveThirtyEight has their player projections for how much each will contribute to their team not just this year but in future seasons. The system is called CARMELO. It stands for Career-Arc Regression Model Estimator with Local Optimization but mostly an excuse to name it CARMELO.

Nate Silver describes how they produced the projections and its similarities to his work in 2003 with baseball player projections. Two main steps: define player skills, and then find similar players in NBA history and look at how they performed.

And naturally, attach a whole lot of uncertainty.

Finally, bringing it all together: win-loss record projections for every team.

Favorites

Reviving the Statistical Atlas of the United States with New Data

Due to budget cuts, there is no plan for an updated atlas. So I recreated the original 1870 Atlas using today’s publicly available data.

Unemployment in America, Mapped Over Time

Watch the regional changes across the country from 1990 to 2016.

Watching the growth of Walmart – now with 100% more Sam’s Club

The ever so popular Walmart growth map gets an update, and yes, it still looks like a wildfire. Sam’s Club follows soon after, although not nearly as vigorously.

A Day in the Life of Americans

I wanted to see how daily patterns emerge at the individual level and how a person’s entire day plays out. So I simulated 1,000 of them.