Jacob Danovitch
Jul 21, 2017 · 1 min read

Thanks for the response! I see your point, but I’m afraid that the “base values” (if that’s the best way to describe it) aren’t mine, as I stated in the article. They belong to NBAMath’s TPA system, which has Westbrook as the leader of defensive points saved (on a cumulative basis, it bears noting). I did my best to rationalize this in my article, but at the end of the day, one errant data point doesn’t invalidate their model.

The real work I did was in converting their points added to wins/dollars. I’m excited to start working on my own model in the coming days, which will hopefully give a solid picture of wins added. I’m likely going to aim my model in the direction of RPM, as you brought up. However, they already had a wins conversion, so that wouldn’t be any fun for me to write about!

I encourage you to check out NBAMath’s TPA model. It’s definitely not perfect, but I find it quite useful.

)
    Jacob Danovitch

    Written by

    First year computer science undergraduate at Carleton . Data and software. Annoying teenager with cringy analytics blog. #HireMeSummer2018