 Okay, this is just a short r-video on density estimation. The go-to method for density estimation is KDE. This is an alternative called average shitted histograms. Most of the time, this is going to be as accurate as you need, but it's also a little bit more computationally efficient compared to KDE. It's a non-parametric method and I just wanted to give a high-level overview of this method. I'm not going to go for every line in this script. I actually got this script from a book called Statistical Computing with R. All I wanted to show is what the smoothing looks like, how average shitted histogram works at a high level. I'm just going to source this script. The main parameter that controls the smoothing is M. This is how many shifted histograms are being averaged over. So in M equals 1, the average shifted histogram line is shown in this tomato color and so it's outlining a standard histogram. Now if I change that parameter to 2, at the midpoint of those bins, there's some averaging going on so things are broken up a little bit into two histograms that are now a little bit offset. Maybe something that might be a little more realistic is 14. It's a little bit more on the low side still, but you start to see the smoothing happening and a nice non-parametric density being built. I think I've heard some people going up to 40 maybe on the smoothing parameter. There's always a trade-off with with going a little bit too high. Let's see what 40 looks like. Yeah, that looks pretty smooth. This is the average shifted histogram and it is a fantastic compute efficient reliable method for estimating densities. I hope you enjoyed watching this video and we'll see you next time.