🔖 Week 09 - Appendix

DS202 - Data Science for Social Scientists

I found the following videos which contains precisely the type of visualisations I wanted to share with you. I hope it helps to complement your understanding of Principal Component Analysis.

Indicative Watching

The equations behind Principal Component Analysis

Key takeaway: PCA is a way to change the “coordinates” of the data.

Simple ilustrations and an example using base R

🌟 A must-watch Julia Silge tidyverse+tidymodel tutorial using PCA

• Watch it also with the goal to reinforce the ideas behind data pre-processing
• If you like this, follow Julia Silge on social media.

(Optional) PCA but also learn about a non-linear dimensionality reduction: UMAP

(Optional) A bit unrelated but here is an intro to tidymodels by … 🥁 … Julia Silge!